diff options
Diffstat (limited to 'tools/perf')
332 files changed, 15278 insertions, 4606 deletions
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index db11478e30b4..ac841bc5c35b 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -47,7 +47,8 @@ man5dir=$(mandir)/man5 man7dir=$(mandir)/man7 ASCIIDOC=asciidoc -ASCIIDOC_EXTRA = --unsafe +ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf +ASCIIDOC_HTML = xhtml11 MANPAGE_XSL = manpage-normal.xsl XMLTO_EXTRA = INSTALL?=install @@ -55,6 +56,14 @@ RM ?= rm -f DOC_REF = origin/man HTML_REF = origin/html +ifdef USE_ASCIIDOCTOR +ASCIIDOC = asciidoctor +ASCIIDOC_EXTRA = -a compat-mode +ASCIIDOC_EXTRA += -I. -rasciidoctor-extensions +ASCIIDOC_EXTRA += -a mansource="perf" -a manmanual="perf Manual" +ASCIIDOC_HTML = xhtml5 +endif + infodir?=$(prefix)/share/info MAKEINFO=makeinfo INSTALL_INFO=install-info @@ -73,10 +82,12 @@ ifeq ($(_tmp_tool_path),) missing_tools = $(ASCIIDOC) endif +ifndef USE_ASCIIDOCTOR _tmp_tool_path := $(call get-executable,$(XMLTO)) ifeq ($(_tmp_tool_path),) missing_tools += $(XMLTO) endif +endif # # For asciidoc ... @@ -264,9 +275,17 @@ clean: $(MAN_HTML): $(OUTPUT)%.html : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ - $(ASCIIDOC) -b xhtml11 -d manpage -f asciidoc.conf \ + $(ASCIIDOC) -b $(ASCIIDOC_HTML) -d manpage \ + $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ + mv $@+ $@ + +ifdef USE_ASCIIDOCTOR +$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : %.txt + $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ + $(ASCIIDOC) -b manpage -d manpage \ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ mv $@+ $@ +endif $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml $(QUIET_XMLTO)$(RM) $@ && \ @@ -274,7 +293,7 @@ $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml $(OUTPUT)%.xml : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ - $(ASCIIDOC) -b docbook -d manpage -f asciidoc.conf \ + $(ASCIIDOC) -b docbook -d manpage \ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ mv $@+ $@ @@ -321,13 +340,13 @@ howto-index.txt: howto-index.sh $(wildcard howto/*.txt) mv $@+ $@ $(patsubst %,%.html,$(ARTICLES)) : %.html : %.txt - $(QUIET_ASCIIDOC)$(ASCIIDOC) -b xhtml11 $*.txt + $(QUIET_ASCIIDOC)$(ASCIIDOC) -b $(ASCIIDOC_HTML) $*.txt WEBDOC_DEST = /pub/software/tools/perf/docs $(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ - sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b xhtml11 - >$@+ && \ + sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b $(ASCIIDOC_HTML) - >$@+ && \ mv $@+ $@ # UNIMPLEMENTED diff --git a/tools/perf/Documentation/asciidoctor-extensions.rb b/tools/perf/Documentation/asciidoctor-extensions.rb new file mode 100644 index 000000000000..d148fe95c0c4 --- /dev/null +++ b/tools/perf/Documentation/asciidoctor-extensions.rb @@ -0,0 +1,29 @@ +require 'asciidoctor' +require 'asciidoctor/extensions' + +module Perf + module Documentation + class LinkPerfProcessor < Asciidoctor::Extensions::InlineMacroProcessor + use_dsl + + named :chrome + + def process(parent, target, attrs) + if parent.document.basebackend? 'html' + %(<a href="#{target}.html">#{target}(#{attrs[1]})</a>\n) + elsif parent.document.basebackend? 'manpage' + "#{target}(#{attrs[1]})" + elsif parent.document.basebackend? 'docbook' + "<citerefentry>\n" \ + "<refentrytitle>#{target}</refentrytitle>" \ + "<manvolnum>#{attrs[1]}</manvolnum>\n" \ + "</citerefentry>\n" + end + end + end + end +end + +Asciidoctor::Extensions.register do + inline_macro Perf::Documentation::LinkPerfProcessor, :linkperf +end diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index c635eab6af54..e8c972f89357 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -21,7 +21,7 @@ If there is no debug info in the object, then annotated assembly is displayed. OPTIONS ------- -i:: ---input=:: +--input=<file>:: Input file name. (default: perf.data unless stdin is a fifo) -d:: @@ -55,6 +55,9 @@ OPTIONS --vmlinux=<file>:: vmlinux pathname. +--ignore-vmlinux:: + Ignore vmlinux files. + -m:: --modules:: Load module symbols. WARNING: use only with -k and LIVE kernel. @@ -69,7 +72,9 @@ OPTIONS --stdio:: Use the stdio interface. ---stdio-color:: +--stdio2:: Use the stdio2 interface, non-interactive, uses the TUI formatting. + +--stdio-color=<mode>:: 'always', 'never' or 'auto', allowing configuring color output via the command line, in addition to via "color.ui" .perfconfig. Use '--stdio-color always' to generate color even when redirecting @@ -84,7 +89,7 @@ OPTIONS --gtk:: Use the GTK interface. -C:: ---cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can +--cpu=<cpu>:: Only report samples for the list of CPUs provided. Multiple CPUs can be provided as a comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. Default is to report samples on all CPUs. @@ -113,6 +118,15 @@ OPTIONS --group:: Show event group information together +--percent-type:: + Set annotation percent type from following choices: + global-period, local-period, global-hits, local-hits + + The local/global keywords set if the percentage is computed + in the scope of the function (local) or the whole data (global). + The period/hits keywords set the base the percentage is computed + on - the samples period or the number of samples (hits). + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index 73c2650bd0db..f6de0952ff3c 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -48,6 +48,9 @@ OPTIONS --purge=:: Purge all cached binaries including older caches which have specified path from the cache. +-P:: +--purge-all:: + Purge all cached binaries. This will flush out entire cache. -M:: --missing=:: List missing build ids in the cache for the specified file. @@ -59,7 +62,9 @@ OPTIONS exactly same build-id, that is replaced by new one. It can be used to update kallsyms and kernel dso to vmlinux in order to support annotation. - +-l:: +--list:: + List all valid binaries from cache. -v:: --verbose:: Be more verbose. diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index 822414235170..095aebdc5bb7 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -116,7 +116,7 @@ and calls standard perf record command. Following perf record options are configured by default: (check perf record man page for details) - -W,-d,--sample-cpu + -W,-d,--phys-data,--sample-cpu Unless specified otherwise with '-e' option, following events are monitored by default: diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 5b4fff3adc4b..32f4a898e3f2 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -334,6 +334,11 @@ annotate.*:: 99.93 │ mov %eax,%eax + annotate.offset_level:: + Default is '1', meaning just jump targets will have offsets show right beside + the instruction. When set to '2' 'call' instructions will also have its offsets + shown, 3 or higher will show offsets for all instructions. + hist.*:: hist.percentage:: This option control the way to calculate overhead of filtered entries - diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt index 90bb4aabe4f8..c87180764829 100644 --- a/tools/perf/Documentation/perf-data.txt +++ b/tools/perf/Documentation/perf-data.txt @@ -1,5 +1,5 @@ perf-data(1) -============== +============ NAME ---- diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt index 721a447f046e..b80c84307dc9 100644 --- a/tools/perf/Documentation/perf-ftrace.txt +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -1,5 +1,5 @@ perf-ftrace(1) -============= +============== NAME ---- diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt index cf9f4040ea5c..f3c620951f6e 100644 --- a/tools/perf/Documentation/perf-kallsyms.txt +++ b/tools/perf/Documentation/perf-kallsyms.txt @@ -1,5 +1,5 @@ perf-kallsyms(1) -============== +================ NAME ---- diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt index 479fc3261a50..85b8ac695c87 100644 --- a/tools/perf/Documentation/perf-kmem.txt +++ b/tools/perf/Documentation/perf-kmem.txt @@ -25,6 +25,10 @@ OPTIONS --input=<file>:: Select the input file (default: perf.data unless stdin is a fifo) +-f:: +--force:: + Don't do ownership validation + -v:: --verbose:: Be more verbose. (show symbol address, etc) @@ -61,7 +65,7 @@ OPTIONS default, but this option shows live (currently allocated) pages instead. (This option works with --page option only) ---time:: +--time=<start>,<stop>:: Only analyze samples within given time window: <start>,<stop>. Times have the format seconds.microseconds. If start is not given (i.e., time string is ',x.y') then analysis starts at the beginning of the file. If diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index e2a897ae3596..236b9b97dfdb 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -18,6 +18,10 @@ various perf commands with the -e option. OPTIONS ------- +-d:: +--desc:: +Print extra event descriptions. (default) + --no-desc:: Don't print descriptions. @@ -25,11 +29,13 @@ Don't print descriptions. --long-desc:: Print longer event descriptions. +--debug:: +Enable debugging output. + --details:: Print how named events are resolved internally into perf events, and also any extra expressions computed by perf stat. - [[EVENT_MODIFIERS]] EVENT MODIFIERS --------------- @@ -124,7 +130,11 @@ The available PMUs and their raw parameters can be listed with For example the raw event "LSD.UOPS" core pmu event above could be specified as - perf stat -e cpu/event=0xa8,umask=0x1,name=LSD.UOPS_CYCLES,cmask=1/ ... + perf stat -e cpu/event=0xa8,umask=0x1,name=LSD.UOPS_CYCLES,cmask=0x1/ ... + + or using extended name syntax + + perf stat -e cpu/event=0xa8,umask=0x1,cmask=0x1,name=\'LSD.UOPS_CYCLES:cmask=0x1\'/ ... PER SOCKET PMUS --------------- @@ -141,7 +151,13 @@ on the first memory controller on socket 0 of a Intel Xeon system Each memory controller has its own PMU. Measuring the complete system bandwidth would require specifying all imc PMUs (see perf list output), -and adding the values together. +and adding the values together. To simplify creation of multiple events, +prefix and glob matching is supported in the PMU name, and the prefix +'uncore_' is also ignored when performing the match. So the command above +can be expanded to all memory controllers by using the syntaxes: + + perf stat -C 0 -a imc/cas_count_read/,imc/cas_count_write/ -I 1000 ... + perf stat -C 0 -a *imc*/cas_count_read/,*imc*/cas_count_write/ -I 1000 ... This example measures the combined core power every second @@ -224,7 +240,7 @@ perf also supports group leader sampling using the :S specifier. perf record -e '{cycles,instructions}:S' ... perf report --group -Normally all events in a event group sample, but with :S only +Normally all events in an event group sample, but with :S only the first event (the leader) samples, and it only reads the values of the other events in the group. diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 4be08a1e3f8d..f8d2167cf3e7 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -28,25 +28,46 @@ OPTIONS <command>...:: Any command you can specify in a shell. +-i:: +--input=<file>:: + Input file name. + +-f:: +--force:: + Don't do ownership validation + -t:: ---type=:: +--type=<type>:: Select the memory operation type: load or store (default: load,store) -D:: ---dump-raw-samples=:: +--dump-raw-samples:: Dump the raw decoded samples on the screen in a format that is easy to parse with one sample per line. -x:: ---field-separator:: +--field-separator=<separator>:: Specify the field separator used when dump raw samples (-D option). By default, The separator is the space character. -C:: ---cpu-list:: - Restrict dump of raw samples to those provided via this option. Note that the same - option can be passed in record mode. It will be interpreted the same way as perf - record. +--cpu=<cpu>:: + Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a + comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. Default + is to monitor all CPUS. +-U:: +--hide-unresolved:: + Only display entries resolved to a symbol. + +-p:: +--phys-data:: + Record/Report sample physical addresses + +RECORD OPTIONS +-------------- +-e:: +--event <event>:: + Event selector. Use 'perf mem record -e list' to list available events. -K:: --all-kernel:: @@ -56,12 +77,15 @@ OPTIONS --all-user:: Configure all used events to run in user space. ---ldload:: +-v:: +--verbose:: + Be more verbose (show counter open errors, etc) + +--ldlat <n>:: Specify desired latency for loads event. --p:: ---phys-data:: - Record/Report sample physical addresses +In addition, for report all perf report options are valid, and for record +all perf record options. SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 3eea6de35a38..246dee081efd 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -57,6 +57,9 @@ OPTIONS FP mode, "dwarf" for DWARF mode, "lbr" for LBR mode and "no" for disable callgraph. - 'stack-size': user stack size for dwarf mode + - 'name' : User defined event name. Single quotes (') may be used to + escape symbols in the name from parsing by shell and tool + like this: name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\'. See the linkperf:perf-list[1] man page for more parameters. @@ -91,7 +94,7 @@ OPTIONS "perf report" to view group events together. --filter=<filter>:: - Event filter. This option should follow a event selector (-e) which + Event filter. This option should follow an event selector (-e) which selects either tracepoint event(s) or a hardware trace PMU (e.g. Intel PT or CoreSight). @@ -150,7 +153,7 @@ OPTIONS --exclude-perf:: Don't record events issued by perf itself. This option should follow - a event selector (-e) which selects tracepoint event(s). It adds a + an event selector (-e) which selects tracepoint event(s). It adds a filter expression 'common_pid != $PERFPID' to filters. If other '--filter' exists, the new filter expression will be combined with them by '&&'. @@ -191,9 +194,16 @@ OPTIONS -i:: --no-inherit:: Child tasks do not inherit counters. + -F:: --freq=:: - Profile at this frequency. + Profile at this frequency. Use 'max' to use the currently maximum + allowed frequency, i.e. the value in the kernel.perf_event_max_sample_rate + sysctl. Will throttle down to the currently maximum allowed frequency. + See --strict-freq. + +--strict-freq:: + Fail if the specified frequency can't be used. -m:: --mmap-pages=:: @@ -308,7 +318,11 @@ can be provided. Each cgroup is applied to the corresponding event, i.e., first to first event, second cgroup to second event and so on. It is possible to provide an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have corresponding events, i.e., they always refer to events defined earlier on the command -line. +line. If the user wants to track multiple events for a specific cgroup, the user can +use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'. + +If wanting to monitor, say, 'cycles' for a cgroup and also for system wide, this +command line can be used: 'perf stat -e cycles -G cgroup_name -a -e cycles'. -b:: --branch-any:: diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 907e505b6309..474a4941f65d 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -80,6 +80,7 @@ OPTIONS - comm: command (name) of the task which can be read via /proc/<pid>/comm - pid: command and tid of the task - dso: name of library or module executed at the time of sample + - dso_size: size of library or module executed at the time of sample - symbol: name of function executed at the time of sample - symbol_size: size of function executed at the time of sample - parent: name of function matched to the parent regex filter. Unmatched @@ -296,6 +297,9 @@ OPTIONS --vmlinux=<file>:: vmlinux pathname +--ignore-vmlinux:: + Ignore vmlinux files. + --kallsyms=<file>:: kallsyms pathname @@ -354,7 +358,8 @@ OPTIONS Path to objdump binary. --group:: - Show event group information together. + Show event group information together. It forces group output also + if there are no groups defined in data file. --demangle:: Demangle symbol names to human readable form. It's enabled by default, @@ -367,7 +372,7 @@ OPTIONS Use the data addresses of samples in addition to instruction addresses to build the histograms. To generate meaningful output, the perf.data file must have been obtained using perf record -d -W and using a - special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See + special event -e cpu/mem-loads/p or -e cpu/mem-stores/p. See 'perf mem' for simpler access. --percent-limit:: @@ -472,6 +477,15 @@ include::itrace.txt[] Display monitored tasks stored in perf data. Displaying pid/tid/ppid plus the command string aligned to distinguish parent and child tasks. +--percent-type:: + Set annotation percent type from following choices: + global-period, local-period, global-hits, local-hits + + The local/global keywords set if the percentage is computed + in the scope of the function (local) or the whole data (global). + The period/hits keywords set the base the percentage is computed + on - the samples period or the number of samples (hits). + include::callchain-overhead-calculation.txt[] SEE ALSO diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt index c7e50f263887..63f938b887dd 100644 --- a/tools/perf/Documentation/perf-sched.txt +++ b/tools/perf/Documentation/perf-sched.txt @@ -1,5 +1,5 @@ perf-sched(1) -============== +============= NAME ---- @@ -104,8 +104,8 @@ OPTIONS for 'perf sched timehist' kallsyms pathname -g:: ---no-call-graph:: - Do not display call chains if present. +--call-graph:: + Display call chains if present (default on). --max-stack:: Maximum number of functions to display in backtrace, default 5. diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt index 142606c0ec9c..5a1f68122f50 100644 --- a/tools/perf/Documentation/perf-script-perl.txt +++ b/tools/perf/Documentation/perf-script-perl.txt @@ -1,5 +1,5 @@ perf-script-perl(1) -================== +=================== NAME ---- diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index 51ec2d20068a..0fb9eda3cbca 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -610,6 +610,32 @@ Various utility functions for use with perf script: nsecs_str(nsecs) - returns printable string in the form secs.nsecs avg(total, n) - returns average given a sum and a total number of values +SUPPORTED FIELDS +---------------- + +Currently supported fields: + +ev_name, comm, pid, tid, cpu, ip, time, period, phys_addr, addr, +symbol, dso, time_enabled, time_running, values, callchain, +brstack, brstacksym, datasrc, datasrc_decode, iregs, uregs, +weight, transaction, raw_buf, attr. + +Some fields have sub items: + +brstack: + from, to, from_dsoname, to_dsoname, mispred, + predicted, in_tx, abort, cycles. + +brstacksym: + items: from, to, pred, in_tx, abort (converted string) + +For example, +We can use this code to print brstack "from", "to", "cycles". + +if 'brstack' in dict: + for entry in dict['brstack']: + print "from %s, to %s, cycles %s" % (entry["from"], entry["to"], entry["cycles"]) + SEE ALSO -------- linkperf:perf-script[1] diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 7730c1d2b5d3..afdafe2110a1 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -228,14 +228,15 @@ OPTIONS For sample events it's possible to display misc field with -F +misc option, following letters are displayed for each bit: - PERF_RECORD_MISC_KERNEL K - PERF_RECORD_MISC_USER U - PERF_RECORD_MISC_HYPERVISOR H - PERF_RECORD_MISC_GUEST_KERNEL G - PERF_RECORD_MISC_GUEST_USER g - PERF_RECORD_MISC_MMAP_DATA* M - PERF_RECORD_MISC_COMM_EXEC E - PERF_RECORD_MISC_SWITCH_OUT S + PERF_RECORD_MISC_KERNEL K + PERF_RECORD_MISC_USER U + PERF_RECORD_MISC_HYPERVISOR H + PERF_RECORD_MISC_GUEST_KERNEL G + PERF_RECORD_MISC_GUEST_USER g + PERF_RECORD_MISC_MMAP_DATA* M + PERF_RECORD_MISC_COMM_EXEC E + PERF_RECORD_MISC_SWITCH_OUT S + PERF_RECORD_MISC_SWITCH_OUT_PREEMPT Sp $ perf script -F +misc ... sched-messaging 1414 K 28690.636582: 4590 cycles ... @@ -303,6 +304,9 @@ OPTIONS --show-lost-events Display lost events i.e. events of type PERF_RECORD_LOST. +--show-round-events + Display finished round events i.e. events of type PERF_RECORD_FINISHED_ROUND. + --demangle:: Demangle symbol names to human readable form. It's enabled by default, disable with --no-demangle. diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 823fce7674bb..b10a90b6a718 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -49,6 +49,13 @@ report:: parameters are defined by corresponding entries in /sys/bus/event_source/devices/<pmu>/format/* + Note that the last two syntaxes support prefix and glob matching in + the PMU name to simplify creation of events accross multiple instances + of the same type of PMU in large systems (e.g. memory controller PMUs). + Multiple PMU instances are typical for uncore PMUs, so the prefix + 'uncore_' is also ignored when performing this match. + + -i:: --no-inherit:: child tasks do not inherit counters @@ -109,6 +116,22 @@ Do not aggregate counts across all monitored CPUs. print counts using a CSV-style output to make it easy to import directly into spreadsheets. Columns are separated by the string specified in SEP. +--table:: Display time for each run (-r option), in a table format, e.g.: + + $ perf stat --null -r 5 --table perf bench sched pipe + + Performance counter stats for 'perf bench sched pipe' (5 runs): + + # Table of individual measurements: + 5.189 (-0.293) # + 5.189 (-0.294) # + 5.186 (-0.296) # + 5.663 (+0.181) ## + 6.186 (+0.703) #### + + # Final result: + 5.483 +- 0.198 seconds time elapsed ( +- 3.62% ) + -G name:: --cgroup name:: monitor only in the container (cgroup) called "name". This option is available only @@ -118,7 +141,11 @@ can be provided. Each cgroup is applied to the corresponding event, i.e., first to first event, second cgroup to second event and so on. It is possible to provide an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have corresponding events, i.e., they always refer to events defined earlier on the command -line. +line. If the user wants to track multiple events for a specific cgroup, the user can +use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'. + +If wanting to monitor, say, 'cycles' for a cgroup and also for system wide, this +command line can be used: 'perf stat -e cycles -G cgroup_name -a -e cycles'. -o file:: --output file:: @@ -142,10 +169,23 @@ perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- m -I msecs:: --interval-print msecs:: -Print count deltas every N milliseconds (minimum: 10ms) +Print count deltas every N milliseconds (minimum: 1ms) The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals. Use with caution. example: 'perf stat -I 1000 -e cycles -a sleep 5' +--interval-count times:: +Print count deltas for fixed number of times. +This option should be used together with "-I" option. + example: 'perf stat -I 1000 --interval-count 2 -e cycles -a' + +--interval-clear:: +Clear the screen before next interval. + +--timeout msecs:: +Stop the 'perf stat' session and print count deltas after N milliseconds (minimum: 10 ms). +This option is not supported with the "-I" option. + example: 'perf stat --time 2000 -e cycles -a' + --metric-only:: Only print computed metrics. Print them in a single line. Don't show any raw values. Not supported with --per-thread. @@ -246,6 +286,16 @@ taskset. --no-merge:: Do not merge results from same PMUs. +When multiple events are created from a single event specification, +stat will, by default, aggregate the event counts and show the result +in a single row. This option disables that behavior and shows +the individual events and counts. + +Multiple events are created from a single event specification when: +1. Prefix or glob matching is used for the PMU name. +2. Aliases, which are listed immediately after the Kernel PMU events + by perf list, are used. + --smi-cost:: Measure SMI cost if msr/aperf/ and msr/smi/ events are supported. @@ -263,20 +313,38 @@ Users who wants to get the actual value can apply --no-metric-only. EXAMPLES -------- -$ perf stat -- make -j +$ perf stat -- make + + Performance counter stats for 'make': + + 83723.452481 task-clock:u (msec) # 1.004 CPUs utilized + 0 context-switches:u # 0.000 K/sec + 0 cpu-migrations:u # 0.000 K/sec + 3,228,188 page-faults:u # 0.039 M/sec + 229,570,665,834 cycles:u # 2.742 GHz + 313,163,853,778 instructions:u # 1.36 insn per cycle + 69,704,684,856 branches:u # 832.559 M/sec + 2,078,861,393 branch-misses:u # 2.98% of all branches + + 83.409183620 seconds time elapsed + + 74.684747000 seconds user + 8.739217000 seconds sys + +TIMINGS +------- +As displayed in the example above we can display 3 types of timings. +We always display the time the counters were enabled/alive: + + 83.409183620 seconds time elapsed - Performance counter stats for 'make -j': +For workload sessions we also display time the workloads spent in +user/system lands: - 8117.370256 task clock ticks # 11.281 CPU utilization factor - 678 context switches # 0.000 M/sec - 133 CPU migrations # 0.000 M/sec - 235724 pagefaults # 0.029 M/sec - 24821162526 CPU cycles # 3057.784 M/sec - 18687303457 instructions # 2302.138 M/sec - 172158895 cache references # 21.209 M/sec - 27075259 cache misses # 3.335 M/sec + 74.684747000 seconds user + 8.739217000 seconds sys - Wall-clock time elapsed: 719.554352 msecs +Those times are the very same as displayed by the 'time' tool. CSV FORMAT ---------- diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 8a32cc77bead..114fda12aa49 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -55,7 +55,9 @@ Default is to monitor all CPUS. -F <freq>:: --freq=<freq>:: - Profile at this frequency. + Profile at this frequency. Use 'max' to use the currently maximum + allowed frequency, i.e. the value in the kernel.perf_event_max_sample_rate + sysctl. -i:: --inherit:: @@ -65,6 +67,9 @@ Default is to monitor all CPUS. --vmlinux=<path>:: Path to vmlinux. Required for annotation functionality. +--ignore-vmlinux:: + Ignore vmlinux files. + -m <pages>:: --mmap-pages=<pages>:: Number of mmap data pages (must be a power of two) or size diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 33a88e984e66..115db9e06ecd 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -63,6 +63,31 @@ filter out the startup phase of the program, which is often very different. --uid=:: Record events in threads owned by uid. Name or number. +-G:: +--cgroup:: + Record events in threads in a cgroup. + + Look for cgroups to set at the /sys/fs/cgroup/perf_event directory, then + remove the /sys/fs/cgroup/perf_event/ part and try: + + perf trace -G A -e sched:*switch + + Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc + _and_ sched:sched_switch to the 'A' cgroup, while: + + perf trace -e sched:*switch -G A + + will only set the sched:sched_switch event to the 'A' cgroup, all the + other events (raw_syscalls:sys_{enter,exit}, etc are left "without" + a cgroup (on the root cgroup, sys wide, etc). + + Multiple cgroups: + + perf trace -G A -e sched:*switch -G B + + the syscall ones go to the 'A' cgroup, the sched:sched_switch goes + to the 'B' cgroup. + --filter-pids=:: Filter out events for these pids and for 'trace' itself (comma separated list). @@ -92,6 +117,9 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. --sched:: Accrue thread runtime and provide a summary at the end of the session. +--failure:: + Show only syscalls that failed, i.e. that returned < 0. + -i:: --input:: Process events from a given perf data file. diff --git a/tools/perf/Documentation/perf-version.txt b/tools/perf/Documentation/perf-version.txt new file mode 100644 index 000000000000..e207b7cfca26 --- /dev/null +++ b/tools/perf/Documentation/perf-version.txt @@ -0,0 +1,24 @@ +perf-version(1) +=============== + +NAME +---- +perf-version - display the version of perf binary + +SYNOPSIS +-------- +'perf version' [--build-options] + +DESCRIPTION +----------- +With no options given, the 'perf version' prints the perf version +on the standard output. + +If the option '--build-options' is given, then the status of +compiled-in libraries are printed on the standard output. + +OPTIONS +------- +--build-options:: + Prints the status of compiled-in libraries on the + standard output. diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index f7d85e89a98a..dfb218feaad9 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -111,8 +111,8 @@ A perf_header_string with the CPU architecture (uname -m) A structure defining the number of CPUs. struct nr_cpus { - uint32_t nr_cpus_online; uint32_t nr_cpus_available; /* CPUs not yet onlined */ + uint32_t nr_cpus_online; }; HEADER_CPUDESC = 8, @@ -153,10 +153,18 @@ struct { HEADER_CPU_TOPOLOGY = 13, String lists defining the core and CPU threads topology. +The string lists are followed by a variable length array +which contains core_id and socket_id of each cpu. +The number of entries can be determined by the size of the +section minus the sizes of both string lists. struct { struct perf_header_string_list cores; /* Variable length */ struct perf_header_string_list threads; /* Variable length */ + struct { + uint32_t core_id; + uint32_t socket_id; + } cpus[nr]; /* Variable length records */ }; Example: @@ -485,10 +493,5 @@ in pmu-tools parser. This allows to read perf.data from python and dump it. quipper The quipper C++ parser is available at -https://chromium.googlesource.com/chromiumos/platform2 - -It is under the chromiumos-wide-profiling/ subdirectory. This library can -convert a perf data file to a protobuf and vice versa. +http://github.com/google/perf_data_converter/tree/master/src/quipper -Unfortunately this parser tends to be many versions behind and may not be able -to parse data files generated by recent perf. diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 225454416ed5..7902a5681fc8 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -84,10 +84,10 @@ endif # has_clean endif # MAKECMDGOALS # -# The clean target is not really parallel, don't print the jobs info: +# Explicitly disable parallelism for the clean target. # clean: - $(make) + $(make) -j1 # # The build-test target is not really parallel, don't print the jobs info, diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0dfdaa9fa81e..f6d1a03c7523 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -27,6 +27,8 @@ NO_SYSCALL_TABLE := 1 # Additional ARCH settings for ppc ifeq ($(SRCARCH),powerpc) NO_PERF_REGS := 0 + NO_SYSCALL_TABLE := 0 + CFLAGS += -I$(OUTPUT)arch/powerpc/include/generated LIBUNWIND_LIBS := -lunwind -lunwind-ppc64 endif @@ -52,6 +54,8 @@ endif ifeq ($(SRCARCH),arm64) NO_PERF_REGS := 0 + NO_SYSCALL_TABLE := 0 + CFLAGS += -I$(OUTPUT)arch/arm64/include/generated LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 endif @@ -66,14 +70,14 @@ ifeq ($(NO_PERF_REGS),0) endif ifneq ($(NO_SYSCALL_TABLE),1) - CFLAGS += -DHAVE_SYSCALL_TABLE + CFLAGS += -DHAVE_SYSCALL_TABLE_SUPPORT endif # So far there's only x86 and arm libdw unwind support merged in perf. # Disable it on all other architectures in case libdw unwind # support is detected in system. Add supported architectures # to the check. -ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm powerpc s390)) +ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390)) NO_LIBDW_DWARF_UNWIND := 1 endif @@ -205,8 +209,7 @@ ifdef PYTHON_CONFIG PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil - PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) - PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS)) + PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) endif @@ -344,12 +347,16 @@ else ifneq ($(feature-dwarf_getlocations), 1) msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157); else - CFLAGS += -DHAVE_DWARF_GETLOCATIONS + CFLAGS += -DHAVE_DWARF_GETLOCATIONS_SUPPORT endif # dwarf_getlocations endif # Dwarf support endif # libelf support endif # NO_LIBELF +ifeq ($(feature-glibc), 1) + CFLAGS += -DHAVE_GLIBC_SUPPORT +endif + ifdef NO_DWARF NO_LIBDW_DWARF_UNWIND := 1 endif @@ -633,6 +640,7 @@ else else LDFLAGS += $(PERL_EMBED_LDFLAGS) EXTLIBS += $(PERL_EMBED_LIBADD) + CFLAGS += -DHAVE_LIBPERL_SUPPORT $(call detected,CONFIG_LIBPERL) endif endif @@ -666,25 +674,11 @@ else ifneq ($(feature-libpython), 1) $(call disable-python,No 'Python.h' (for Python 2.x support) was found: disables Python support - please install python-devel/python-dev) else - ifneq ($(feature-libpython-version), 1) - $(warning Python 3 is not yet supported; please set) - $(warning PYTHON and/or PYTHON_CONFIG appropriately.) - $(warning If you also have Python 2 installed, then) - $(warning try something like:) - $(warning $(and ,)) - $(warning $(and ,) make PYTHON=python2) - $(warning $(and ,)) - $(warning Otherwise, disable Python support entirely:) - $(warning $(and ,)) - $(warning $(and ,) make NO_LIBPYTHON=1) - $(warning $(and ,)) - $(error $(and ,)) - else - LDFLAGS += $(PYTHON_EMBED_LDFLAGS) - EXTLIBS += $(PYTHON_EMBED_LIBADD) - LANG_BINDINGS += $(obj-perf)python/perf.so - $(call detected,CONFIG_LIBPYTHON) - endif + LDFLAGS += $(PYTHON_EMBED_LDFLAGS) + EXTLIBS += $(PYTHON_EMBED_LIBADD) + LANG_BINDINGS += $(obj-perf)python/perf.so + CFLAGS += -DHAVE_LIBPYTHON_SUPPORT + $(call detected,CONFIG_LIBPYTHON) endif endif endif @@ -854,7 +848,7 @@ ifndef NO_JVMTI ifeq ($(feature-jvmti), 1) $(call detected_var,JDIR) else - $(warning No openjdk development package found, please install JDK package) + $(warning No openjdk development package found, please install JDK package, e.g. openjdk-8-jdk, java-1.8.0-openjdk-devel) NO_JVMTI := 1 endif endif @@ -892,6 +886,8 @@ endif # Among the variables below, these: # perfexecdir +# perf_include_dir +# perf_examples_dir # template_dir # mandir # infodir @@ -911,6 +907,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative)) mandir = share/man infodir = share/info perfexecdir = libexec/perf-core +perf_include_dir = lib/perf/include +perf_examples_dir = lib/perf/examples sharedir = $(prefix)/share template_dir = share/perf-core/templates STRACE_GROUPS_DIR = share/perf-core/strace/groups @@ -941,6 +939,8 @@ bindir_SQ = $(subst ','\'',$(bindir)) mandir_SQ = $(subst ','\'',$(mandir)) infodir_SQ = $(subst ','\'',$(infodir)) perfexecdir_SQ = $(subst ','\'',$(perfexecdir)) +perf_include_dir_SQ = $(subst ','\'',$(perf_include_dir)) +perf_examples_dir_SQ = $(subst ','\'',$(perf_examples_dir)) template_dir_SQ = $(subst ','\'',$(template_dir)) htmldir_SQ = $(subst ','\'',$(htmldir)) tipdir_SQ = $(subst ','\'',$(tipdir)) @@ -951,14 +951,20 @@ srcdir_SQ = $(subst ','\'',$(srcdir)) ifneq ($(filter /%,$(firstword $(perfexecdir))),) perfexec_instdir = $(perfexecdir) +perf_include_instdir = $(perf_include_dir) +perf_examples_instdir = $(perf_examples_dir) STRACE_GROUPS_INSTDIR = $(STRACE_GROUPS_DIR) tip_instdir = $(tipdir) else perfexec_instdir = $(prefix)/$(perfexecdir) +perf_include_instdir = $(prefix)/$(perf_include_dir) +perf_examples_instdir = $(prefix)/$(perf_examples_dir) STRACE_GROUPS_INSTDIR = $(prefix)/$(STRACE_GROUPS_DIR) tip_instdir = $(prefix)/$(tipdir) endif perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir)) +perf_include_instdir_SQ = $(subst ','\'',$(perf_include_instdir)) +perf_examples_instdir_SQ = $(subst ','\'',$(perf_examples_instdir)) STRACE_GROUPS_INSTDIR_SQ = $(subst ','\'',$(STRACE_GROUPS_INSTDIR)) tip_instdir_SQ = $(subst ','\'',$(tip_instdir)) @@ -1006,6 +1012,8 @@ $(call detected_var,ETC_PERFCONFIG_SQ) $(call detected_var,STRACE_GROUPS_DIR_SQ) $(call detected_var,prefix_SQ) $(call detected_var,perfexecdir_SQ) +$(call detected_var,perf_include_dir_SQ) +$(call detected_var,perf_examples_dir_SQ) $(call detected_var,tipdir_SQ) $(call detected_var,srcdir_SQ) $(call detected_var,LIBDIR) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 012328038594..5224ade3d5af 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -296,7 +296,7 @@ PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/ PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/ export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP -python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so +python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT)python/perf*.so PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources) PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPI) @@ -364,7 +364,8 @@ LIBS = -Wl,--whole-archive $(PERFLIBS) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive ifeq ($(USE_CLANG), 1) CLANGLIBS_LIST = AST Basic CodeGen Driver Frontend Lex Tooling Edit Sema Analysis Parse Serialization - LIBCLANG = $(foreach l,$(CLANGLIBS_LIST),$(wildcard $(shell $(LLVM_CONFIG) --libdir)/libclang$(l).a)) + CLANGLIBS_NOEXT_LIST = $(foreach l,$(CLANGLIBS_LIST),$(shell $(LLVM_CONFIG) --libdir)/libclang$(l)) + LIBCLANG = $(foreach l,$(CLANGLIBS_NOEXT_LIST),$(wildcard $(l).a $(l).so)) LIBS += -Wl,--start-group $(LIBCLANG) -Wl,--end-group endif @@ -383,6 +384,8 @@ export INSTALL SHELL_PATH SHELL = $(SHELL_PATH) +linux_uapi_dir := $(srctree)/tools/include/uapi/linux + beauty_outdir := $(OUTPUT)trace/beauty/generated beauty_ioctl_outdir := $(beauty_outdir)/ioctl drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c @@ -430,6 +433,12 @@ 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_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl) + $(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@ + vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh @@ -473,7 +482,7 @@ $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_D $(PYTHON_WORD) util/setup.py \ --quiet build_ext; \ mkdir -p $(OUTPUT)python && \ - cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/ + cp $(PYTHON_EXTBUILD_LIB)perf*.so $(OUTPUT)python/ please_set_SHELL_PATH_to_a_more_modern_shell: $(Q)$$(:) @@ -565,6 +574,7 @@ 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) \ $(vhost_virtio_ioctl_array) \ $(madvise_behavior_array) \ $(perf_ioctl_array) \ @@ -708,15 +718,15 @@ TAG_FILES= ../../include/uapi/linux/perf_event.h TAGS: $(QUIET_GEN)$(RM) TAGS; \ - $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs etags -a $(TAG_FILES) + $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs etags -a $(TAG_FILES) tags: $(QUIET_GEN)$(RM) tags; \ - $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs ctags -a $(TAG_FILES) + $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs ctags -a $(TAG_FILES) cscope: $(QUIET_GEN)$(RM) cscope*; \ - $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs cscope -b $(TAG_FILES) + $(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs cscope -b $(TAG_FILES) ### Testing rules @@ -766,6 +776,14 @@ ifndef NO_JVMTI endif $(call QUIET_INSTALL, libexec) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' +ifndef NO_LIBBPF + $(call QUIET_INSTALL, bpf-headers) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \ + $(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' + $(call QUIET_INSTALL, bpf-examples) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \ + $(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' +endif $(call QUIET_INSTALL, perf-archive) \ $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' $(call QUIET_INSTALL, perf-with-kcore) \ @@ -849,6 +867,7 @@ 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) \ $(OUTPUT)$(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 new file mode 100644 index 000000000000..90ec4c8cb880 --- /dev/null +++ b/tools/perf/arch/arm/include/arch-tests.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_TESTS_H +#define ARCH_TESTS_H + +#ifdef HAVE_DWARF_UNWIND_SUPPORT +struct thread; +struct perf_sample; +#endif + +extern struct test arch_tests[]; + +#endif diff --git a/tools/perf/arch/arm/tests/Build b/tools/perf/arch/arm/tests/Build index b30eff9bcc83..883c57ff0c08 100644 --- a/tools/perf/arch/arm/tests/Build +++ b/tools/perf/arch/arm/tests/Build @@ -1,2 +1,4 @@ libperf-y += regs_load.o libperf-y += dwarf-unwind.o + +libperf-y += arch-tests.o diff --git a/tools/perf/arch/arm/tests/arch-tests.c b/tools/perf/arch/arm/tests/arch-tests.c new file mode 100644 index 000000000000..5b1543c98022 --- /dev/null +++ b/tools/perf/arch/arm/tests/arch-tests.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include "tests/tests.h" +#include "arch-tests.h" + +struct test arch_tests[] = { +#ifdef HAVE_DWARF_UNWIND_SUPPORT + { + .desc = "DWARF unwind", + .func = test__dwarf_unwind, + }, +#endif + { + .func = NULL, + }, +}; diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c index 8cb347760233..9a0242e74cfc 100644 --- a/tools/perf/arch/arm/tests/dwarf-unwind.c +++ b/tools/perf/arch/arm/tests/dwarf-unwind.c @@ -25,7 +25,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_ARM_SP]; - map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp); + map = map_groups__find(thread->mg, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 2323581b157d..1ce6bdbda561 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -1,18 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2015 Linaro Limited. All rights reserved. * Author: Mathieu Poirier <mathieu.poirier@linaro.org> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program. If not, see <http://www.gnu.org/licenses/>. */ #include <stdbool.h> @@ -68,7 +57,7 @@ struct auxtrace_record bool found_spe = false; static struct perf_pmu **arm_spe_pmus = NULL; static int nr_spes = 0; - int i; + int i = 0; if (!evlist) return NULL; diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index fbfc055d3f4d..2f595cd73da6 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -1,18 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2015 Linaro Limited. All rights reserved. * Author: Mathieu Poirier <mathieu.poirier@linaro.org> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program. If not, see <http://www.gnu.org/licenses/>. */ #include <api/fs/fs.h> @@ -298,12 +287,17 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, { int i; int etmv3 = 0, etmv4 = 0; - const struct cpu_map *cpus = evlist->cpus; + struct cpu_map *event_cpus = evlist->cpus; + struct cpu_map *online_cpus = cpu_map__new(NULL); /* cpu map is not empty, we have specific CPUs to work with */ - if (!cpu_map__empty(cpus)) { - for (i = 0; i < cpu_map__nr(cpus); i++) { - if (cs_etm_is_etmv4(itr, cpus->map[i])) + if (!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)) + continue; + + if (cs_etm_is_etmv4(itr, i)) etmv4++; else etmv3++; @@ -311,6 +305,9 @@ 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)) + continue; + if (cs_etm_is_etmv4(itr, i)) etmv4++; else @@ -318,6 +315,8 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, } } + cpu_map__put(online_cpus); + return (CS_ETM_HEADER_SIZE + (etmv4 * CS_ETMV4_PRIV_SIZE) + (etmv3 * CS_ETMV3_PRIV_SIZE)); @@ -447,7 +446,9 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, int i; u32 offset; u64 nr_cpu, type; - const struct cpu_map *cpus = session->evlist->cpus; + struct cpu_map *cpu_map; + struct cpu_map *event_cpus = session->evlist->cpus; + struct cpu_map *online_cpus = cpu_map__new(NULL); struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; @@ -458,8 +459,21 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, if (!session->evlist->nr_mmaps) return -EINVAL; - /* If the cpu_map is empty all CPUs are involved */ - nr_cpu = cpu_map__empty(cpus) ? cpu__max_cpu() : cpu_map__nr(cpus); + /* If the cpu_map is empty all online CPUs are involved */ + if (cpu_map__empty(event_cpus)) { + cpu_map = online_cpus; + } else { + /* Make sure all specified CPUs are online */ + for (i = 0; i < cpu_map__nr(event_cpus); i++) { + if (cpu_map__has(event_cpus, i) && + !cpu_map__has(online_cpus, i)) + return -EINVAL; + } + + cpu_map = event_cpus; + } + + nr_cpu = cpu_map__nr(cpu_map); /* Get PMU type as dynamically assigned by the core */ type = cs_etm_pmu->type; @@ -472,15 +486,11 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, offset = CS_ETM_SNAPSHOT + 1; - /* cpu map is not empty, we have specific CPUs to work with */ - if (!cpu_map__empty(cpus)) { - for (i = 0; i < cpu_map__nr(cpus) && offset < priv_size; i++) - cs_etm_get_metadata(cpus->map[i], &offset, itr, info); - } else { - /* get configuration for all CPUs in the system */ - for (i = 0; i < cpu__max_cpu(); i++) + for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++) + if (cpu_map__has(cpu_map, i)) cs_etm_get_metadata(i, &offset, itr, info); - } + + cpu_map__put(online_cpus); return 0; } diff --git a/tools/perf/arch/arm/util/cs-etm.h b/tools/perf/arch/arm/util/cs-etm.h index 5256741be549..1a12e64f5127 100644 --- a/tools/perf/arch/arm/util/cs-etm.h +++ b/tools/perf/arch/arm/util/cs-etm.h @@ -1,18 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright(C) 2015 Linaro Limited. All rights reserved. * Author: Mathieu Poirier <mathieu.poirier@linaro.org> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program. If not, see <http://www.gnu.org/licenses/>. */ #ifndef INCLUDE__PERF_CS_ETM_H__ diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index ac4dffc807b8..e047571e6080 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -1,18 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2015 Linaro Limited. All rights reserved. * Author: Mathieu Poirier <mathieu.poirier@linaro.org> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program. If not, see <http://www.gnu.org/licenses/>. */ #include <string.h> diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index 91de4860faad..dbef716a1913 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -4,3 +4,25 @@ PERF_HAVE_DWARF_REGS := 1 endif PERF_HAVE_JITDUMP := 1 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 + +# +# Syscall table generation for perf +# + +out := $(OUTPUT)arch/arm64/include/generated/asm +header := $(out)/syscalls.c +incpath := $(srctree)/tools +sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h +sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/ +systbl := $(sysprf)/mksyscalltbl + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +$(header): $(sysdef) $(systbl) + $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ + +clean:: + $(call QUIET_CLEAN, arm64) $(RM) $(header) + +archheaders: $(header) diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl new file mode 100755 index 000000000000..2dbb8cade048 --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl @@ -0,0 +1,62 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate system call table for perf. Derived from +# powerpc script. +# +# Copyright IBM Corp. 2017 +# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> +# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> +# Changed by: Kim Phillips <kim.phillips@arm.com> + +gcc=$1 +hostcc=$2 +incpath=$3 +input=$4 + +if ! test -r $input; then + echo "Could not read input file" >&2 + exit 1 +fi + +create_table_from_c() +{ + local sc nr last_sc + + create_table_exe=`mktemp /tmp/create-table-XXXXXX` + + { + + cat <<-_EoHEADER + #include <stdio.h> + #include "$input" + int main(int argc, char *argv[]) + { + _EoHEADER + + while read sc nr; do + printf "%s\n" " printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);" + last_sc=$sc + done + + printf "%s\n" " printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);" + printf "}\n" + + } | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c - + + $create_table_exe + + rm -f $create_table_exe +} + +create_table() +{ + echo "static const char *syscalltbl_arm64[] = {" + create_table_from_c + echo "};" +} + +$gcc -E -dM -x c $input \ + |sed -ne 's/^#define __NR_//p' \ + |sort -t' ' -k2 -nu \ + |create_table diff --git a/tools/perf/arch/arm64/include/arch-tests.h b/tools/perf/arch/arm64/include/arch-tests.h new file mode 100644 index 000000000000..90ec4c8cb880 --- /dev/null +++ b/tools/perf/arch/arm64/include/arch-tests.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_TESTS_H +#define ARCH_TESTS_H + +#ifdef HAVE_DWARF_UNWIND_SUPPORT +struct thread; +struct perf_sample; +#endif + +extern struct test arch_tests[]; + +#endif diff --git a/tools/perf/arch/arm64/tests/Build b/tools/perf/arch/arm64/tests/Build index b30eff9bcc83..883c57ff0c08 100644 --- a/tools/perf/arch/arm64/tests/Build +++ b/tools/perf/arch/arm64/tests/Build @@ -1,2 +1,4 @@ libperf-y += regs_load.o libperf-y += dwarf-unwind.o + +libperf-y += arch-tests.o diff --git a/tools/perf/arch/arm64/tests/arch-tests.c b/tools/perf/arch/arm64/tests/arch-tests.c new file mode 100644 index 000000000000..5b1543c98022 --- /dev/null +++ b/tools/perf/arch/arm64/tests/arch-tests.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include "tests/tests.h" +#include "arch-tests.h" + +struct test arch_tests[] = { +#ifdef HAVE_DWARF_UNWIND_SUPPORT + { + .desc = "DWARF unwind", + .func = test__dwarf_unwind, + }, +#endif + { + .func = NULL, + }, +}; diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c index e907f0f4c20c..5522ce384723 100644 --- a/tools/perf/arch/arm64/tests/dwarf-unwind.c +++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c @@ -25,7 +25,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_ARM64_SP]; - map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp); + map = map_groups__find(thread->mg, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build index c0b8dfef98ba..68f8a8eb3ad0 100644 --- a/tools/perf/arch/arm64/util/Build +++ b/tools/perf/arch/arm64/util/Build @@ -2,6 +2,7 @@ libperf-y += header.o libperf-y += sym-handling.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o +libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o libperf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \ ../../arm/util/auxtrace.o \ diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 1120e39c1b00..5ccfce87e693 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -194,6 +194,7 @@ struct auxtrace_record *arm_spe_recording_init(int *err, sper->itr.read_finish = arm_spe_read_finish; sper->itr.alignment = 0; + *err = 0; return &sper->itr; } diff --git a/tools/perf/arch/arm64/util/unwind-libdw.c b/tools/perf/arch/arm64/util/unwind-libdw.c new file mode 100644 index 000000000000..7623d85e77f3 --- /dev/null +++ b/tools/perf/arch/arm64/util/unwind-libdw.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <elfutils/libdwfl.h> +#include "../../util/unwind-libdw.h" +#include "../../util/perf_regs.h" +#include "../../util/event.h" + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct unwind_info *ui = arg; + struct regs_dump *user_regs = &ui->sample->user_regs; + Dwarf_Word dwarf_regs[PERF_REG_ARM64_MAX], dwarf_pc; + +#define REG(r) ({ \ + Dwarf_Word val = 0; \ + perf_reg_value(&val, user_regs, PERF_REG_ARM64_##r); \ + val; \ +}) + + dwarf_regs[0] = REG(X0); + dwarf_regs[1] = REG(X1); + dwarf_regs[2] = REG(X2); + dwarf_regs[3] = REG(X3); + dwarf_regs[4] = REG(X4); + dwarf_regs[5] = REG(X5); + dwarf_regs[6] = REG(X6); + dwarf_regs[7] = REG(X7); + dwarf_regs[8] = REG(X8); + dwarf_regs[9] = REG(X9); + dwarf_regs[10] = REG(X10); + dwarf_regs[11] = REG(X11); + dwarf_regs[12] = REG(X12); + dwarf_regs[13] = REG(X13); + dwarf_regs[14] = REG(X14); + dwarf_regs[15] = REG(X15); + dwarf_regs[16] = REG(X16); + dwarf_regs[17] = REG(X17); + dwarf_regs[18] = REG(X18); + dwarf_regs[19] = REG(X19); + dwarf_regs[20] = REG(X20); + dwarf_regs[21] = REG(X21); + dwarf_regs[22] = REG(X22); + dwarf_regs[23] = REG(X23); + dwarf_regs[24] = REG(X24); + dwarf_regs[25] = REG(X25); + dwarf_regs[26] = REG(X26); + dwarf_regs[27] = REG(X27); + dwarf_regs[28] = REG(X28); + dwarf_regs[29] = REG(X29); + dwarf_regs[30] = REG(LR); + dwarf_regs[31] = REG(SP); + + if (!dwfl_thread_state_registers(thread, 0, PERF_REG_ARM64_MAX, + dwarf_regs)) + return false; + + dwarf_pc = REG(PC); + dwfl_thread_state_register_pc(thread, dwarf_pc); + + return true; +} diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index c6f373508a4f..82657c01a3b8 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -189,7 +189,7 @@ out_error: return -1; } -int perf_env__lookup_objdump(struct perf_env *env) +int perf_env__lookup_objdump(struct perf_env *env, const char **path) { /* * For live mode, env->arch will be NULL and we can use @@ -198,5 +198,5 @@ int perf_env__lookup_objdump(struct perf_env *env) if (env->arch == NULL) return 0; - return perf_env__lookup_binutils_path(env, "objdump", &objdump_path); + return perf_env__lookup_binutils_path(env, "objdump", path); } diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h index 2d875baa92e6..2167001b18c5 100644 --- a/tools/perf/arch/common.h +++ b/tools/perf/arch/common.h @@ -4,8 +4,6 @@ #include "../util/env.h" -extern const char *objdump_path; - -int perf_env__lookup_objdump(struct perf_env *env); +int perf_env__lookup_objdump(struct perf_env *env, const char **path); #endif /* ARCH_PERF_COMMON_H */ diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index 42dab7c8f508..a111239df182 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -6,3 +6,28 @@ endif HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 PERF_HAVE_JITDUMP := 1 + +# +# Syscall table generation for perf +# + +out := $(OUTPUT)arch/powerpc/include/generated/asm +header32 := $(out)/syscalls_32.c +header64 := $(out)/syscalls_64.c +sysdef := $(srctree)/tools/arch/powerpc/include/uapi/asm/unistd.h +sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls/ +systbl := $(sysprf)/mksyscalltbl + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +$(header64): $(sysdef) $(systbl) + $(Q)$(SHELL) '$(systbl)' '64' '$(CC)' $(sysdef) > $@ + +$(header32): $(sysdef) $(systbl) + $(Q)$(SHELL) '$(systbl)' '32' '$(CC)' $(sysdef) > $@ + +clean:: + $(call QUIET_CLEAN, powerpc) $(RM) $(header32) $(header64) + +archheaders: $(header32) $(header64) diff --git a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl new file mode 100755 index 000000000000..ef52e1dd694b --- /dev/null +++ b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl @@ -0,0 +1,37 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate system call table for perf. Derived from +# s390 script. +# +# Copyright IBM Corp. 2017 +# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> +# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> + +wordsize=$1 +gcc=$2 +input=$3 + +if ! test -r $input; then + echo "Could not read input file" >&2 + exit 1 +fi + +create_table() +{ + local wordsize=$1 + local max_nr + + echo "static const char *syscalltbl_powerpc_${wordsize}[] = {" + while read sc nr; do + printf '\t[%d] = "%s",\n' $nr $sc + max_nr=$nr + done + echo '};' + echo "#define SYSCALLTBL_POWERPC_${wordsize}_MAX_ID $max_nr" +} + +$gcc -m${wordsize} -E -dM -x c $input \ + |sed -ne 's/^#define __NR_//p' \ + |sort -t' ' -k2 -nu \ + |create_table ${wordsize} diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c index 30cbbd6d5be0..5f39efef0856 100644 --- a/tools/perf/arch/powerpc/tests/dwarf-unwind.c +++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c @@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_POWERPC_R1]; - map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp); + map = map_groups__find(thread->mg, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 0c370f81e002..7c6eeb4633fe 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -58,9 +58,13 @@ static int check_return_reg(int ra_regno, Dwarf_Frame *frame) } /* - * Check if return address is on the stack. + * Check if return address is on the stack. If return address + * is in a register (typically R0), it is yet to be saved on + * the stack. */ - if (nops != 0 || ops != NULL) + if ((nops != 0 || ops != NULL) && + !(nops == 1 && ops[0].atom == DW_OP_regx && + ops[0].number2 == 0 && ops[0].offset == 0)) return 0; /* @@ -243,13 +247,12 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) u64 ip; u64 skip_slot = -1; - if (chain->nr < 3) + if (!chain || chain->nr < 3) return skip_slot; - ip = chain->ips[2]; + ip = chain->ips[1]; - thread__find_addr_location(thread, PERF_RECORD_MISC_USER, - MAP__FUNCTION, ip, &al); + thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); if (al.map) dso = al.map->dso; diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 53d83d7e6a09..10a44e946f77 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -22,15 +22,16 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) #endif -#if !defined(_CALL_ELF) || _CALL_ELF != 2 int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb __maybe_unused) { char *sym = syma->name; +#if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Skip over any initial dot */ if (*sym == '.') sym++; +#endif /* Avoid "SyS" kernel syscall aliases */ if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3)) @@ -41,6 +42,7 @@ int arch__choose_best_symbol(struct symbol *syma, return SYMBOL_A; } +#if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Allow matching against dot variants */ int arch__compare_symbol_names(const char *namea, const char *nameb) { @@ -141,8 +143,10 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev, for (i = 0; i < ntevs; i++) { tev = &pev->tevs[i]; map__for_each_symbol(map, sym, tmp) { - if (map->unmap_ip(map, sym->start) == tev->point.address) + if (map->unmap_ip(map, sym->start) == tev->point.address) { arch__fix_tev_from_maps(pev, tev, map, sym); + break; + } } } } diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c index 8c72b44444cb..cee4e2f7c057 100644 --- a/tools/perf/arch/s390/annotate/instructions.c +++ b/tools/perf/arch/s390/annotate/instructions.c @@ -1,6 +1,113 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> +static int s390_call__parse(struct arch *arch, struct ins_operands *ops, + struct map_symbol *ms) +{ + char *endptr, *tok, *name; + struct map *map = ms->map; + struct addr_map_symbol target = { + .map = map, + }; + + tok = strchr(ops->raw, ','); + if (!tok) + return -1; + + ops->target.addr = strtoull(tok + 1, &endptr, 16); + + name = strchr(endptr, '<'); + if (name == NULL) + return -1; + + name++; + + if (arch->objdump.skip_functions_char && + strchr(name, arch->objdump.skip_functions_char)) + return -1; + + tok = strchr(name, '>'); + if (tok == NULL) + return -1; + + *tok = '\0'; + ops->target.name = strdup(name); + *tok = '>'; + + if (ops->target.name == NULL) + return -1; + target.addr = map__objdump_2mem(map, ops->target.addr); + + if (map_groups__find_ams(&target) == 0 && + map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr) + ops->target.sym = target.sym; + + return 0; +} + +static int call__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops); + +static struct ins_ops s390_call_ops = { + .parse = s390_call__parse, + .scnprintf = call__scnprintf, +}; + +static int s390_mov__parse(struct arch *arch __maybe_unused, + struct ins_operands *ops, + struct map_symbol *ms __maybe_unused) +{ + char *s = strchr(ops->raw, ','), *target, *endptr; + + if (s == NULL) + return -1; + + *s = '\0'; + ops->source.raw = strdup(ops->raw); + *s = ','; + + if (ops->source.raw == NULL) + return -1; + + target = ++s; + ops->target.raw = strdup(target); + if (ops->target.raw == NULL) + goto out_free_source; + + ops->target.addr = strtoull(target, &endptr, 16); + if (endptr == target) + goto out_free_target; + + s = strchr(endptr, '<'); + if (s == NULL) + goto out_free_target; + endptr = strchr(s + 1, '>'); + if (endptr == NULL) + goto out_free_target; + + *endptr = '\0'; + ops->target.name = strdup(s + 1); + *endptr = '>'; + if (ops->target.name == NULL) + goto out_free_target; + + return 0; + +out_free_target: + zfree(&ops->target.raw); +out_free_source: + zfree(&ops->source.raw); + return -1; +} + +static int mov__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops); + +static struct ins_ops s390_mov_ops = { + .parse = s390_mov__parse, + .scnprintf = mov__scnprintf, +}; + static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name) { struct ins_ops *ops = NULL; @@ -14,21 +121,54 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na if (!strcmp(name, "bras") || !strcmp(name, "brasl") || !strcmp(name, "basr")) - ops = &call_ops; + ops = &s390_call_ops; if (!strcmp(name, "br")) ops = &ret_ops; + /* override load/store relative to PC */ + if (!strcmp(name, "lrl") || + !strcmp(name, "lgrl") || + !strcmp(name, "lgfrl") || + !strcmp(name, "llgfrl") || + !strcmp(name, "strl") || + !strcmp(name, "stgrl")) + ops = &s390_mov_ops; if (ops) arch__associate_ins_ops(arch, name, ops); return ops; } +static int s390__cpuid_parse(struct arch *arch, char *cpuid) +{ + unsigned int family; + char model[16], model_c[16], cpumf_v[16], cpumf_a[16]; + int ret; + + /* + * cpuid string format: + * "IBM,family,model-capacity,model[,cpum_cf-version,cpum_cf-authorization]" + */ + ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%s", &family, model_c, + model, cpumf_v, cpumf_a); + if (ret >= 2) { + arch->family = family; + arch->model = 0; + return 0; + } + + return -1; +} + static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused) { + int err = 0; + if (!arch->initialized) { arch->initialized = true; arch->associate_instruction_ops = s390__associate_ins_ops; + if (cpuid) + err = s390__cpuid_parse(arch, cpuid); } - return 0; + return err; } diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c index 6cb48e4cffd9..44c857388897 100644 --- a/tools/perf/arch/s390/util/auxtrace.c +++ b/tools/perf/arch/s390/util/auxtrace.c @@ -30,6 +30,7 @@ cpumsf_info_fill(struct auxtrace_record *itr __maybe_unused, struct auxtrace_info_event *auxtrace_info __maybe_unused, size_t priv_size __maybe_unused) { + auxtrace_info->type = PERF_AUXTRACE_S390_CPUMSF; return 0; } @@ -87,6 +88,7 @@ struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist, struct perf_evsel *pos; int diagnose = 0; + *err = 0; if (evlist->nr_entries == 0) return NULL; diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c index 9fa6c3e5782c..163b92f33998 100644 --- a/tools/perf/arch/s390/util/header.c +++ b/tools/perf/arch/s390/util/header.c @@ -1,8 +1,9 @@ /* * Implementation of get_cpuid(). * - * Copyright 2014 IBM Corp. + * Copyright IBM Corp. 2014, 2018 * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com> + * Thomas Richter <tmricht@linux.vnet.ibm.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -13,16 +14,135 @@ #include <unistd.h> #include <stdio.h> #include <string.h> +#include <ctype.h> #include "../../util/header.h" +#include "../../util/util.h" + +#define SYSINFO_MANU "Manufacturer:" +#define SYSINFO_TYPE "Type:" +#define SYSINFO_MODEL "Model:" +#define SRVLVL_CPUMF "CPU-MF:" +#define SRVLVL_VERSION "version=" +#define SRVLVL_AUTHORIZATION "authorization=" +#define SYSINFO "/proc/sysinfo" +#define SRVLVL "/proc/service_levels" int get_cpuid(char *buffer, size_t sz) { - const char *cpuid = "IBM/S390"; + char *cp, *line = NULL, *line2; + char type[8], model[33], version[8], manufacturer[32], authorization[8]; + int tpsize = 0, mdsize = 0, vssize = 0, mfsize = 0, atsize = 0; + int read; + unsigned long line_sz; + size_t nbytes; + FILE *sysinfo; + + /* + * Scan /proc/sysinfo line by line and read out values for + * Manufacturer:, Type: and Model:, for example: + * Manufacturer: IBM + * Type: 2964 + * Model: 702 N96 + * The first word is the Model Capacity and the second word is + * Model (can be omitted). Both words have a maximum size of 16 + * bytes. + */ + memset(manufacturer, 0, sizeof(manufacturer)); + memset(type, 0, sizeof(type)); + memset(model, 0, sizeof(model)); + memset(version, 0, sizeof(version)); + memset(authorization, 0, sizeof(authorization)); + + sysinfo = fopen(SYSINFO, "r"); + if (sysinfo == NULL) + return -1; + + while ((read = getline(&line, &line_sz, sysinfo)) != -1) { + if (!strncmp(line, SYSINFO_MANU, strlen(SYSINFO_MANU))) { + line2 = line + strlen(SYSINFO_MANU); + + while ((cp = strtok_r(line2, "\n ", &line2))) { + mfsize += scnprintf(manufacturer + mfsize, + sizeof(manufacturer) - mfsize, "%s", cp); + } + } + + if (!strncmp(line, SYSINFO_TYPE, strlen(SYSINFO_TYPE))) { + line2 = line + strlen(SYSINFO_TYPE); + + while ((cp = strtok_r(line2, "\n ", &line2))) { + tpsize += scnprintf(type + tpsize, + sizeof(type) - tpsize, "%s", cp); + } + } + + if (!strncmp(line, SYSINFO_MODEL, strlen(SYSINFO_MODEL))) { + line2 = line + strlen(SYSINFO_MODEL); + + while ((cp = strtok_r(line2, "\n ", &line2))) { + mdsize += scnprintf(model + mdsize, sizeof(model) - mdsize, + "%s%s", model[0] ? "," : "", cp); + } + break; + } + } + fclose(sysinfo); - if (strlen(cpuid) + 1 > sz) + /* Missing manufacturer, type or model information should not happen */ + if (!manufacturer[0] || !type[0] || !model[0]) return -1; - strcpy(buffer, cpuid); - return 0; + /* + * Scan /proc/service_levels and return the CPU-MF counter facility + * version number and authorization level. + * Optional, does not exist on z/VM guests. + */ + sysinfo = fopen(SRVLVL, "r"); + if (sysinfo == NULL) + goto skip_sysinfo; + while ((read = getline(&line, &line_sz, sysinfo)) != -1) { + if (strncmp(line, SRVLVL_CPUMF, strlen(SRVLVL_CPUMF))) + continue; + + line2 = line + strlen(SRVLVL_CPUMF); + while ((cp = strtok_r(line2, "\n ", &line2))) { + if (!strncmp(cp, SRVLVL_VERSION, + strlen(SRVLVL_VERSION))) { + char *sep = strchr(cp, '='); + + vssize += scnprintf(version + vssize, + sizeof(version) - vssize, "%s", sep + 1); + } + if (!strncmp(cp, SRVLVL_AUTHORIZATION, + strlen(SRVLVL_AUTHORIZATION))) { + char *sep = strchr(cp, '='); + + atsize += scnprintf(authorization + atsize, + sizeof(authorization) - atsize, "%s", sep + 1); + } + } + } + fclose(sysinfo); + +skip_sysinfo: + free(line); + + if (version[0] && authorization[0] ) + nbytes = snprintf(buffer, sz, "%s,%s,%s,%s,%s", + manufacturer, type, model, version, + authorization); + else + nbytes = snprintf(buffer, sz, "%s,%s,%s", manufacturer, type, + model); + return (nbytes >= sz) ? -1 : 0; +} + +char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused) +{ + char *buf = malloc(128); + + if (buf && get_cpuid(buf, 128) < 0) + zfree(&buf); + return buf; } diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c index d233e2eb9592..aaabab5e2830 100644 --- a/tools/perf/arch/s390/util/kvm-stat.c +++ b/tools/perf/arch/s390/util/kvm-stat.c @@ -102,7 +102,7 @@ const char * const kvm_skip_events[] = { int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid) { - if (strstr(cpuid, "IBM/S390")) { + if (strstr(cpuid, "IBM")) { kvm->exit_reasons = sie_exit_reasons; kvm->exit_reasons_isa = "SIE"; } else diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index d74eaa7aa927..8cc6642fce7a 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -19,9 +19,6 @@ systbl := $(sys)/syscalltbl.sh _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sys)/syscall_64.tbl $(systbl) - @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ - (diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \ - || echo "Warning: Kernel ABI header at 'tools/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@ clean:: diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 5bd1ba8c0282..44f5aba78210 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -1,21 +1,43 @@ // SPDX-License-Identifier: GPL-2.0 static struct ins x86__instructions[] = { + { .name = "adc", .ops = &mov_ops, }, + { .name = "adcb", .ops = &mov_ops, }, + { .name = "adcl", .ops = &mov_ops, }, { .name = "add", .ops = &mov_ops, }, { .name = "addl", .ops = &mov_ops, }, { .name = "addq", .ops = &mov_ops, }, + { .name = "addsd", .ops = &mov_ops, }, { .name = "addw", .ops = &mov_ops, }, { .name = "and", .ops = &mov_ops, }, + { .name = "andb", .ops = &mov_ops, }, + { .name = "andl", .ops = &mov_ops, }, + { .name = "andpd", .ops = &mov_ops, }, + { .name = "andps", .ops = &mov_ops, }, + { .name = "andq", .ops = &mov_ops, }, + { .name = "andw", .ops = &mov_ops, }, + { .name = "bsr", .ops = &mov_ops, }, + { .name = "bt", .ops = &mov_ops, }, + { .name = "btr", .ops = &mov_ops, }, { .name = "bts", .ops = &mov_ops, }, + { .name = "btsq", .ops = &mov_ops, }, { .name = "call", .ops = &call_ops, }, { .name = "callq", .ops = &call_ops, }, + { .name = "cmovbe", .ops = &mov_ops, }, + { .name = "cmove", .ops = &mov_ops, }, + { .name = "cmovae", .ops = &mov_ops, }, { .name = "cmp", .ops = &mov_ops, }, { .name = "cmpb", .ops = &mov_ops, }, { .name = "cmpl", .ops = &mov_ops, }, { .name = "cmpq", .ops = &mov_ops, }, { .name = "cmpw", .ops = &mov_ops, }, { .name = "cmpxch", .ops = &mov_ops, }, + { .name = "cmpxchg", .ops = &mov_ops, }, + { .name = "cs", .ops = &mov_ops, }, { .name = "dec", .ops = &dec_ops, }, { .name = "decl", .ops = &dec_ops, }, + { .name = "divsd", .ops = &mov_ops, }, + { .name = "divss", .ops = &mov_ops, }, + { .name = "gs", .ops = &mov_ops, }, { .name = "imul", .ops = &mov_ops, }, { .name = "inc", .ops = &dec_ops, }, { .name = "incl", .ops = &dec_ops, }, @@ -57,25 +79,68 @@ static struct ins x86__instructions[] = { { .name = "lea", .ops = &mov_ops, }, { .name = "lock", .ops = &lock_ops, }, { .name = "mov", .ops = &mov_ops, }, + { .name = "movapd", .ops = &mov_ops, }, + { .name = "movaps", .ops = &mov_ops, }, { .name = "movb", .ops = &mov_ops, }, { .name = "movdqa", .ops = &mov_ops, }, + { .name = "movdqu", .ops = &mov_ops, }, { .name = "movl", .ops = &mov_ops, }, { .name = "movq", .ops = &mov_ops, }, + { .name = "movsd", .ops = &mov_ops, }, { .name = "movslq", .ops = &mov_ops, }, + { .name = "movss", .ops = &mov_ops, }, + { .name = "movupd", .ops = &mov_ops, }, + { .name = "movups", .ops = &mov_ops, }, + { .name = "movw", .ops = &mov_ops, }, { .name = "movzbl", .ops = &mov_ops, }, { .name = "movzwl", .ops = &mov_ops, }, + { .name = "mulsd", .ops = &mov_ops, }, + { .name = "mulss", .ops = &mov_ops, }, { .name = "nop", .ops = &nop_ops, }, { .name = "nopl", .ops = &nop_ops, }, { .name = "nopw", .ops = &nop_ops, }, { .name = "or", .ops = &mov_ops, }, + { .name = "orb", .ops = &mov_ops, }, { .name = "orl", .ops = &mov_ops, }, + { .name = "orps", .ops = &mov_ops, }, + { .name = "orq", .ops = &mov_ops, }, + { .name = "pand", .ops = &mov_ops, }, + { .name = "paddq", .ops = &mov_ops, }, + { .name = "pcmpeqb", .ops = &mov_ops, }, + { .name = "por", .ops = &mov_ops, }, + { .name = "rclb", .ops = &mov_ops, }, + { .name = "rcll", .ops = &mov_ops, }, + { .name = "retq", .ops = &ret_ops, }, + { .name = "sbb", .ops = &mov_ops, }, + { .name = "sbbl", .ops = &mov_ops, }, + { .name = "sete", .ops = &mov_ops, }, + { .name = "sub", .ops = &mov_ops, }, + { .name = "subl", .ops = &mov_ops, }, + { .name = "subq", .ops = &mov_ops, }, + { .name = "subsd", .ops = &mov_ops, }, + { .name = "subw", .ops = &mov_ops, }, { .name = "test", .ops = &mov_ops, }, { .name = "testb", .ops = &mov_ops, }, { .name = "testl", .ops = &mov_ops, }, + { .name = "ucomisd", .ops = &mov_ops, }, + { .name = "ucomiss", .ops = &mov_ops, }, + { .name = "vaddsd", .ops = &mov_ops, }, + { .name = "vandpd", .ops = &mov_ops, }, + { .name = "vmovdqa", .ops = &mov_ops, }, + { .name = "vmovq", .ops = &mov_ops, }, + { .name = "vmovsd", .ops = &mov_ops, }, + { .name = "vmulsd", .ops = &mov_ops, }, + { .name = "vorpd", .ops = &mov_ops, }, + { .name = "vsubsd", .ops = &mov_ops, }, + { .name = "vucomisd", .ops = &mov_ops, }, { .name = "xadd", .ops = &mov_ops, }, { .name = "xbeginl", .ops = &jump_ops, }, { .name = "xbeginq", .ops = &jump_ops, }, - { .name = "retq", .ops = &ret_ops, }, + { .name = "xchg", .ops = &mov_ops, }, + { .name = "xor", .ops = &mov_ops, }, + { .name = "xorb", .ops = &mov_ops, }, + { .name = "xorpd", .ops = &mov_ops, }, + { .name = "xorps", .ops = &mov_ops, }, }; static bool x86__ins_is_fused(struct arch *arch, const char *ins1, diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 5aef183e2f85..f0b1709a5ffb 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -4,379 +4,385 @@ # The format is: # <number> <abi> <name> <entry point> # +# The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls +# # The abi is "common", "64" or "x32" for this file. # -0 common read sys_read -1 common write sys_write -2 common open sys_open -3 common close sys_close -4 common stat sys_newstat -5 common fstat sys_newfstat -6 common lstat sys_newlstat -7 common poll sys_poll -8 common lseek sys_lseek -9 common mmap sys_mmap -10 common mprotect sys_mprotect -11 common munmap sys_munmap -12 common brk sys_brk -13 64 rt_sigaction sys_rt_sigaction -14 common rt_sigprocmask sys_rt_sigprocmask -15 64 rt_sigreturn sys_rt_sigreturn/ptregs -16 64 ioctl sys_ioctl -17 common pread64 sys_pread64 -18 common pwrite64 sys_pwrite64 -19 64 readv sys_readv -20 64 writev sys_writev -21 common access sys_access -22 common pipe sys_pipe -23 common select sys_select -24 common sched_yield sys_sched_yield -25 common mremap sys_mremap -26 common msync sys_msync -27 common mincore sys_mincore -28 common madvise sys_madvise -29 common shmget sys_shmget -30 common shmat sys_shmat -31 common shmctl sys_shmctl -32 common dup sys_dup -33 common dup2 sys_dup2 -34 common pause sys_pause -35 common nanosleep sys_nanosleep -36 common getitimer sys_getitimer -37 common alarm sys_alarm -38 common setitimer sys_setitimer -39 common getpid sys_getpid -40 common sendfile sys_sendfile64 -41 common socket sys_socket -42 common connect sys_connect -43 common accept sys_accept -44 common sendto sys_sendto -45 64 recvfrom sys_recvfrom -46 64 sendmsg sys_sendmsg -47 64 recvmsg sys_recvmsg -48 common shutdown sys_shutdown -49 common bind sys_bind -50 common listen sys_listen -51 common getsockname sys_getsockname -52 common getpeername sys_getpeername -53 common socketpair sys_socketpair -54 64 setsockopt sys_setsockopt -55 64 getsockopt sys_getsockopt -56 common clone sys_clone/ptregs -57 common fork sys_fork/ptregs -58 common vfork sys_vfork/ptregs -59 64 execve sys_execve/ptregs -60 common exit sys_exit -61 common wait4 sys_wait4 -62 common kill sys_kill -63 common uname sys_newuname -64 common semget sys_semget -65 common semop sys_semop -66 common semctl sys_semctl -67 common shmdt sys_shmdt -68 common msgget sys_msgget -69 common msgsnd sys_msgsnd -70 common msgrcv sys_msgrcv -71 common msgctl sys_msgctl -72 common fcntl sys_fcntl -73 common flock sys_flock -74 common fsync sys_fsync -75 common fdatasync sys_fdatasync -76 common truncate sys_truncate -77 common ftruncate sys_ftruncate -78 common getdents sys_getdents -79 common getcwd sys_getcwd -80 common chdir sys_chdir -81 common fchdir sys_fchdir -82 common rename sys_rename -83 common mkdir sys_mkdir -84 common rmdir sys_rmdir -85 common creat sys_creat -86 common link sys_link -87 common unlink sys_unlink -88 common symlink sys_symlink -89 common readlink sys_readlink -90 common chmod sys_chmod -91 common fchmod sys_fchmod -92 common chown sys_chown -93 common fchown sys_fchown -94 common lchown sys_lchown -95 common umask sys_umask -96 common gettimeofday sys_gettimeofday -97 common getrlimit sys_getrlimit -98 common getrusage sys_getrusage -99 common sysinfo sys_sysinfo -100 common times sys_times -101 64 ptrace sys_ptrace -102 common getuid sys_getuid -103 common syslog sys_syslog -104 common getgid sys_getgid -105 common setuid sys_setuid -106 common setgid sys_setgid -107 common geteuid sys_geteuid -108 common getegid sys_getegid -109 common setpgid sys_setpgid -110 common getppid sys_getppid -111 common getpgrp sys_getpgrp -112 common setsid sys_setsid -113 common setreuid sys_setreuid -114 common setregid sys_setregid -115 common getgroups sys_getgroups -116 common setgroups sys_setgroups -117 common setresuid sys_setresuid -118 common getresuid sys_getresuid -119 common setresgid sys_setresgid -120 common getresgid sys_getresgid -121 common getpgid sys_getpgid -122 common setfsuid sys_setfsuid -123 common setfsgid sys_setfsgid -124 common getsid sys_getsid -125 common capget sys_capget -126 common capset sys_capset -127 64 rt_sigpending sys_rt_sigpending -128 64 rt_sigtimedwait sys_rt_sigtimedwait -129 64 rt_sigqueueinfo sys_rt_sigqueueinfo -130 common rt_sigsuspend sys_rt_sigsuspend -131 64 sigaltstack sys_sigaltstack -132 common utime sys_utime -133 common mknod sys_mknod +0 common read __x64_sys_read +1 common write __x64_sys_write +2 common open __x64_sys_open +3 common close __x64_sys_close +4 common stat __x64_sys_newstat +5 common fstat __x64_sys_newfstat +6 common lstat __x64_sys_newlstat +7 common poll __x64_sys_poll +8 common lseek __x64_sys_lseek +9 common mmap __x64_sys_mmap +10 common mprotect __x64_sys_mprotect +11 common munmap __x64_sys_munmap +12 common brk __x64_sys_brk +13 64 rt_sigaction __x64_sys_rt_sigaction +14 common rt_sigprocmask __x64_sys_rt_sigprocmask +15 64 rt_sigreturn __x64_sys_rt_sigreturn/ptregs +16 64 ioctl __x64_sys_ioctl +17 common pread64 __x64_sys_pread64 +18 common pwrite64 __x64_sys_pwrite64 +19 64 readv __x64_sys_readv +20 64 writev __x64_sys_writev +21 common access __x64_sys_access +22 common pipe __x64_sys_pipe +23 common select __x64_sys_select +24 common sched_yield __x64_sys_sched_yield +25 common mremap __x64_sys_mremap +26 common msync __x64_sys_msync +27 common mincore __x64_sys_mincore +28 common madvise __x64_sys_madvise +29 common shmget __x64_sys_shmget +30 common shmat __x64_sys_shmat +31 common shmctl __x64_sys_shmctl +32 common dup __x64_sys_dup +33 common dup2 __x64_sys_dup2 +34 common pause __x64_sys_pause +35 common nanosleep __x64_sys_nanosleep +36 common getitimer __x64_sys_getitimer +37 common alarm __x64_sys_alarm +38 common setitimer __x64_sys_setitimer +39 common getpid __x64_sys_getpid +40 common sendfile __x64_sys_sendfile64 +41 common socket __x64_sys_socket +42 common connect __x64_sys_connect +43 common accept __x64_sys_accept +44 common sendto __x64_sys_sendto +45 64 recvfrom __x64_sys_recvfrom +46 64 sendmsg __x64_sys_sendmsg +47 64 recvmsg __x64_sys_recvmsg +48 common shutdown __x64_sys_shutdown +49 common bind __x64_sys_bind +50 common listen __x64_sys_listen +51 common getsockname __x64_sys_getsockname +52 common getpeername __x64_sys_getpeername +53 common socketpair __x64_sys_socketpair +54 64 setsockopt __x64_sys_setsockopt +55 64 getsockopt __x64_sys_getsockopt +56 common clone __x64_sys_clone/ptregs +57 common fork __x64_sys_fork/ptregs +58 common vfork __x64_sys_vfork/ptregs +59 64 execve __x64_sys_execve/ptregs +60 common exit __x64_sys_exit +61 common wait4 __x64_sys_wait4 +62 common kill __x64_sys_kill +63 common uname __x64_sys_newuname +64 common semget __x64_sys_semget +65 common semop __x64_sys_semop +66 common semctl __x64_sys_semctl +67 common shmdt __x64_sys_shmdt +68 common msgget __x64_sys_msgget +69 common msgsnd __x64_sys_msgsnd +70 common msgrcv __x64_sys_msgrcv +71 common msgctl __x64_sys_msgctl +72 common fcntl __x64_sys_fcntl +73 common flock __x64_sys_flock +74 common fsync __x64_sys_fsync +75 common fdatasync __x64_sys_fdatasync +76 common truncate __x64_sys_truncate +77 common ftruncate __x64_sys_ftruncate +78 common getdents __x64_sys_getdents +79 common getcwd __x64_sys_getcwd +80 common chdir __x64_sys_chdir +81 common fchdir __x64_sys_fchdir +82 common rename __x64_sys_rename +83 common mkdir __x64_sys_mkdir +84 common rmdir __x64_sys_rmdir +85 common creat __x64_sys_creat +86 common link __x64_sys_link +87 common unlink __x64_sys_unlink +88 common symlink __x64_sys_symlink +89 common readlink __x64_sys_readlink +90 common chmod __x64_sys_chmod +91 common fchmod __x64_sys_fchmod +92 common chown __x64_sys_chown +93 common fchown __x64_sys_fchown +94 common lchown __x64_sys_lchown +95 common umask __x64_sys_umask +96 common gettimeofday __x64_sys_gettimeofday +97 common getrlimit __x64_sys_getrlimit +98 common getrusage __x64_sys_getrusage +99 common sysinfo __x64_sys_sysinfo +100 common times __x64_sys_times +101 64 ptrace __x64_sys_ptrace +102 common getuid __x64_sys_getuid +103 common syslog __x64_sys_syslog +104 common getgid __x64_sys_getgid +105 common setuid __x64_sys_setuid +106 common setgid __x64_sys_setgid +107 common geteuid __x64_sys_geteuid +108 common getegid __x64_sys_getegid +109 common setpgid __x64_sys_setpgid +110 common getppid __x64_sys_getppid +111 common getpgrp __x64_sys_getpgrp +112 common setsid __x64_sys_setsid +113 common setreuid __x64_sys_setreuid +114 common setregid __x64_sys_setregid +115 common getgroups __x64_sys_getgroups +116 common setgroups __x64_sys_setgroups +117 common setresuid __x64_sys_setresuid +118 common getresuid __x64_sys_getresuid +119 common setresgid __x64_sys_setresgid +120 common getresgid __x64_sys_getresgid +121 common getpgid __x64_sys_getpgid +122 common setfsuid __x64_sys_setfsuid +123 common setfsgid __x64_sys_setfsgid +124 common getsid __x64_sys_getsid +125 common capget __x64_sys_capget +126 common capset __x64_sys_capset +127 64 rt_sigpending __x64_sys_rt_sigpending +128 64 rt_sigtimedwait __x64_sys_rt_sigtimedwait +129 64 rt_sigqueueinfo __x64_sys_rt_sigqueueinfo +130 common rt_sigsuspend __x64_sys_rt_sigsuspend +131 64 sigaltstack __x64_sys_sigaltstack +132 common utime __x64_sys_utime +133 common mknod __x64_sys_mknod 134 64 uselib -135 common personality sys_personality -136 common ustat sys_ustat -137 common statfs sys_statfs -138 common fstatfs sys_fstatfs -139 common sysfs sys_sysfs -140 common getpriority sys_getpriority -141 common setpriority sys_setpriority -142 common sched_setparam sys_sched_setparam -143 common sched_getparam sys_sched_getparam -144 common sched_setscheduler sys_sched_setscheduler -145 common sched_getscheduler sys_sched_getscheduler -146 common sched_get_priority_max sys_sched_get_priority_max -147 common sched_get_priority_min sys_sched_get_priority_min -148 common sched_rr_get_interval sys_sched_rr_get_interval -149 common mlock sys_mlock -150 common munlock sys_munlock -151 common mlockall sys_mlockall -152 common munlockall sys_munlockall -153 common vhangup sys_vhangup -154 common modify_ldt sys_modify_ldt -155 common pivot_root sys_pivot_root -156 64 _sysctl sys_sysctl -157 common prctl sys_prctl -158 common arch_prctl sys_arch_prctl -159 common adjtimex sys_adjtimex -160 common setrlimit sys_setrlimit -161 common chroot sys_chroot -162 common sync sys_sync -163 common acct sys_acct -164 common settimeofday sys_settimeofday -165 common mount sys_mount -166 common umount2 sys_umount -167 common swapon sys_swapon -168 common swapoff sys_swapoff -169 common reboot sys_reboot -170 common sethostname sys_sethostname -171 common setdomainname sys_setdomainname -172 common iopl sys_iopl/ptregs -173 common ioperm sys_ioperm +135 common personality __x64_sys_personality +136 common ustat __x64_sys_ustat +137 common statfs __x64_sys_statfs +138 common fstatfs __x64_sys_fstatfs +139 common sysfs __x64_sys_sysfs +140 common getpriority __x64_sys_getpriority +141 common setpriority __x64_sys_setpriority +142 common sched_setparam __x64_sys_sched_setparam +143 common sched_getparam __x64_sys_sched_getparam +144 common sched_setscheduler __x64_sys_sched_setscheduler +145 common sched_getscheduler __x64_sys_sched_getscheduler +146 common sched_get_priority_max __x64_sys_sched_get_priority_max +147 common sched_get_priority_min __x64_sys_sched_get_priority_min +148 common sched_rr_get_interval __x64_sys_sched_rr_get_interval +149 common mlock __x64_sys_mlock +150 common munlock __x64_sys_munlock +151 common mlockall __x64_sys_mlockall +152 common munlockall __x64_sys_munlockall +153 common vhangup __x64_sys_vhangup +154 common modify_ldt __x64_sys_modify_ldt +155 common pivot_root __x64_sys_pivot_root +156 64 _sysctl __x64_sys_sysctl +157 common prctl __x64_sys_prctl +158 common arch_prctl __x64_sys_arch_prctl +159 common adjtimex __x64_sys_adjtimex +160 common setrlimit __x64_sys_setrlimit +161 common chroot __x64_sys_chroot +162 common sync __x64_sys_sync +163 common acct __x64_sys_acct +164 common settimeofday __x64_sys_settimeofday +165 common mount __x64_sys_mount +166 common umount2 __x64_sys_umount +167 common swapon __x64_sys_swapon +168 common swapoff __x64_sys_swapoff +169 common reboot __x64_sys_reboot +170 common sethostname __x64_sys_sethostname +171 common setdomainname __x64_sys_setdomainname +172 common iopl __x64_sys_iopl/ptregs +173 common ioperm __x64_sys_ioperm 174 64 create_module -175 common init_module sys_init_module -176 common delete_module sys_delete_module +175 common init_module __x64_sys_init_module +176 common delete_module __x64_sys_delete_module 177 64 get_kernel_syms 178 64 query_module -179 common quotactl sys_quotactl +179 common quotactl __x64_sys_quotactl 180 64 nfsservctl 181 common getpmsg 182 common putpmsg 183 common afs_syscall 184 common tuxcall 185 common security -186 common gettid sys_gettid -187 common readahead sys_readahead -188 common setxattr sys_setxattr -189 common lsetxattr sys_lsetxattr -190 common fsetxattr sys_fsetxattr -191 common getxattr sys_getxattr -192 common lgetxattr sys_lgetxattr -193 common fgetxattr sys_fgetxattr -194 common listxattr sys_listxattr -195 common llistxattr sys_llistxattr -196 common flistxattr sys_flistxattr -197 common removexattr sys_removexattr -198 common lremovexattr sys_lremovexattr -199 common fremovexattr sys_fremovexattr -200 common tkill sys_tkill -201 common time sys_time -202 common futex sys_futex -203 common sched_setaffinity sys_sched_setaffinity -204 common sched_getaffinity sys_sched_getaffinity +186 common gettid __x64_sys_gettid +187 common readahead __x64_sys_readahead +188 common setxattr __x64_sys_setxattr +189 common lsetxattr __x64_sys_lsetxattr +190 common fsetxattr __x64_sys_fsetxattr +191 common getxattr __x64_sys_getxattr +192 common lgetxattr __x64_sys_lgetxattr +193 common fgetxattr __x64_sys_fgetxattr +194 common listxattr __x64_sys_listxattr +195 common llistxattr __x64_sys_llistxattr +196 common flistxattr __x64_sys_flistxattr +197 common removexattr __x64_sys_removexattr +198 common lremovexattr __x64_sys_lremovexattr +199 common fremovexattr __x64_sys_fremovexattr +200 common tkill __x64_sys_tkill +201 common time __x64_sys_time +202 common futex __x64_sys_futex +203 common sched_setaffinity __x64_sys_sched_setaffinity +204 common sched_getaffinity __x64_sys_sched_getaffinity 205 64 set_thread_area -206 64 io_setup sys_io_setup -207 common io_destroy sys_io_destroy -208 common io_getevents sys_io_getevents -209 64 io_submit sys_io_submit -210 common io_cancel sys_io_cancel +206 64 io_setup __x64_sys_io_setup +207 common io_destroy __x64_sys_io_destroy +208 common io_getevents __x64_sys_io_getevents +209 64 io_submit __x64_sys_io_submit +210 common io_cancel __x64_sys_io_cancel 211 64 get_thread_area -212 common lookup_dcookie sys_lookup_dcookie -213 common epoll_create sys_epoll_create +212 common lookup_dcookie __x64_sys_lookup_dcookie +213 common epoll_create __x64_sys_epoll_create 214 64 epoll_ctl_old 215 64 epoll_wait_old -216 common remap_file_pages sys_remap_file_pages -217 common getdents64 sys_getdents64 -218 common set_tid_address sys_set_tid_address -219 common restart_syscall sys_restart_syscall -220 common semtimedop sys_semtimedop -221 common fadvise64 sys_fadvise64 -222 64 timer_create sys_timer_create -223 common timer_settime sys_timer_settime -224 common timer_gettime sys_timer_gettime -225 common timer_getoverrun sys_timer_getoverrun -226 common timer_delete sys_timer_delete -227 common clock_settime sys_clock_settime -228 common clock_gettime sys_clock_gettime -229 common clock_getres sys_clock_getres -230 common clock_nanosleep sys_clock_nanosleep -231 common exit_group sys_exit_group -232 common epoll_wait sys_epoll_wait -233 common epoll_ctl sys_epoll_ctl -234 common tgkill sys_tgkill -235 common utimes sys_utimes +216 common remap_file_pages __x64_sys_remap_file_pages +217 common getdents64 __x64_sys_getdents64 +218 common set_tid_address __x64_sys_set_tid_address +219 common restart_syscall __x64_sys_restart_syscall +220 common semtimedop __x64_sys_semtimedop +221 common fadvise64 __x64_sys_fadvise64 +222 64 timer_create __x64_sys_timer_create +223 common timer_settime __x64_sys_timer_settime +224 common timer_gettime __x64_sys_timer_gettime +225 common timer_getoverrun __x64_sys_timer_getoverrun +226 common timer_delete __x64_sys_timer_delete +227 common clock_settime __x64_sys_clock_settime +228 common clock_gettime __x64_sys_clock_gettime +229 common clock_getres __x64_sys_clock_getres +230 common clock_nanosleep __x64_sys_clock_nanosleep +231 common exit_group __x64_sys_exit_group +232 common epoll_wait __x64_sys_epoll_wait +233 common epoll_ctl __x64_sys_epoll_ctl +234 common tgkill __x64_sys_tgkill +235 common utimes __x64_sys_utimes 236 64 vserver -237 common mbind sys_mbind -238 common set_mempolicy sys_set_mempolicy -239 common get_mempolicy sys_get_mempolicy -240 common mq_open sys_mq_open -241 common mq_unlink sys_mq_unlink -242 common mq_timedsend sys_mq_timedsend -243 common mq_timedreceive sys_mq_timedreceive -244 64 mq_notify sys_mq_notify -245 common mq_getsetattr sys_mq_getsetattr -246 64 kexec_load sys_kexec_load -247 64 waitid sys_waitid -248 common add_key sys_add_key -249 common request_key sys_request_key -250 common keyctl sys_keyctl -251 common ioprio_set sys_ioprio_set -252 common ioprio_get sys_ioprio_get -253 common inotify_init sys_inotify_init -254 common inotify_add_watch sys_inotify_add_watch -255 common inotify_rm_watch sys_inotify_rm_watch -256 common migrate_pages sys_migrate_pages -257 common openat sys_openat -258 common mkdirat sys_mkdirat -259 common mknodat sys_mknodat -260 common fchownat sys_fchownat -261 common futimesat sys_futimesat -262 common newfstatat sys_newfstatat -263 common unlinkat sys_unlinkat -264 common renameat sys_renameat -265 common linkat sys_linkat -266 common symlinkat sys_symlinkat -267 common readlinkat sys_readlinkat -268 common fchmodat sys_fchmodat -269 common faccessat sys_faccessat -270 common pselect6 sys_pselect6 -271 common ppoll sys_ppoll -272 common unshare sys_unshare -273 64 set_robust_list sys_set_robust_list -274 64 get_robust_list sys_get_robust_list -275 common splice sys_splice -276 common tee sys_tee -277 common sync_file_range sys_sync_file_range -278 64 vmsplice sys_vmsplice -279 64 move_pages sys_move_pages -280 common utimensat sys_utimensat -281 common epoll_pwait sys_epoll_pwait -282 common signalfd sys_signalfd -283 common timerfd_create sys_timerfd_create -284 common eventfd sys_eventfd -285 common fallocate sys_fallocate -286 common timerfd_settime sys_timerfd_settime -287 common timerfd_gettime sys_timerfd_gettime -288 common accept4 sys_accept4 -289 common signalfd4 sys_signalfd4 -290 common eventfd2 sys_eventfd2 -291 common epoll_create1 sys_epoll_create1 -292 common dup3 sys_dup3 -293 common pipe2 sys_pipe2 -294 common inotify_init1 sys_inotify_init1 -295 64 preadv sys_preadv -296 64 pwritev sys_pwritev -297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo -298 common perf_event_open sys_perf_event_open -299 64 recvmmsg sys_recvmmsg -300 common fanotify_init sys_fanotify_init -301 common fanotify_mark sys_fanotify_mark -302 common prlimit64 sys_prlimit64 -303 common name_to_handle_at sys_name_to_handle_at -304 common open_by_handle_at sys_open_by_handle_at -305 common clock_adjtime sys_clock_adjtime -306 common syncfs sys_syncfs -307 64 sendmmsg sys_sendmmsg -308 common setns sys_setns -309 common getcpu sys_getcpu -310 64 process_vm_readv sys_process_vm_readv -311 64 process_vm_writev sys_process_vm_writev -312 common kcmp sys_kcmp -313 common finit_module sys_finit_module -314 common sched_setattr sys_sched_setattr -315 common sched_getattr sys_sched_getattr -316 common renameat2 sys_renameat2 -317 common seccomp sys_seccomp -318 common getrandom sys_getrandom -319 common memfd_create sys_memfd_create -320 common kexec_file_load sys_kexec_file_load -321 common bpf sys_bpf -322 64 execveat sys_execveat/ptregs -323 common userfaultfd sys_userfaultfd -324 common membarrier sys_membarrier -325 common mlock2 sys_mlock2 -326 common copy_file_range sys_copy_file_range -327 64 preadv2 sys_preadv2 -328 64 pwritev2 sys_pwritev2 -329 common pkey_mprotect sys_pkey_mprotect -330 common pkey_alloc sys_pkey_alloc -331 common pkey_free sys_pkey_free -332 common statx sys_statx +237 common mbind __x64_sys_mbind +238 common set_mempolicy __x64_sys_set_mempolicy +239 common get_mempolicy __x64_sys_get_mempolicy +240 common mq_open __x64_sys_mq_open +241 common mq_unlink __x64_sys_mq_unlink +242 common mq_timedsend __x64_sys_mq_timedsend +243 common mq_timedreceive __x64_sys_mq_timedreceive +244 64 mq_notify __x64_sys_mq_notify +245 common mq_getsetattr __x64_sys_mq_getsetattr +246 64 kexec_load __x64_sys_kexec_load +247 64 waitid __x64_sys_waitid +248 common add_key __x64_sys_add_key +249 common request_key __x64_sys_request_key +250 common keyctl __x64_sys_keyctl +251 common ioprio_set __x64_sys_ioprio_set +252 common ioprio_get __x64_sys_ioprio_get +253 common inotify_init __x64_sys_inotify_init +254 common inotify_add_watch __x64_sys_inotify_add_watch +255 common inotify_rm_watch __x64_sys_inotify_rm_watch +256 common migrate_pages __x64_sys_migrate_pages +257 common openat __x64_sys_openat +258 common mkdirat __x64_sys_mkdirat +259 common mknodat __x64_sys_mknodat +260 common fchownat __x64_sys_fchownat +261 common futimesat __x64_sys_futimesat +262 common newfstatat __x64_sys_newfstatat +263 common unlinkat __x64_sys_unlinkat +264 common renameat __x64_sys_renameat +265 common linkat __x64_sys_linkat +266 common symlinkat __x64_sys_symlinkat +267 common readlinkat __x64_sys_readlinkat +268 common fchmodat __x64_sys_fchmodat +269 common faccessat __x64_sys_faccessat +270 common pselect6 __x64_sys_pselect6 +271 common ppoll __x64_sys_ppoll +272 common unshare __x64_sys_unshare +273 64 set_robust_list __x64_sys_set_robust_list +274 64 get_robust_list __x64_sys_get_robust_list +275 common splice __x64_sys_splice +276 common tee __x64_sys_tee +277 common sync_file_range __x64_sys_sync_file_range +278 64 vmsplice __x64_sys_vmsplice +279 64 move_pages __x64_sys_move_pages +280 common utimensat __x64_sys_utimensat +281 common epoll_pwait __x64_sys_epoll_pwait +282 common signalfd __x64_sys_signalfd +283 common timerfd_create __x64_sys_timerfd_create +284 common eventfd __x64_sys_eventfd +285 common fallocate __x64_sys_fallocate +286 common timerfd_settime __x64_sys_timerfd_settime +287 common timerfd_gettime __x64_sys_timerfd_gettime +288 common accept4 __x64_sys_accept4 +289 common signalfd4 __x64_sys_signalfd4 +290 common eventfd2 __x64_sys_eventfd2 +291 common epoll_create1 __x64_sys_epoll_create1 +292 common dup3 __x64_sys_dup3 +293 common pipe2 __x64_sys_pipe2 +294 common inotify_init1 __x64_sys_inotify_init1 +295 64 preadv __x64_sys_preadv +296 64 pwritev __x64_sys_pwritev +297 64 rt_tgsigqueueinfo __x64_sys_rt_tgsigqueueinfo +298 common perf_event_open __x64_sys_perf_event_open +299 64 recvmmsg __x64_sys_recvmmsg +300 common fanotify_init __x64_sys_fanotify_init +301 common fanotify_mark __x64_sys_fanotify_mark +302 common prlimit64 __x64_sys_prlimit64 +303 common name_to_handle_at __x64_sys_name_to_handle_at +304 common open_by_handle_at __x64_sys_open_by_handle_at +305 common clock_adjtime __x64_sys_clock_adjtime +306 common syncfs __x64_sys_syncfs +307 64 sendmmsg __x64_sys_sendmmsg +308 common setns __x64_sys_setns +309 common getcpu __x64_sys_getcpu +310 64 process_vm_readv __x64_sys_process_vm_readv +311 64 process_vm_writev __x64_sys_process_vm_writev +312 common kcmp __x64_sys_kcmp +313 common finit_module __x64_sys_finit_module +314 common sched_setattr __x64_sys_sched_setattr +315 common sched_getattr __x64_sys_sched_getattr +316 common renameat2 __x64_sys_renameat2 +317 common seccomp __x64_sys_seccomp +318 common getrandom __x64_sys_getrandom +319 common memfd_create __x64_sys_memfd_create +320 common kexec_file_load __x64_sys_kexec_file_load +321 common bpf __x64_sys_bpf +322 64 execveat __x64_sys_execveat/ptregs +323 common userfaultfd __x64_sys_userfaultfd +324 common membarrier __x64_sys_membarrier +325 common mlock2 __x64_sys_mlock2 +326 common copy_file_range __x64_sys_copy_file_range +327 64 preadv2 __x64_sys_preadv2 +328 64 pwritev2 __x64_sys_pwritev2 +329 common pkey_mprotect __x64_sys_pkey_mprotect +330 common pkey_alloc __x64_sys_pkey_alloc +331 common pkey_free __x64_sys_pkey_free +332 common statx __x64_sys_statx +333 common io_pgetevents __x64_sys_io_pgetevents +334 common rseq __x64_sys_rseq # # x32-specific system call numbers start at 512 to avoid cache impact -# for native 64-bit operation. +# for native 64-bit operation. The __x32_compat_sys stubs are created +# on-the-fly for compat_sys_*() compatibility system calls if X86_X32 +# is defined. # -512 x32 rt_sigaction compat_sys_rt_sigaction +512 x32 rt_sigaction __x32_compat_sys_rt_sigaction 513 x32 rt_sigreturn sys32_x32_rt_sigreturn -514 x32 ioctl compat_sys_ioctl -515 x32 readv compat_sys_readv -516 x32 writev compat_sys_writev -517 x32 recvfrom compat_sys_recvfrom -518 x32 sendmsg compat_sys_sendmsg -519 x32 recvmsg compat_sys_recvmsg -520 x32 execve compat_sys_execve/ptregs -521 x32 ptrace compat_sys_ptrace -522 x32 rt_sigpending compat_sys_rt_sigpending -523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait -524 x32 rt_sigqueueinfo compat_sys_rt_sigqueueinfo -525 x32 sigaltstack compat_sys_sigaltstack -526 x32 timer_create compat_sys_timer_create -527 x32 mq_notify compat_sys_mq_notify -528 x32 kexec_load compat_sys_kexec_load -529 x32 waitid compat_sys_waitid -530 x32 set_robust_list compat_sys_set_robust_list -531 x32 get_robust_list compat_sys_get_robust_list -532 x32 vmsplice compat_sys_vmsplice -533 x32 move_pages compat_sys_move_pages -534 x32 preadv compat_sys_preadv64 -535 x32 pwritev compat_sys_pwritev64 -536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo -537 x32 recvmmsg compat_sys_recvmmsg -538 x32 sendmmsg compat_sys_sendmmsg -539 x32 process_vm_readv compat_sys_process_vm_readv -540 x32 process_vm_writev compat_sys_process_vm_writev -541 x32 setsockopt compat_sys_setsockopt -542 x32 getsockopt compat_sys_getsockopt -543 x32 io_setup compat_sys_io_setup -544 x32 io_submit compat_sys_io_submit -545 x32 execveat compat_sys_execveat/ptregs -546 x32 preadv2 compat_sys_preadv64v2 -547 x32 pwritev2 compat_sys_pwritev64v2 +514 x32 ioctl __x32_compat_sys_ioctl +515 x32 readv __x32_compat_sys_readv +516 x32 writev __x32_compat_sys_writev +517 x32 recvfrom __x32_compat_sys_recvfrom +518 x32 sendmsg __x32_compat_sys_sendmsg +519 x32 recvmsg __x32_compat_sys_recvmsg +520 x32 execve __x32_compat_sys_execve/ptregs +521 x32 ptrace __x32_compat_sys_ptrace +522 x32 rt_sigpending __x32_compat_sys_rt_sigpending +523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait +524 x32 rt_sigqueueinfo __x32_compat_sys_rt_sigqueueinfo +525 x32 sigaltstack __x32_compat_sys_sigaltstack +526 x32 timer_create __x32_compat_sys_timer_create +527 x32 mq_notify __x32_compat_sys_mq_notify +528 x32 kexec_load __x32_compat_sys_kexec_load +529 x32 waitid __x32_compat_sys_waitid +530 x32 set_robust_list __x32_compat_sys_set_robust_list +531 x32 get_robust_list __x32_compat_sys_get_robust_list +532 x32 vmsplice __x32_compat_sys_vmsplice +533 x32 move_pages __x32_compat_sys_move_pages +534 x32 preadv __x32_compat_sys_preadv64 +535 x32 pwritev __x32_compat_sys_pwritev64 +536 x32 rt_tgsigqueueinfo __x32_compat_sys_rt_tgsigqueueinfo +537 x32 recvmmsg __x32_compat_sys_recvmmsg +538 x32 sendmmsg __x32_compat_sys_sendmmsg +539 x32 process_vm_readv __x32_compat_sys_process_vm_readv +540 x32 process_vm_writev __x32_compat_sys_process_vm_writev +541 x32 setsockopt __x32_compat_sys_setsockopt +542 x32 getsockopt __x32_compat_sys_getsockopt +543 x32 io_setup __x32_compat_sys_io_setup +544 x32 io_submit __x32_compat_sys_io_submit +545 x32 execveat __x32_compat_sys_execveat/ptregs +546 x32 preadv2 __x32_compat_sys_preadv64v2 +547 x32 pwritev2 __x32_compat_sys_pwritev64v2 diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index c1bd979b957b..613709cfbbd0 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -9,6 +9,7 @@ struct test; int test__rdpmc(struct test *test __maybe_unused, int subtest); int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest); int test__insn_x86(struct test *test __maybe_unused, int subtest); +int test__bp_modify(struct test *test, int subtest); #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 8e2c5a38c3b9..586849ff83a0 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -5,3 +5,4 @@ libperf-y += arch-tests.o libperf-y += rdpmc.o libperf-y += perf-time-to-tsc.o libperf-$(CONFIG_AUXTRACE) += insn-x86.o +libperf-$(CONFIG_X86_64) += bp-modify.o diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index cc1802ff5410..d47d3f8e3c8e 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -24,6 +24,12 @@ struct test arch_tests[] = { .func = test__insn_x86, }, #endif +#if defined(__x86_64__) + { + .desc = "x86 bp modify", + .func = test__bp_modify, + }, +#endif { .func = NULL, }, diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c new file mode 100644 index 000000000000..f53e4406709f --- /dev/null +++ b/tools/perf/arch/x86/tests/bp-modify.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/user.h> +#include <syscall.h> +#include <unistd.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/ptrace.h> +#include <asm/ptrace.h> +#include <errno.h> +#include "debug.h" +#include "tests/tests.h" +#include "arch-tests.h" + +static noinline int bp_1(void) +{ + pr_debug("in %s\n", __func__); + return 0; +} + +static noinline int bp_2(void) +{ + pr_debug("in %s\n", __func__); + return 0; +} + +static int spawn_child(void) +{ + int child = fork(); + + if (child == 0) { + /* + * The child sets itself for as tracee and + * waits in signal for parent to trace it, + * then it calls bp_1 and quits. + */ + int err = ptrace(PTRACE_TRACEME, 0, NULL, NULL); + + if (err) { + pr_debug("failed to PTRACE_TRACEME\n"); + exit(1); + } + + raise(SIGCONT); + bp_1(); + exit(0); + } + + return child; +} + +/* + * This tests creates HW breakpoint, tries to + * change it and checks it was properly changed. + */ +static int bp_modify1(void) +{ + pid_t child; + int status; + unsigned long rip = 0, dr7 = 1; + + child = spawn_child(); + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 1\n"); + return TEST_FAIL; + } + + /* + * The parent does following steps: + * - creates a new breakpoint (id 0) for bp_2 function + * - changes that breakponit to bp_1 function + * - waits for the breakpoint to hit and checks + * it has proper rip of bp_1 function + * - detaches the child + */ + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_2)) { + pr_debug("failed to set breakpoint, 1st time: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_1)) { + pr_debug("failed to set breakpoint, 2nd time: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[7]), dr7)) { + pr_debug("failed to set dr7: %s\n", strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_CONT, child, NULL, NULL)) { + pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + goto out; + } + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 2\n"); + return TEST_FAIL; + } + + rip = ptrace(PTRACE_PEEKUSER, child, + offsetof(struct user_regs_struct, rip), NULL); + if (rip == (unsigned long) -1) { + pr_debug("failed to PTRACE_PEEKUSER: %s\n", + strerror(errno)); + goto out; + } + + pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); + +out: + if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { + pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + return TEST_FAIL; + } + + return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; +} + +/* + * This tests creates HW breakpoint, tries to + * change it to bogus value and checks the original + * breakpoint is hit. + */ +static int bp_modify2(void) +{ + pid_t child; + int status; + unsigned long rip = 0, dr7 = 1; + + child = spawn_child(); + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 1\n"); + return TEST_FAIL; + } + + /* + * The parent does following steps: + * - creates a new breakpoint (id 0) for bp_1 function + * - tries to change that breakpoint to (-1) address + * - waits for the breakpoint to hit and checks + * it has proper rip of bp_1 function + * - detaches the child + */ + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_1)) { + pr_debug("failed to set breakpoint: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[7]), dr7)) { + pr_debug("failed to set dr7: %s\n", strerror(errno)); + goto out; + } + + if (!ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), (unsigned long) (-1))) { + pr_debug("failed, breakpoint set to bogus address\n"); + goto out; + } + + if (ptrace(PTRACE_CONT, child, NULL, NULL)) { + pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + goto out; + } + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 2\n"); + return TEST_FAIL; + } + + rip = ptrace(PTRACE_PEEKUSER, child, + offsetof(struct user_regs_struct, rip), NULL); + if (rip == (unsigned long) -1) { + pr_debug("failed to PTRACE_PEEKUSER: %s\n", + strerror(errno)); + goto out; + } + + pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); + +out: + if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { + pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + return TEST_FAIL; + } + + return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; +} + +int test__bp_modify(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1()); + TEST_ASSERT_VAL("modify test 2 failed\n", !bp_modify2()); + + return 0; +} diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index 95036c7a59e8..7879df34569a 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_X86_SP]; - map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp); + map = map_groups__find(thread->mg, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index 06abe8108b33..7a7721604b86 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -60,6 +60,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe union perf_event *event; u64 test_tsc, comm1_tsc, comm2_tsc; u64 test_time, comm1_time = 0, comm2_time = 0; + struct perf_mmap *md; threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -109,7 +110,11 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe perf_evlist__disable(evlist); for (i = 0; i < evlist->nr_mmaps; i++) { - while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + md = &evlist->mmap[i]; + if (perf_mmap__read_init(md) < 0) + continue; + + while ((event = perf_mmap__read_event(md)) != NULL) { struct perf_sample sample; if (event->header.type != PERF_RECORD_COMM || @@ -128,8 +133,9 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe comm2_time = sample.time; } next_event: - perf_evlist__mmap_consume(evlist, i); + perf_mmap__consume(md); } + perf_mmap__read_done(md); } if (!comm1_time || !comm2_time) diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index f95e6f46ef0d..844b8f335532 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -4,6 +4,8 @@ libperf-y += pmu.o libperf-y += kvm-stat.o libperf-y += perf_regs.o libperf-y += group.o +libperf-y += machine.o +libperf-y += event.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c index 6aa3f2a38321..b135af62011c 100644 --- a/tools/perf/arch/x86/util/auxtrace.c +++ b/tools/perf/arch/x86/util/auxtrace.c @@ -37,15 +37,11 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist, intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME); intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME); - if (evlist) { - evlist__for_each_entry(evlist, evsel) { - if (intel_pt_pmu && - evsel->attr.type == intel_pt_pmu->type) - found_pt = true; - if (intel_bts_pmu && - evsel->attr.type == intel_bts_pmu->type) - found_bts = true; - } + evlist__for_each_entry(evlist, evsel) { + if (intel_pt_pmu && evsel->attr.type == intel_pt_pmu->type) + found_pt = true; + if (intel_bts_pmu && evsel->attr.type == intel_bts_pmu->type) + found_bts = true; } if (found_pt && found_bts) { diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c new file mode 100644 index 000000000000..675a0213044d --- /dev/null +++ b/tools/perf/arch/x86/util/event.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/types.h> +#include <linux/string.h> + +#include "../../util/machine.h" +#include "../../util/tool.h" +#include "../../util/map.h" +#include "../../util/util.h" +#include "../../util/debug.h" + +#if defined(__x86_64__) + +int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + int rc = 0; + struct map *pos; + struct map_groups *kmaps = &machine->kmaps; + struct maps *maps = &kmaps->maps; + union perf_event *event = zalloc(sizeof(event->mmap) + + machine->id_hdr_size); + + if (!event) { + pr_debug("Not enough memory synthesizing mmap event " + "for extra kernel maps\n"); + return -1; + } + + for (pos = maps__first(maps); pos; pos = map__next(pos)) { + struct kmap *kmap; + size_t size; + + if (!__map__is_extra_kernel_map(pos)) + continue; + + kmap = map__kmap(pos); + + size = sizeof(event->mmap) - sizeof(event->mmap.filename) + + PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) + + machine->id_hdr_size; + + memset(event, 0, size); + + event->mmap.header.type = PERF_RECORD_MMAP; + + /* + * kernel uses 0 for user space maps, see kernel/perf_event.c + * __perf_event_mmap + */ + if (machine__is_host(machine)) + event->header.misc = PERF_RECORD_MISC_KERNEL; + else + event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; + + event->mmap.header.size = size; + + event->mmap.start = pos->start; + event->mmap.len = pos->end - pos->start; + event->mmap.pgoff = pos->pgoff; + event->mmap.pid = machine->pid; + + strlcpy(event->mmap.filename, kmap->name, PATH_MAX); + + if (perf_tool__process_synth_event(tool, event, machine, + process) != 0) { + rc = -1; + break; + } + } + + free(event); + return rc; +} + +#endif diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c new file mode 100644 index 000000000000..4520ac53caa9 --- /dev/null +++ b/tools/perf/arch/x86/util/machine.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/types.h> +#include <linux/string.h> +#include <stdlib.h> + +#include "../../util/machine.h" +#include "../../util/map.h" +#include "../../util/symbol.h" +#include "../../util/sane_ctype.h" + +#include <symbol/kallsyms.h> + +#if defined(__x86_64__) + +struct extra_kernel_map_info { + int cnt; + int max_cnt; + struct extra_kernel_map *maps; + bool get_entry_trampolines; + u64 entry_trampoline; +}; + +static int add_extra_kernel_map(struct extra_kernel_map_info *mi, u64 start, + u64 end, u64 pgoff, const char *name) +{ + if (mi->cnt >= mi->max_cnt) { + void *buf; + size_t sz; + + mi->max_cnt = mi->max_cnt ? mi->max_cnt * 2 : 32; + sz = sizeof(struct extra_kernel_map) * mi->max_cnt; + buf = realloc(mi->maps, sz); + if (!buf) + return -1; + mi->maps = buf; + } + + mi->maps[mi->cnt].start = start; + mi->maps[mi->cnt].end = end; + mi->maps[mi->cnt].pgoff = pgoff; + strlcpy(mi->maps[mi->cnt].name, name, KMAP_NAME_LEN); + + mi->cnt += 1; + + return 0; +} + +static int find_extra_kernel_maps(void *arg, const char *name, char type, + u64 start) +{ + struct extra_kernel_map_info *mi = arg; + + if (!mi->entry_trampoline && kallsyms2elf_binding(type) == STB_GLOBAL && + !strcmp(name, "_entry_trampoline")) { + mi->entry_trampoline = start; + return 0; + } + + if (is_entry_trampoline(name)) { + u64 end = start + page_size; + + return add_extra_kernel_map(mi, start, end, 0, name); + } + + return 0; +} + +int machine__create_extra_kernel_maps(struct machine *machine, + struct dso *kernel) +{ + struct extra_kernel_map_info mi = { .cnt = 0, }; + char filename[PATH_MAX]; + int ret; + int i; + + machine__get_kallsyms_filename(machine, filename, PATH_MAX); + + if (symbol__restricted_filename(filename, "/proc/kallsyms")) + return 0; + + ret = kallsyms__parse(filename, &mi, find_extra_kernel_maps); + if (ret) + goto out_free; + + if (!mi.entry_trampoline) + goto out_free; + + for (i = 0; i < mi.cnt; i++) { + struct extra_kernel_map *xm = &mi.maps[i]; + + xm->pgoff = mi.entry_trampoline; + ret = machine__create_extra_kernel_map(machine, kernel, xm); + if (ret) + goto out_free; + } + + machine->trampolines_mapped = mi.cnt; +out_free: + free(mi.maps); + return ret; +} + +#endif diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index 4b2caf6d48e7..fead6b3b4206 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -226,7 +226,7 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op) else if (rm[2].rm_so != rm[2].rm_eo) prefix[0] = '+'; else - strncpy(prefix, "+0", 2); + scnprintf(prefix, sizeof(prefix), "+0"); } /* Rename register */ diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index 63a74c32ddc5..e33ef5bc31c5 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <string.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include "../../util/intel-pt.h" diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 06bae7023a51..950539f9a4f7 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -2,6 +2,7 @@ #include <stdbool.h> #include <errno.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include "../../perf.h" diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build index 60bf11943047..eafce1a130a1 100644 --- a/tools/perf/bench/Build +++ b/tools/perf/bench/Build @@ -7,6 +7,7 @@ perf-y += futex-wake-parallel.o perf-y += futex-requeue.o perf-y += futex-lock-pi.o +perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index b43f8d2a34ec..9ad015a1e202 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -6,6 +6,7 @@ #define altinstr_replacement text #define globl p2align 4; .globl #define _ASM_EXTABLE_FAULT(x, y) +#define _ASM_EXTABLE(x, y) #include "../../arch/x86/lib/memcpy_64.S" /* diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c new file mode 100644 index 000000000000..4130734dde84 --- /dev/null +++ b/tools/perf/bench/mem-memcpy-x86-64-lib.c @@ -0,0 +1,24 @@ +/* + * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy + * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy' + * happy. + */ +#include <linux/types.h> + +unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt); +unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len); + +unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len) +{ + for (; len; --len, to++, from++) { + /* + * Call the assembly routine back directly since + * memcpy_mcsafe() may silently fallback to memcpy. + */ + unsigned long rem = __memcpy_mcsafe(to, from, 1); + + if (rem) + break; + } + return len; +} diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 944070e98a2c..44195514b19e 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -175,7 +175,7 @@ static const struct option options[] = { OPT_UINTEGER('s', "nr_secs" , &p0.nr_secs, "max number of seconds to run (default: 5 secs)"), OPT_UINTEGER('u', "usleep" , &p0.sleep_usecs, "usecs to sleep per loop iteration"), - OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via writes (can be mixed with -W)"), + OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via reads (can be mixed with -W)"), OPT_BOOLEAN('W', "data_writes" , &p0.data_writes, "access the data via writes (can be mixed with -R)"), OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards, "access the data backwards as well"), OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"), @@ -1098,7 +1098,7 @@ static void *worker_thread(void *__tdata) u8 *global_data; u8 *process_data; u8 *thread_data; - u64 bytes_done; + u64 bytes_done, secs; long work_done; u32 l; struct rusage rusage; @@ -1254,7 +1254,8 @@ static void *worker_thread(void *__tdata) timersub(&stop, &start0, &diff); td->runtime_ns = diff.tv_sec * NSEC_PER_SEC; td->runtime_ns += diff.tv_usec * NSEC_PER_USEC; - td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9; + secs = td->runtime_ns / NSEC_PER_SEC; + td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0; getrusage(RUSAGE_THREAD, &rusage); td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC; diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index f15731a3d438..830481b8db26 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -40,10 +40,11 @@ struct perf_annotate { struct perf_tool tool; struct perf_session *session; - bool use_tui, use_stdio, use_gtk; - bool full_paths; - bool print_line; + struct annotation_options opts; + bool use_tui, use_stdio, use_stdio2, use_gtk; bool skip_missing; + bool has_br_stack; + bool group_set; const char *sym_hist_filter; const char *cpu_list; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); @@ -146,16 +147,78 @@ static void process_branch_stack(struct branch_stack *bs, struct addr_location * free(bi); } +static int hist_iter__branch_callback(struct hist_entry_iter *iter, + struct addr_location *al __maybe_unused, + bool single __maybe_unused, + void *arg __maybe_unused) +{ + struct hist_entry *he = iter->he; + struct branch_info *bi; + struct perf_sample *sample = iter->sample; + struct perf_evsel *evsel = iter->evsel; + int err; + + hist__account_cycles(sample->branch_stack, al, sample, false); + + bi = he->branch_info; + err = addr_map_symbol__inc_samples(&bi->from, sample, evsel); + + if (err) + goto out; + + err = addr_map_symbol__inc_samples(&bi->to, sample, evsel); + +out: + return err; +} + +static int process_branch_callback(struct perf_evsel *evsel, + struct perf_sample *sample, + struct addr_location *al __maybe_unused, + struct perf_annotate *ann, + struct machine *machine) +{ + struct hist_entry_iter iter = { + .evsel = evsel, + .sample = sample, + .add_entry_cb = hist_iter__branch_callback, + .hide_unresolved = symbol_conf.hide_unresolved, + .ops = &hist_iter_branch, + }; + + struct addr_location a; + int ret; + + if (machine__resolve(machine, &a, sample) < 0) + return -1; + + if (a.sym == NULL) + return 0; + + if (a.map != NULL) + a.map->dso->hit = 1; + + ret = hist_entry_iter__add(&iter, &a, PERF_MAX_STACK_DEPTH, ann); + return ret; +} + +static bool has_annotation(struct perf_annotate *ann) +{ + return ui__has_annotation() || ann->use_stdio2; +} + static int perf_evsel__add_sample(struct perf_evsel *evsel, struct perf_sample *sample, struct addr_location *al, - struct perf_annotate *ann) + struct perf_annotate *ann, + struct machine *machine) { struct hists *hists = evsel__hists(evsel); struct hist_entry *he; int ret; - if (ann->sym_hist_filter != NULL && + if ((!ann->has_br_stack || !has_annotation(ann)) && + ann->sym_hist_filter != NULL && (al->sym == NULL || strcmp(ann->sym_hist_filter, al->sym->name) != 0)) { /* We're only interested in a symbol named sym_hist_filter */ @@ -165,7 +228,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, */ if (al->sym != NULL) { rb_erase(&al->sym->rb_node, - &al->map->dso->symbols[al->map->type]); + &al->map->dso->symbols); symbol__delete(al->sym); dso__reset_find_symbol_cache(al->map->dso); } @@ -178,11 +241,14 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, */ process_branch_stack(sample->branch_stack, al, sample); + if (ann->has_br_stack && has_annotation(ann)) + return process_branch_callback(evsel, sample, al, ann, machine); + he = hists__add_entry(hists, al, NULL, NULL, NULL, sample, true); if (he == NULL) return -ENOMEM; - ret = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr); + ret = hist_entry__inc_addr_samples(he, sample, evsel, al->addr); hists__inc_nr_samples(hists, true); return ret; } @@ -206,7 +272,8 @@ static int process_sample_event(struct perf_tool *tool, if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap)) goto out_put; - if (!al.filtered && perf_evsel__add_sample(evsel, sample, &al, ann)) { + if (!al.filtered && + perf_evsel__add_sample(evsel, sample, &al, ann, machine)) { pr_warning("problem incrementing symbol count, " "skipping event\n"); ret = -1; @@ -216,12 +283,23 @@ out_put: return ret; } +static int process_feature_event(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session) +{ + if (event->feat.feat_id < HEADER_LAST_FEATURE) + return perf_event__process_feature(tool, event, session); + return 0; +} + static int hist_entry__tty_annotate(struct hist_entry *he, struct perf_evsel *evsel, struct perf_annotate *ann) { - return symbol__tty_annotate(he->ms.sym, he->ms.map, evsel, - ann->print_line, ann->full_paths, 0, 0); + if (!ann->use_stdio2) + return symbol__tty_annotate(he->ms.sym, he->ms.map, evsel, &ann->opts); + + return symbol__tty_annotate2(he->ms.sym, he->ms.map, evsel, &ann->opts); } static void hists__find_annotations(struct hists *hists, @@ -238,6 +316,10 @@ static void hists__find_annotations(struct hists *hists, if (he->ms.sym == NULL || he->ms.map->dso->annotate_warned) goto find_next; + if (ann->sym_hist_filter && + (strcmp(he->ms.sym->name, ann->sym_hist_filter) != 0)) + goto find_next; + notes = symbol__annotation(he->ms.sym); if (notes->src == NULL) { find_next: @@ -268,7 +350,8 @@ find_next: /* skip missing symbols */ nd = rb_next(nd); } else if (use_browser == 1) { - key = hist_entry__tui_annotate(he, evsel, NULL); + key = hist_entry__tui_annotate(he, evsel, NULL, &ann->opts); + switch (key) { case -1: if (!ann->skip_missing) @@ -314,8 +397,9 @@ static int __cmd_annotate(struct perf_annotate *ann) goto out; } - if (!objdump_path) { - ret = perf_env__lookup_objdump(&session->header.env); + if (!ann->opts.objdump_path) { + ret = perf_env__lookup_objdump(&session->header.env, + &ann->opts.objdump_path); if (ret) goto out; } @@ -396,10 +480,11 @@ int cmd_annotate(int argc, const char **argv) .attr = perf_event__process_attr, .build_id = perf_event__process_build_id, .tracing_data = perf_event__process_tracing_data, - .feature = perf_event__process_feature, + .feature = process_feature_event, .ordered_events = true, .ordering_requires_timestamps = true, }, + .opts = annotation__default_options, }; struct perf_data data = { .mode = PERF_DATA_MODE_READ, @@ -420,27 +505,33 @@ int cmd_annotate(int argc, const char **argv) OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"), OPT_BOOLEAN(0, "tui", &annotate.use_tui, "Use the TUI interface"), OPT_BOOLEAN(0, "stdio", &annotate.use_stdio, "Use the stdio interface"), + OPT_BOOLEAN(0, "stdio2", &annotate.use_stdio2, "Use the stdio interface"), + OPT_BOOLEAN(0, "ignore-vmlinux", &symbol_conf.ignore_vmlinux, + "don't load vmlinux even if found"), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, "file", "vmlinux pathname"), OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules, "load module symbols - WARNING: use only with -k and LIVE kernel"), - OPT_BOOLEAN('l', "print-line", &annotate.print_line, + OPT_BOOLEAN('l', "print-line", &annotate.opts.print_lines, "print matching source lines (may be slow)"), - OPT_BOOLEAN('P', "full-paths", &annotate.full_paths, + OPT_BOOLEAN('P', "full-paths", &annotate.opts.full_path, "Don't shorten the displayed pathnames"), OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing, "Skip symbols that cannot be annotated"), + OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group, + &annotate.group_set, + "Show event group information together"), OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"), OPT_CALLBACK(0, "symfs", NULL, "directory", "Look for files with symbols relative to this directory", symbol__config_symfs), - OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src, + OPT_BOOLEAN(0, "source", &annotate.opts.annotate_src, "Interleave source code with assembly code (default)"), - OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw, + OPT_BOOLEAN(0, "asm-raw", &annotate.opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), - OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", + OPT_STRING('M', "disassembler-style", &annotate.opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), - OPT_STRING(0, "objdump", &objdump_path, "path", + OPT_STRING(0, "objdump", &annotate.opts.objdump_path, "path", "objdump binary to use for disassembly and annotations"), OPT_BOOLEAN(0, "group", &symbol_conf.event_group, "Show event group information together"), @@ -451,6 +542,10 @@ int cmd_annotate(int argc, const char **argv) OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode", "'always' (default), 'never' or 'auto' only applicable to --stdio mode", stdio__config_color, "always"), + OPT_CALLBACK(0, "percent-type", &annotate.opts, "local-period", + "Set percent type local/global-period/hits", + annotate_parse_percent_type), + OPT_END() }; int ret; @@ -489,20 +584,25 @@ int cmd_annotate(int argc, const char **argv) if (annotate.session == NULL) return -1; + annotate.has_br_stack = perf_header__has_feat(&annotate.session->header, + HEADER_BRANCH_STACK); + + if (annotate.group_set) + perf_evlist__force_leader(annotate.session->evlist); + ret = symbol__annotation_init(); if (ret < 0) goto out_delete; + annotation_config__init(); + symbol_conf.try_vmlinux_path = true; ret = symbol__init(&annotate.session->header.env); if (ret < 0) goto out_delete; - if (setup_sorting(NULL) < 0) - usage_with_options(annotate_usage, options); - - if (annotate.use_stdio) + if (annotate.use_stdio || annotate.use_stdio2) use_browser = 0; else if (annotate.use_tui) use_browser = 1; @@ -511,6 +611,15 @@ int cmd_annotate(int argc, const char **argv) setup_browser(true); + if ((use_browser == 1 || annotate.use_stdio2) && annotate.has_br_stack) { + sort__mode = SORT_MODE__BRANCH; + if (setup_sorting(annotate.session->evlist) < 0) + usage_with_options(annotate_usage, options); + } else { + if (setup_sorting(NULL) < 0) + usage_with_options(annotate_usage, options); + } + ret = __cmd_annotate(&annotate); out_delete: diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 41db2cba77eb..115110a4796a 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -25,6 +25,7 @@ #include "util/session.h" #include "util/symbol.h" #include "util/time-utils.h" +#include "util/probe-file.h" static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid) { @@ -239,6 +240,34 @@ out: return err; } +static int build_id_cache__purge_all(void) +{ + struct strlist *list; + struct str_node *pos; + int err = 0; + char *buf; + + list = build_id_cache__list_all(false); + if (!list) { + pr_debug("Failed to get buildids: -%d\n", errno); + return -EINVAL; + } + + strlist__for_each_entry(pos, list) { + buf = build_id_cache__origname(pos->s); + err = build_id_cache__remove_s(pos->s); + pr_debug("Removing %s (%s): %s\n", buf, pos->s, + err ? "FAIL" : "Ok"); + free(buf); + if (err) + break; + } + strlist__delete(list); + + pr_debug("Purged all: %s\n", err ? "FAIL" : "Ok"); + return err; +} + static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) { char filename[PATH_MAX]; @@ -297,6 +326,26 @@ static int build_id_cache__update_file(const char *filename, struct nsinfo *nsi) return err; } +static int build_id_cache__show_all(void) +{ + struct strlist *bidlist; + struct str_node *nd; + char *buf; + + bidlist = build_id_cache__list_all(true); + if (!bidlist) { + pr_debug("Failed to get buildids: -%d\n", errno); + return -1; + } + strlist__for_each_entry(nd, bidlist) { + buf = build_id_cache__origname(nd->s); + fprintf(stdout, "%s %s\n", nd->s, buf); + free(buf); + } + strlist__delete(bidlist); + return 0; +} + int cmd_buildid_cache(int argc, const char **argv) { struct strlist *list; @@ -304,6 +353,9 @@ int cmd_buildid_cache(int argc, const char **argv) int ret = 0; int ns_id = -1; bool force = false; + bool list_files = false; + bool opts_flag = false; + bool purge_all = false; char const *add_name_list_str = NULL, *remove_name_list_str = NULL, *purge_name_list_str = NULL, @@ -327,6 +379,8 @@ int cmd_buildid_cache(int argc, const char **argv) "file(s) to remove"), OPT_STRING('p', "purge", &purge_name_list_str, "file list", "file(s) to remove (remove old caches too)"), + OPT_BOOLEAN('P', "purge-all", &purge_all, "purge all cached files"), + OPT_BOOLEAN('l', "list", &list_files, "list all cached files"), OPT_STRING('M', "missing", &missing_filename, "file", "to find missing build ids in the cache"), OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), @@ -344,11 +398,20 @@ int cmd_buildid_cache(int argc, const char **argv) argc = parse_options(argc, argv, buildid_cache_options, buildid_cache_usage, 0); - if (argc || (!add_name_list_str && !kcore_filename && - !remove_name_list_str && !purge_name_list_str && - !missing_filename && !update_name_list_str)) + opts_flag = add_name_list_str || kcore_filename || + remove_name_list_str || purge_name_list_str || + missing_filename || update_name_list_str || + purge_all; + + if (argc || !(list_files || opts_flag)) usage_with_options(buildid_cache_usage, buildid_cache_options); + /* -l is exclusive. It can not be used with other options. */ + if (list_files && opts_flag) { + usage_with_options_msg(buildid_cache_usage, + buildid_cache_options, "-l is exclusive.\n"); + } + if (ns_id > 0) nsi = nsinfo__new(ns_id); @@ -366,6 +429,11 @@ int cmd_buildid_cache(int argc, const char **argv) setup_pager(); + if (list_files) { + ret = build_id_cache__show_all(); + goto out; + } + if (add_name_list_str) { list = strlist__new(add_name_list_str, NULL); if (list) { @@ -420,6 +488,13 @@ int cmd_buildid_cache(int argc, const char **argv) } } + if (purge_all) { + if (build_id_cache__purge_all()) { + pr_warning("Couldn't remove some caches. Error: %s.\n", + str_error_r(errno, sbuf, sizeof(sbuf))); + } + } + if (missing_filename) ret = build_id_cache__fprintf_missing(session, stdout); diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 539c3d460158..f3aa9d02a5ab 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -32,6 +32,7 @@ #include "evsel.h" #include "ui/browsers/hists.h" #include "thread.h" +#include "mem2node.h" struct c2c_hists { struct hists hists; @@ -49,11 +50,17 @@ struct c2c_hist_entry { struct c2c_hists *hists; struct c2c_stats stats; unsigned long *cpuset; + unsigned long *nodeset; struct c2c_stats *node_stats; unsigned int cacheline_idx; struct compute_stats cstats; + unsigned long paddr; + unsigned long paddr_cnt; + bool paddr_zero; + char *nodestr; + /* * must be at the end, * because of its callchain dynamic entry @@ -66,6 +73,7 @@ static char const *coalesce_default = "pid,iaddr"; struct perf_c2c { struct perf_tool tool; struct c2c_hists hists; + struct mem2node mem2node; unsigned long **nodes; int nodes_cnt; @@ -123,6 +131,10 @@ static void *c2c_he_zalloc(size_t size) if (!c2c_he->cpuset) return NULL; + c2c_he->nodeset = bitmap_alloc(c2c.nodes_cnt); + if (!c2c_he->nodeset) + return NULL; + c2c_he->node_stats = zalloc(c2c.nodes_cnt * sizeof(*c2c_he->node_stats)); if (!c2c_he->node_stats) return NULL; @@ -145,6 +157,8 @@ static void c2c_he_free(void *he) } free(c2c_he->cpuset); + free(c2c_he->nodeset); + free(c2c_he->nodestr); free(c2c_he->node_stats); free(c2c_he); } @@ -194,6 +208,28 @@ static void c2c_he__set_cpu(struct c2c_hist_entry *c2c_he, set_bit(sample->cpu, c2c_he->cpuset); } +static void c2c_he__set_node(struct c2c_hist_entry *c2c_he, + struct perf_sample *sample) +{ + int node; + + if (!sample->phys_addr) { + c2c_he->paddr_zero = true; + return; + } + + node = mem2node__node(&c2c.mem2node, sample->phys_addr); + if (WARN_ONCE(node < 0, "WARNING: failed to find node\n")) + return; + + set_bit(node, c2c_he->nodeset); + + if (c2c_he->paddr != sample->phys_addr) { + c2c_he->paddr_cnt++; + c2c_he->paddr = sample->phys_addr; + } +} + static void compute_stats(struct c2c_hist_entry *c2c_he, struct c2c_stats *stats, u64 weight) @@ -237,9 +273,12 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, if (mi == NULL) return -ENOMEM; - mi_dup = memdup(mi, sizeof(*mi)); - if (!mi_dup) - goto free_mi; + /* + * The mi object is released in hists__add_entry_ops, + * if it gets sorted out into existing data, so we need + * to take the copy now. + */ + mi_dup = mem_info__get(mi); c2c_decode_stats(&stats, mi); @@ -247,13 +286,14 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, &al, NULL, NULL, mi, sample, true); if (he == NULL) - goto free_mi_dup; + goto free_mi; c2c_he = container_of(he, struct c2c_hist_entry, he); c2c_add_stats(&c2c_he->stats, &stats); c2c_add_stats(&c2c_hists->stats, &stats); c2c_he__set_cpu(c2c_he, sample); + c2c_he__set_node(c2c_he, sample); hists__inc_nr_samples(&c2c_hists->hists, he->filtered); ret = hist_entry__append_callchain(he, sample); @@ -272,19 +312,15 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, mi = mi_dup; - mi_dup = memdup(mi, sizeof(*mi)); - if (!mi_dup) - goto free_mi; - c2c_hists = he__get_c2c_hists(he, c2c.cl_sort, 2); if (!c2c_hists) - goto free_mi_dup; + goto free_mi; he = hists__add_entry_ops(&c2c_hists->hists, &c2c_entry_ops, &al, NULL, NULL, mi, sample, true); if (he == NULL) - goto free_mi_dup; + goto free_mi; c2c_he = container_of(he, struct c2c_hist_entry, he); c2c_add_stats(&c2c_he->stats, &stats); @@ -294,6 +330,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, compute_stats(c2c_he, &stats, sample->weight); c2c_he__set_cpu(c2c_he, sample); + c2c_he__set_node(c2c_he, sample); hists__inc_nr_samples(&c2c_hists->hists, he->filtered); ret = hist_entry__append_callchain(he, sample); @@ -303,10 +340,9 @@ out: addr_location__put(&al); return ret; -free_mi_dup: - free(mi_dup); free_mi: - free(mi); + mem_info__put(mi_dup); + mem_info__put(mi); ret = -ENOMEM; goto out; } @@ -457,6 +493,31 @@ static int dcacheline_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, return scnprintf(hpp->buf, hpp->size, "%*s", width, HEX_STR(buf, addr)); } +static int +dcacheline_node_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct c2c_hist_entry *c2c_he; + int width = c2c_width(fmt, hpp, he->hists); + + c2c_he = container_of(he, struct c2c_hist_entry, he); + if (WARN_ON_ONCE(!c2c_he->nodestr)) + return 0; + + return scnprintf(hpp->buf, hpp->size, "%*s", width, c2c_he->nodestr); +} + +static int +dcacheline_node_count(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct c2c_hist_entry *c2c_he; + int width = c2c_width(fmt, hpp, he->hists); + + c2c_he = container_of(he, struct c2c_hist_entry, he); + return scnprintf(hpp->buf, hpp->size, "%*lu", width, c2c_he->paddr_cnt); +} + static int offset_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he) { @@ -1202,23 +1263,47 @@ cl_idx_empty_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, } static struct c2c_dimension dim_dcacheline = { - .header = HEADER_LOW("Cacheline"), + .header = HEADER_SPAN("--- Cacheline ----", "Address", 2), .name = "dcacheline", .cmp = dcacheline_cmp, .entry = dcacheline_entry, .width = 18, }; -static struct c2c_header header_offset_tui = HEADER_LOW("Off"); +static struct c2c_dimension dim_dcacheline_node = { + .header = HEADER_LOW("Node"), + .name = "dcacheline_node", + .cmp = empty_cmp, + .entry = dcacheline_node_entry, + .width = 4, +}; + +static struct c2c_dimension dim_dcacheline_count = { + .header = HEADER_LOW("PA cnt"), + .name = "dcacheline_count", + .cmp = empty_cmp, + .entry = dcacheline_node_count, + .width = 6, +}; + +static struct c2c_header header_offset_tui = HEADER_SPAN("-----", "Off", 2); static struct c2c_dimension dim_offset = { - .header = HEADER_BOTH("Data address", "Offset"), + .header = HEADER_SPAN("--- Data address -", "Offset", 2), .name = "offset", .cmp = offset_cmp, .entry = offset_entry, .width = 18, }; +static struct c2c_dimension dim_offset_node = { + .header = HEADER_LOW("Node"), + .name = "offset_node", + .cmp = empty_cmp, + .entry = dcacheline_node_entry, + .width = 4, +}; + static struct c2c_dimension dim_iaddr = { .header = HEADER_LOW("Code address"), .name = "iaddr", @@ -1538,7 +1623,10 @@ static struct c2c_dimension dim_dcacheline_num_empty = { static struct c2c_dimension *dimensions[] = { &dim_dcacheline, + &dim_dcacheline_node, + &dim_dcacheline_count, &dim_offset, + &dim_offset_node, &dim_iaddr, &dim_tot_hitm, &dim_lcl_hitm, @@ -1841,20 +1929,56 @@ static inline int valid_hitm_or_store(struct hist_entry *he) return has_hitm || c2c_he->stats.store; } -static void calc_width(struct hist_entry *he) +static void set_node_width(struct c2c_hist_entry *c2c_he, int len) +{ + struct c2c_dimension *dim; + + dim = &c2c.hists == c2c_he->hists ? + &dim_dcacheline_node : &dim_offset_node; + + if (len > dim->width) + dim->width = len; +} + +static int set_nodestr(struct c2c_hist_entry *c2c_he) +{ + char buf[30]; + int len; + + if (c2c_he->nodestr) + return 0; + + if (bitmap_weight(c2c_he->nodeset, c2c.nodes_cnt)) { + len = bitmap_scnprintf(c2c_he->nodeset, c2c.nodes_cnt, + buf, sizeof(buf)); + } else { + len = scnprintf(buf, sizeof(buf), "N/A"); + } + + set_node_width(c2c_he, len); + c2c_he->nodestr = strdup(buf); + return c2c_he->nodestr ? 0 : -ENOMEM; +} + +static void calc_width(struct c2c_hist_entry *c2c_he) { struct c2c_hists *c2c_hists; - c2c_hists = container_of(he->hists, struct c2c_hists, hists); - hists__calc_col_len(&c2c_hists->hists, he); + c2c_hists = container_of(c2c_he->he.hists, struct c2c_hists, hists); + hists__calc_col_len(&c2c_hists->hists, &c2c_he->he); + set_nodestr(c2c_he); } static int filter_cb(struct hist_entry *he) { + struct c2c_hist_entry *c2c_he; + + c2c_he = container_of(he, struct c2c_hist_entry, he); + if (c2c.show_src && !he->srcline) - he->srcline = hist_entry__get_srcline(he); + he->srcline = hist_entry__srcline(he); - calc_width(he); + calc_width(c2c_he); if (!valid_hitm_or_store(he)) he->filtered = HIST_FILTER__C2C; @@ -1871,12 +1995,11 @@ static int resort_cl_cb(struct hist_entry *he) c2c_he = container_of(he, struct c2c_hist_entry, he); c2c_hists = c2c_he->hists; - calc_width(he); - if (display && c2c_hists) { static unsigned int idx; c2c_he->cacheline_idx = idx++; + calc_width(c2c_he); c2c_hists__reinit(c2c_hists, c2c.cl_output, c2c.cl_resort); @@ -2070,7 +2193,7 @@ static void print_cacheline(struct c2c_hists *c2c_hists, fprintf(out, "%s\n", bf); fprintf(out, " -------------------------------------------------------------\n"); - hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, true); + hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, false); } static void print_pareto(FILE *out) @@ -2145,7 +2268,7 @@ static void perf_c2c__hists_fprintf(FILE *out, struct perf_session *session) fprintf(out, "=================================================\n"); fprintf(out, "#\n"); - hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, false); + hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, true); fprintf(out, "\n"); fprintf(out, "=================================================\n"); @@ -2226,6 +2349,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he) " s Toggle full length of symbol and source line columns \n" " q Return back to cacheline list \n"; + if (!he) + return 0; + /* Display compact version first. */ c2c.symbol_full = false; @@ -2350,14 +2476,66 @@ static void perf_c2c_display(struct perf_session *session) } #endif /* HAVE_SLANG_SUPPORT */ -static void ui_quirks(void) +static char *fill_line(const char *orig, int len) { + int i, j, olen = strlen(orig); + char *buf; + + buf = zalloc(len + 1); + if (!buf) + return NULL; + + j = len / 2 - olen / 2; + + for (i = 0; i < j - 1; i++) + buf[i] = '-'; + + buf[i++] = ' '; + + strcpy(buf + i, orig); + + i += olen; + + buf[i++] = ' '; + + for (; i < len; i++) + buf[i] = '-'; + + return buf; +} + +static int ui_quirks(void) +{ + const char *nodestr = "Data address"; + char *buf; + if (!c2c.use_stdio) { dim_offset.width = 5; dim_offset.header = header_offset_tui; + nodestr = "CL"; } dim_percent_hitm.header = percent_hitm_header[c2c.display]; + + /* Fix the zero line for dcacheline column. */ + buf = fill_line("Cacheline", dim_dcacheline.width + + dim_dcacheline_node.width + + dim_dcacheline_count.width + 4); + if (!buf) + return -ENOMEM; + + dim_dcacheline.header.line[0].text = buf; + + /* Fix the zero line for offset column. */ + buf = fill_line(nodestr, dim_offset.width + + dim_offset_node.width + + dim_dcacheline_count.width + 4); + if (!buf) + return -ENOMEM; + + dim_offset.header.line[0].text = buf; + + return 0; } #define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function,percent" @@ -2473,7 +2651,7 @@ static int build_cl_output(char *cl_sort, bool no_source) "percent_lcl_hitm," "percent_stores_l1hit," "percent_stores_l1miss," - "offset,", + "offset,offset_node,dcacheline_count,", add_pid ? "pid," : "", add_tid ? "tid," : "", add_iaddr ? "iaddr," : "", @@ -2602,17 +2780,21 @@ static int perf_c2c__report(int argc, const char **argv) goto out; } - err = setup_callchain(session->evlist); + err = mem2node__init(&c2c.mem2node, &session->header.env); if (err) goto out_session; + err = setup_callchain(session->evlist); + if (err) + goto out_mem2node; + if (symbol__init(&session->header.env) < 0) - goto out_session; + goto out_mem2node; /* No pipe support at the moment. */ if (perf_data__is_pipe(session->data)) { pr_debug("No pipe support at the moment.\n"); - goto out_session; + goto out_mem2node; } if (c2c.use_stdio) @@ -2625,12 +2807,14 @@ static int perf_c2c__report(int argc, const char **argv) err = perf_session__process_events(session); if (err) { pr_err("failed to process sample\n"); - goto out_session; + goto out_mem2node; } c2c_hists__reinit(&c2c.hists, "cl_idx," "dcacheline," + "dcacheline_node," + "dcacheline_count," "tot_recs," "percent_hitm," "tot_hitm,lcl_hitm,rmt_hitm," @@ -2652,10 +2836,15 @@ static int perf_c2c__report(int argc, const char **argv) ui_progress__finish(); - ui_quirks(); + if (ui_quirks()) { + pr_err("failed to setup UI\n"); + goto out_mem2node; + } perf_c2c_display(session); +out_mem2node: + mem2node__exit(&c2c.mem2node); out_session: perf_session__delete(session); out: @@ -2706,7 +2895,7 @@ static int perf_c2c__record(int argc, const char **argv) argc = parse_options(argc, argv, options, record_mem_usage, PARSE_OPT_KEEP_UNKNOWN); - rec_argc = argc + 10; /* max number of arguments */ + rec_argc = argc + 11; /* max number of arguments */ rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (!rec_argv) return -1; @@ -2722,6 +2911,7 @@ static int perf_c2c__record(int argc, const char **argv) rec_argv[i++] = "-W"; rec_argv[i++] = "-d"; + rec_argv[i++] = "--phys-data"; rec_argv[i++] = "--sample-cpu"; for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index d660cb7b222b..39db2ee32d48 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -696,7 +696,7 @@ static void hists__process(struct hists *hists) hists__output_resort(hists, NULL); hists__fprintf(hists, !quiet, 0, 0, 0, stdout, - symbol_conf.use_callchain); + !symbol_conf.use_callchain); } static void data__fprintf(void) diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 25a42acabee1..f42f228e8899 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -72,6 +72,7 @@ static int __write_tracing_file(const char *name, const char *val, bool append) ssize_t size = strlen(val); int flags = O_WRONLY; char errbuf[512]; + char *val_copy; file = get_tracing_file(name); if (!file) { @@ -91,12 +92,23 @@ static int __write_tracing_file(const char *name, const char *val, bool append) goto out; } - if (write(fd, val, size) == size) + /* + * Copy the original value and append a '\n'. Without this, + * the kernel can hide possible errors. + */ + val_copy = strdup(val); + if (!val_copy) + goto out_close; + val_copy[size] = '\n'; + + if (write(fd, val_copy, size + 1) == size + 1) ret = 0; else pr_debug("write '%s' to tracing/%s failed: %s\n", val, name, str_error_r(errno, errbuf, sizeof(errbuf))); + free(val_copy); +out_close: close(fd); out: put_tracing_file(file); @@ -280,8 +292,10 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) signal(SIGCHLD, sig_handler); signal(SIGPIPE, sig_handler); - if (reset_tracing_files(ftrace) < 0) + if (reset_tracing_files(ftrace) < 0) { + pr_err("failed to reset ftrace\n"); goto out; + } /* reset ftrace buffer */ if (write_tracing_file("trace", "0") < 0) diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 4aca13f23b9d..1c41b4eaf73c 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -439,7 +439,7 @@ int cmd_help(int argc, const char **argv) #ifdef HAVE_LIBELF_SUPPORT "probe", #endif -#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE) +#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT) "trace", #endif NULL }; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 40fe919bbcf3..a3b346359ba0 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -440,9 +440,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, goto repipe; } - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al); - - if (al.map != NULL) { + if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) { if (!al.map->dso->hit) { al.map->dso->hit = 1; if (map__load(al.map) >= 0) { diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c index bcfb363112d3..90d1a2305b72 100644 --- a/tools/perf/builtin-kallsyms.c +++ b/tools/perf/builtin-kallsyms.c @@ -27,7 +27,7 @@ static int __cmd_kallsyms(int argc, const char **argv) for (i = 0; i < argc; ++i) { struct map *map; - struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map); + struct symbol *symbol = machine__find_kernel_symbol_by_name(machine, argv[i], &map); if (symbol == NULL) { printf("%s: not found\n", argv[i]); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index ae11e4c3516a..b63bca4b0c2a 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -729,7 +729,7 @@ static char *compact_gfp_string(unsigned long gfp_flags) static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample, unsigned int gfp_flags) { - struct pevent_record record = { + struct tep_record record = { .cpu = sample->cpu, .data = sample->raw_data, .size = sample->raw_size, @@ -747,7 +747,7 @@ static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample, } trace_seq_init(&seq); - pevent_event_info(&seq, evsel->tp_format, &record); + tep_event_info(&seq, evsel->tp_format, &record); str = strtok_r(seq.buffer, " ", &pos); while (str) { @@ -1004,7 +1004,7 @@ static void __print_slab_result(struct rb_root *root, if (is_caller) { addr = data->call_site; if (!raw_ip) - sym = machine__find_kernel_function(machine, addr, &map); + sym = machine__find_kernel_symbol(machine, addr, &map); } else addr = data->ptr; @@ -1068,7 +1068,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines) char *caller = buf; data = rb_entry(next, struct page_stat, node); - sym = machine__find_kernel_function(machine, data->callsite, &map); + sym = machine__find_kernel_symbol(machine, data->callsite, &map); if (sym) caller = sym->name; else @@ -1110,7 +1110,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines char *caller = buf; data = rb_entry(next, struct page_stat, node); - sym = machine__find_kernel_function(machine, data->callsite, &map); + sym = machine__find_kernel_symbol(machine, data->callsite, &map); if (sym) caller = sym->name; else @@ -1974,7 +1974,7 @@ int cmd_kmem(int argc, const char **argv) goto out_delete; } - kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent); + kmem_page_size = tep_get_page_size(evsel->tp_format->pevent); symbol_conf.use_callchain = true; } diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 55d919dc5bc6..2b1ef704169f 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -743,16 +743,23 @@ static bool verify_vcpu(int vcpu) static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, u64 *mmap_time) { + struct perf_evlist *evlist = kvm->evlist; union perf_event *event; + struct perf_mmap *md; u64 timestamp; s64 n = 0; int err; *mmap_time = ULLONG_MAX; - while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) { - err = perf_evlist__parse_sample_timestamp(kvm->evlist, event, ×tamp); + md = &evlist->mmap[idx]; + err = perf_mmap__read_init(md); + if (err < 0) + return (err == -EAGAIN) ? 0 : -1; + + while ((event = perf_mmap__read_event(md)) != NULL) { + err = perf_evlist__parse_sample_timestamp(evlist, event, ×tamp); if (err) { - perf_evlist__mmap_consume(kvm->evlist, idx); + perf_mmap__consume(md); pr_err("Failed to parse sample\n"); return -1; } @@ -762,7 +769,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, * FIXME: Here we can't consume the event, as perf_session__queue_event will * point to it, and it'll get possibly overwritten by the kernel. */ - perf_evlist__mmap_consume(kvm->evlist, idx); + perf_mmap__consume(md); if (err) { pr_err("Failed to enqueue sample: %d\n", err); @@ -779,6 +786,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, break; } + perf_mmap__read_done(md); return n; } @@ -1430,8 +1438,6 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, goto out; } - symbol_conf.nr_events = kvm->evlist->nr_entries; - if (perf_evlist__create_maps(kvm->evlist, &kvm->opts.target) < 0) usage_with_options(live_usage, live_options); diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 506564651cda..57393e94d156 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -83,7 +83,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) }; argc = parse_options(argc, argv, options, record_mem_usage, - PARSE_OPT_STOP_AT_NON_OPTION); + PARSE_OPT_KEEP_UNKNOWN); rec_argc = argc + 9; /* max number of arguments */ rec_argv = calloc(rec_argc + 1, sizeof(char *)); @@ -436,7 +436,7 @@ int cmd_mem(int argc, const char **argv) } argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands, - mem_usage, PARSE_OPT_STOP_AT_NON_OPTION); + mem_usage, PARSE_OPT_KEEP_UNKNOWN); if (!argc || !(strncmp(argv[0], "rec", 3) || mem.operation)) usage_with_options(mem_usage, mem_options); diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index c0065923a525..99de91698de1 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -81,8 +81,7 @@ static int parse_probe_event(const char *str) params.target_used = true; } - if (params.nsi) - pev->nsi = nsinfo__get(params.nsi); + pev->nsi = nsinfo__get(params.nsi); /* Parse a perf-probe command into event */ ret = parse_perf_probe_command(str, pev); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index a217623fec2e..22ebeb92ac51 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -45,6 +45,7 @@ #include <errno.h> #include <inttypes.h> +#include <locale.h> #include <poll.h> #include <unistd.h> #include <sched.h> @@ -70,7 +71,6 @@ struct record { struct auxtrace_record *itr; struct perf_evlist *evlist; struct perf_session *session; - const char *progname; int realtime_prio; bool no_buildid; bool no_buildid_set; @@ -273,6 +273,24 @@ static void record__read_auxtrace_snapshot(struct record *rec) } } +static int record__auxtrace_init(struct record *rec) +{ + int err; + + if (!rec->itr) { + rec->itr = auxtrace_record__init(rec->evlist, &err); + if (err) + return err; + } + + err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts, + rec->opts.auxtrace_snapshot_opts); + if (err) + return err; + + return auxtrace_parse_filters(rec->evlist); +} + #else static inline @@ -293,6 +311,11 @@ int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused) return 0; } +static int record__auxtrace_init(struct record *rec __maybe_unused) +{ + return 0; +} + #endif static int record__mmap_evlist(struct record *rec, @@ -509,7 +532,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap; if (maps[i].base) { - if (perf_mmap__push(&maps[i], overwrite, rec, record__pushfn) != 0) { + if (perf_mmap__push(&maps[i], rec, record__pushfn) != 0) { rc = -1; goto out; } @@ -731,13 +754,10 @@ static int record__synthesize(struct record *rec, bool tail) return 0; if (data->is_pipe) { - err = perf_event__synthesize_features( - tool, session, rec->evlist, process_synthesized_event); - if (err < 0) { - pr_err("Couldn't synthesize features.\n"); - return err; - } - + /* + * We need to synthesize events first, because some + * features works on top of them (on report side). + */ err = perf_event__synthesize_attrs(tool, session, process_synthesized_event); if (err < 0) { @@ -745,6 +765,13 @@ static int record__synthesize(struct record *rec, bool tail) goto out; } + err = perf_event__synthesize_features(tool, session, rec->evlist, + process_synthesized_event); + if (err < 0) { + pr_err("Couldn't synthesize features.\n"); + return err; + } + if (have_tracepoints(&rec->evlist->entries)) { /* * FIXME err <= 0 here actually means that @@ -830,7 +857,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) int status = 0; unsigned long waking = 0; const bool forks = argc > 0; - struct machine *machine; struct perf_tool *tool = &rec->tool; struct record_opts *opts = &rec->opts; struct perf_data *data = &rec->data; @@ -838,8 +864,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) bool disabled = false, draining = false; int fd; - rec->progname = argv[0]; - atexit(record__sig_exit); signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); @@ -935,8 +959,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) goto out_child; } - machine = &session->machines.host; - err = record__synthesize(rec, false); if (err < 0) goto out_child; @@ -964,6 +986,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * Let the child rip */ if (forks) { + struct machine *machine = &session->machines.host; union perf_event *event; pid_t tgid; @@ -1260,10 +1283,12 @@ static int perf_record_config(const char *var, const char *value, void *cb) return -1; return 0; } - if (!strcmp(var, "record.call-graph")) - var = "call-graph.record-mode"; /* fall-through */ + if (!strcmp(var, "record.call-graph")) { + var = "call-graph.record-mode"; + return perf_default_config(var, value, cb); + } - return perf_default_config(var, value, cb); + return 0; } struct clockid_map { @@ -1551,7 +1576,11 @@ static struct option __record_options[] = { OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize, "synthesize non-sample events at the end of output"), OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"), - OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"), + OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq, + "Fail if the specified frequency can't be used"), + OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'", + "profile at this frequency", + record__parse_freq), OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]", "number of mmap data pages and AUX area tracing mmap pages", record__parse_mmap_pages), @@ -1660,6 +1689,8 @@ int cmd_record(int argc, const char **argv) struct record *rec = &record; char errbuf[BUFSIZ]; + setlocale(LC_ALL, ""); + #ifndef HAVE_LIBBPF_SUPPORT # define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, "NO_LIBBPF=1", c) set_nobuild('\0', "clang-path", true); @@ -1720,17 +1751,6 @@ int cmd_record(int argc, const char **argv) alarm(rec->switch_output.time); } - if (!rec->itr) { - rec->itr = auxtrace_record__init(rec->evlist, &err); - if (err) - goto out; - } - - err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts, - rec->opts.auxtrace_snapshot_opts); - if (err) - goto out; - /* * Allow aliases to facilitate the lookup of symbols for address * filters. Refer to auxtrace_parse_filters(). @@ -1739,7 +1759,7 @@ int cmd_record(int argc, const char **argv) symbol__init(NULL); - err = auxtrace_parse_filters(rec->evlist); + err = record__auxtrace_init(rec); if (err) goto out; @@ -1812,7 +1832,7 @@ int cmd_record(int argc, const char **argv) err = target__validate(&rec->opts.target); if (err) { target__strerror(&rec->opts.target, err, errbuf, BUFSIZ); - ui__warning("%s", errbuf); + ui__warning("%s\n", errbuf); } err = target__parse_uid(&rec->opts.target); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 4ad5dc649716..76e12bcd1765 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -68,8 +68,10 @@ struct report { bool header; bool header_only; bool nonany_branch_mode; + bool group_set; int max_stack; struct perf_read_values show_threads_values; + struct annotation_options annotation_opts; const char *pretty_printing_style; const char *cpu_list; const char *symbol_filter_str; @@ -135,26 +137,25 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter, if (sort__mode == SORT_MODE__BRANCH) { bi = he->branch_info; - err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx); + err = addr_map_symbol__inc_samples(&bi->from, sample, evsel); if (err) goto out; - err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx); + err = addr_map_symbol__inc_samples(&bi->to, sample, evsel); } else if (rep->mem_mode) { mi = he->mem_info; - err = addr_map_symbol__inc_samples(&mi->daddr, sample, evsel->idx); + err = addr_map_symbol__inc_samples(&mi->daddr, sample, evsel); if (err) goto out; - err = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr); + err = hist_entry__inc_addr_samples(he, sample, evsel, al->addr); } else if (symbol_conf.cumulate_callchain) { if (single) - err = hist_entry__inc_addr_samples(he, sample, evsel->idx, - al->addr); + err = hist_entry__inc_addr_samples(he, sample, evsel, al->addr); } else { - err = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr); + err = hist_entry__inc_addr_samples(he, sample, evsel, al->addr); } out: @@ -180,11 +181,11 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter, rep->nonany_branch_mode); bi = he->branch_info; - err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx); + err = addr_map_symbol__inc_samples(&bi->from, sample, evsel); if (err) goto out; - err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx); + err = addr_map_symbol__inc_samples(&bi->to, sample, evsel); branch_type_count(&rep->brtype_stat, &bi->flags, bi->from.addr, bi->to.addr); @@ -193,6 +194,37 @@ out: return err; } +static void setup_forced_leader(struct report *report, + struct perf_evlist *evlist) +{ + if (report->group_set) + perf_evlist__force_leader(evlist); +} + +static int process_feature_event(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session __maybe_unused) +{ + struct report *rep = container_of(tool, struct report, tool); + + if (event->feat.feat_id < HEADER_LAST_FEATURE) + return perf_event__process_feature(tool, event, session); + + if (event->feat.feat_id != HEADER_LAST_FEATURE) { + pr_err("failed: wrong feature ID: %" PRIu64 "\n", + event->feat.feat_id); + return -1; + } + + /* + * (feat_id = HEADER_LAST_FEATURE) is the end marker which + * means all features are received, now we can force the + * group if needed. + */ + setup_forced_leader(rep, session->evlist); + return 0; +} + static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -400,8 +432,10 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report nr_samples = convert_unit(nr_samples, &unit); ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit); - if (evname != NULL) - ret += fprintf(fp, " of event '%s'", evname); + if (evname != NULL) { + ret += fprintf(fp, " of event%s '%s'", + evsel->nr_members > 1 ? "s" : "", evname); + } if (rep->time_str) ret += fprintf(fp, " (time slices: %s)", rep->time_str); @@ -444,8 +478,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, hists__fprintf_nr_sample_events(hists, rep, evname, stdout); hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout, - symbol_conf.use_callchain || - symbol_conf.show_branchflag_count); + !(symbol_conf.use_callchain || + symbol_conf.show_branchflag_count)); fprintf(stdout, "\n\n"); } @@ -481,12 +515,9 @@ static void report__warn_kptr_restrict(const struct report *rep) "As no suitable kallsyms nor vmlinux was found, kernel samples\n" "can't be resolved."; - if (kernel_map) { - const struct dso *kdso = kernel_map->dso; - if (!RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION])) { - desc = "If some relocation was applied (e.g. " - "kexec) symbols may be misresolved."; - } + if (kernel_map && map__has_symbols(kernel_map)) { + desc = "If some relocation was applied (e.g. " + "kexec) symbols may be misresolved."; } ui__warning( @@ -531,7 +562,7 @@ static int report__browse_hists(struct report *rep) ret = perf_evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent, &session->header.env, - true); + true, &rep->annotation_opts); /* * Usually "ret" is the last pressed key, and we only * care if the key notifies us to switch data file. @@ -614,6 +645,7 @@ static int stats_print(struct report *rep) static void tasks_setup(struct report *rep) { memset(&rep->tool, 0, sizeof(rep->tool)); + rep->tool.ordered_events = true; if (rep->mmaps_mode) { rep->tool.mmap = perf_event__process_mmap; rep->tool.mmap2 = perf_event__process_mmap2; @@ -675,10 +707,7 @@ static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) static int map_groups__fprintf_task(struct map_groups *mg, int indent, FILE *fp) { - int printed = 0, i; - for (i = 0; i < MAP__NR_TYPES; ++i) - printed += maps__fprintf_task(&mg->maps[i], indent, fp); - return printed; + return maps__fprintf_task(&mg->maps, indent, fp); } static void task__print_level(struct task *task, FILE *fp, int level) @@ -918,12 +947,6 @@ parse_percent_limit(const struct option *opt, const char *str, return 0; } -#define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function,percent" - -const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n" - CALLCHAIN_REPORT_HELP - "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT; - int cmd_report(int argc, const char **argv) { struct perf_session *session; @@ -932,6 +955,10 @@ int cmd_report(int argc, const char **argv) bool has_br_stack = false; int branch_mode = -1; bool branch_call_mode = false; +#define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function,percent" + const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n" + CALLCHAIN_REPORT_HELP + "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT; char callchain_default_opt[] = CALLCHAIN_DEFAULT_OPT; const char * const report_usage[] = { "perf report [<options>]", @@ -954,13 +981,14 @@ int cmd_report(int argc, const char **argv) .id_index = perf_event__process_id_index, .auxtrace_info = perf_event__process_auxtrace_info, .auxtrace = perf_event__process_auxtrace, - .feature = perf_event__process_feature, + .feature = process_feature_event, .ordered_events = true, .ordering_requires_timestamps = true, }, .max_stack = PERF_MAX_STACK_DEPTH, .pretty_printing_style = "normal", .socket_filter = -1, + .annotation_opts = annotation__default_options, }; const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", @@ -975,6 +1003,8 @@ int cmd_report(int argc, const char **argv) OPT_BOOLEAN(0, "mmaps", &report.mmaps_mode, "Display recorded tasks memory maps"), 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", &symbol_conf.force, "don't complain, do it"), @@ -1048,22 +1078,22 @@ int cmd_report(int argc, const char **argv) "list of cpus to profile"), OPT_BOOLEAN('I', "show-info", &report.show_full_info, "Display extended information about perf.data file"), - OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src, + OPT_BOOLEAN(0, "source", &report.annotation_opts.annotate_src, "Interleave source code with assembly code (default)"), - OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw, + OPT_BOOLEAN(0, "asm-raw", &report.annotation_opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), - OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", + OPT_STRING('M', "disassembler-style", &report.annotation_opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), - OPT_BOOLEAN(0, "group", &symbol_conf.event_group, + OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group, &report.group_set, "Show event group information together"), OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "", "use branch records for per branch histogram filling", parse_branch_mode), OPT_BOOLEAN(0, "branch-history", &branch_call_mode, "add last branch records to call history"), - OPT_STRING(0, "objdump", &objdump_path, "path", + OPT_STRING(0, "objdump", &report.annotation_opts.objdump_path, "path", "objdump binary to use for disassembly and annotations"), OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, "Disable symbol demangling"), @@ -1094,6 +1124,9 @@ int cmd_report(int argc, const char **argv) "Time span of interest (start,stop)"), OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name, "Show inline function"), + OPT_CALLBACK(0, "percent-type", &report.annotation_opts, "local-period", + "Set percent type local/global-period/hits", + annotate_parse_percent_type), OPT_END() }; struct perf_data data = { @@ -1173,6 +1206,8 @@ repeat: has_br_stack = perf_header__has_feat(&session->header, HEADER_BRANCH_STACK); + setup_forced_leader(&report, session->evlist); + if (itrace_synth_opts.last_branch) has_br_stack = true; @@ -1295,6 +1330,7 @@ repeat: symbol_conf.priv_size += sizeof(u32); symbol_conf.sort_by_name = true; } + annotation_config__init(); } if (symbol__init(&session->header.env) < 0) @@ -1332,6 +1368,15 @@ repeat: report.range_num = 1; } + if (session->tevent.pevent && + tep_set_function_resolver(session->tevent.pevent, + machine__resolve_kernel_addr, + &session->machines.host) < 0) { + pr_err("%s: failed to set libtraceevent function resolver\n", + __func__); + return -1; + } + sort__setup_elide(stdout); ret = __cmd_report(&report); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 83283fedb00f..cbf39dab19c1 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -254,6 +254,10 @@ struct thread_runtime { u64 total_delay_time; int last_state; + + char shortname[3]; + bool comm_changed; + u64 migrations; }; @@ -897,6 +901,37 @@ struct sort_dimension { struct list_head list; }; +/* + * handle runtime stats saved per thread + */ +static struct thread_runtime *thread__init_runtime(struct thread *thread) +{ + struct thread_runtime *r; + + r = zalloc(sizeof(struct thread_runtime)); + if (!r) + return NULL; + + init_stats(&r->run_stats); + thread__set_priv(thread, r); + + return r; +} + +static struct thread_runtime *thread__get_runtime(struct thread *thread) +{ + struct thread_runtime *tr; + + tr = thread__priv(thread); + if (tr == NULL) { + tr = thread__init_runtime(thread); + if (tr == NULL) + pr_debug("Failed to malloc memory for runtime data.\n"); + } + + return tr; +} + static int thread_lat_cmp(struct list_head *list, struct work_atoms *l, struct work_atoms *r) { @@ -1480,6 +1515,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, { const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid"); struct thread *sched_in; + struct thread_runtime *tr; int new_shortname; u64 timestamp0, timestamp = sample->time; s64 delta; @@ -1519,22 +1555,28 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, if (sched_in == NULL) return -1; + tr = thread__get_runtime(sched_in); + if (tr == NULL) { + thread__put(sched_in); + return -1; + } + sched->curr_thread[this_cpu] = thread__get(sched_in); printf(" "); new_shortname = 0; - if (!sched_in->shortname[0]) { + if (!tr->shortname[0]) { if (!strcmp(thread__comm_str(sched_in), "swapper")) { /* * Don't allocate a letter-number for swapper:0 * as a shortname. Instead, we use '.' for it. */ - sched_in->shortname[0] = '.'; - sched_in->shortname[1] = ' '; + tr->shortname[0] = '.'; + tr->shortname[1] = ' '; } else { - sched_in->shortname[0] = sched->next_shortname1; - sched_in->shortname[1] = sched->next_shortname2; + tr->shortname[0] = sched->next_shortname1; + tr->shortname[1] = sched->next_shortname2; if (sched->next_shortname1 < 'Z') { sched->next_shortname1++; @@ -1552,6 +1594,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_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 thread_runtime *curr_tr; const char *pid_color = color; const char *cpu_color = color; @@ -1569,9 +1612,14 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, else color_fprintf(stdout, cpu_color, "*"); - if (sched->curr_thread[cpu]) - color_fprintf(stdout, pid_color, "%2s ", sched->curr_thread[cpu]->shortname); - else + if (sched->curr_thread[cpu]) { + curr_tr = thread__get_runtime(sched->curr_thread[cpu]); + if (curr_tr == NULL) { + thread__put(sched_in); + return -1; + } + color_fprintf(stdout, pid_color, "%2s ", curr_tr->shortname); + } else color_fprintf(stdout, color, " "); } @@ -1580,14 +1628,15 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp)); color_fprintf(stdout, color, " %12s secs ", stimestamp); - if (new_shortname || (verbose > 0 && sched_in->tid)) { + if (new_shortname || tr->comm_changed || (verbose > 0 && sched_in->tid)) { const char *pid_color = color; if (thread__has_color(sched_in)) pid_color = COLOR_PIDS; color_fprintf(stdout, pid_color, "%s => %s:%d", - sched_in->shortname, thread__comm_str(sched_in), sched_in->tid); + tr->shortname, thread__comm_str(sched_in), sched_in->tid); + tr->comm_changed = false; } if (sched->map.comp && new_cpu) @@ -1691,6 +1740,37 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_ return err; } +static int perf_sched__process_comm(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct thread *thread; + struct thread_runtime *tr; + int err; + + err = perf_event__process_comm(tool, event, sample, machine); + if (err) + return err; + + thread = machine__find_thread(machine, sample->pid, sample->tid); + if (!thread) { + pr_err("Internal error: can't find thread\n"); + return -1; + } + + tr = thread__get_runtime(thread); + if (tr == NULL) { + thread__put(thread); + return -1; + } + + tr->comm_changed = true; + thread__put(thread); + + return 0; +} + static int perf_sched__read_events(struct perf_sched *sched) { const struct perf_evsel_str_handler handlers[] = { @@ -2063,7 +2143,7 @@ static void save_task_callchain(struct perf_sched *sched, return; } - if (!symbol_conf.use_callchain || sample->callchain == NULL) + if (!sched->show_callchain || sample->callchain == NULL) return; if (thread__resolve_callchain(thread, cursor, evsel, sample, @@ -2191,46 +2271,16 @@ static struct thread *get_idle_thread(int cpu) return idle_threads[cpu]; } -static void save_idle_callchain(struct idle_thread_runtime *itr, +static void save_idle_callchain(struct perf_sched *sched, + struct idle_thread_runtime *itr, struct perf_sample *sample) { - if (!symbol_conf.use_callchain || sample->callchain == NULL) + if (!sched->show_callchain || sample->callchain == NULL) return; callchain_cursor__copy(&itr->cursor, &callchain_cursor); } -/* - * handle runtime stats saved per thread - */ -static struct thread_runtime *thread__init_runtime(struct thread *thread) -{ - struct thread_runtime *r; - - r = zalloc(sizeof(struct thread_runtime)); - if (!r) - return NULL; - - init_stats(&r->run_stats); - thread__set_priv(thread, r); - - return r; -} - -static struct thread_runtime *thread__get_runtime(struct thread *thread) -{ - struct thread_runtime *tr; - - tr = thread__priv(thread); - if (tr == NULL) { - tr = thread__init_runtime(thread); - if (tr == NULL) - pr_debug("Failed to malloc memory for runtime data.\n"); - } - - return tr; -} - static struct thread *timehist_get_thread(struct perf_sched *sched, struct perf_sample *sample, struct machine *machine, @@ -2271,7 +2321,7 @@ static struct thread *timehist_get_thread(struct perf_sched *sched, /* copy task callchain when entering to idle */ if (perf_evsel__intval(evsel, sample, "next_pid") == 0) - save_idle_callchain(itr, sample); + save_idle_callchain(sched, itr, sample); } } @@ -2800,7 +2850,7 @@ static void timehist_print_summary(struct perf_sched *sched, printf(" CPU %2d idle entire time window\n", i); } - if (sched->idle_hist && symbol_conf.use_callchain) { + if (sched->idle_hist && sched->show_callchain) { callchain_param.mode = CHAIN_FOLDED; callchain_param.value = CCVAL_PERIOD; @@ -2884,8 +2934,7 @@ static int timehist_check_attr(struct perf_sched *sched, return -1; } - if (sched->show_callchain && - !(evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) { + if (sched->show_callchain && !evsel__has_callchain(evsel)) { pr_info("Samples do not have callchains.\n"); sched->show_callchain = 0; symbol_conf.use_callchain = 0; @@ -3291,7 +3340,7 @@ int cmd_sched(int argc, const char **argv) struct perf_sched sched = { .tool = { .sample = perf_sched__process_tracepoint_sample, - .comm = perf_event__process_comm, + .comm = perf_sched__process_comm, .namespaces = perf_event__process_namespaces, .lost = perf_event__process_lost, .fork = perf_sched__process_fork_event, diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index ab19a6ee4093..ba481d73f910 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -153,8 +153,8 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -165,8 +165,9 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD | PERF_OUTPUT_BPF_OUTPUT, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | + PERF_OUTPUT_BPF_OUTPUT, .invalid_fields = PERF_OUTPUT_TRACE, }, @@ -179,16 +180,28 @@ static struct { PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE }, + [PERF_TYPE_HW_CACHE] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, + [PERF_TYPE_RAW] = { .user_set = false, .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD | PERF_OUTPUT_ADDR | - PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT | - PERF_OUTPUT_PHYS_ADDR, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | + PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC | + PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -199,8 +212,8 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_PERIOD, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -211,8 +224,8 @@ static struct { .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | - PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | - PERF_OUTPUT_SYNTH, + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_SYNTH, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -516,7 +529,7 @@ static int perf_session__check_output_opt(struct perf_session *session) evlist__for_each_entry(session->evlist, evsel) { not_pipe = true; - if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { + if (evsel__has_callchain(evsel)) { use_callchain = true; break; } @@ -531,21 +544,18 @@ static int perf_session__check_output_opt(struct perf_session *session) */ if (symbol_conf.use_callchain && !output[PERF_TYPE_TRACEPOINT].user_set) { - struct perf_event_attr *attr; - j = PERF_TYPE_TRACEPOINT; evlist__for_each_entry(session->evlist, evsel) { if (evsel->attr.type != j) continue; - attr = &evsel->attr; - - if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) { + if (evsel__has_callchain(evsel)) { output[j].fields |= PERF_OUTPUT_IP; output[j].fields |= PERF_OUTPUT_SYM; + output[j].fields |= PERF_OUTPUT_SYMOFFSET; output[j].fields |= PERF_OUTPUT_DSO; - set_print_ip_opts(attr); + set_print_ip_opts(&evsel->attr); goto out; } } @@ -608,7 +618,7 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, if (PRINT_FIELD(COMM)) { if (latency_format) printed += fprintf(fp, "%8.8s ", thread__comm_str(thread)); - else if (PRINT_FIELD(IP) && symbol_conf.use_callchain) + else if (PRINT_FIELD(IP) && evsel__has_callchain(evsel) && symbol_conf.use_callchain) printed += fprintf(fp, "%s ", thread__comm_str(thread)); else printed += fprintf(fp, "%16s ", thread__comm_str(thread)); @@ -657,8 +667,11 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, break; case PERF_RECORD_SWITCH: case PERF_RECORD_SWITCH_CPU_WIDE: - if (has(SWITCH_OUT)) + if (has(SWITCH_OUT)) { ret += fprintf(fp, "S"); + if (sample->misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT) + ret += fprintf(fp, "p"); + } default: break; } @@ -714,8 +727,8 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, if (PRINT_FIELD(DSO)) { memset(&alf, 0, sizeof(alf)); memset(&alt, 0, sizeof(alt)); - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); + thread__find_map(thread, sample->cpumode, from, &alf); + thread__find_map(thread, sample->cpumode, to, &alt); } printed += fprintf(fp, " 0x%"PRIx64, from); @@ -761,13 +774,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, from = br->entries[i].from; to = br->entries[i].to; - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); - if (alf.map) - alf.sym = map__find_symbol(alf.map, alf.addr); - - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); - if (alt.map) - alt.sym = map__find_symbol(alt.map, alt.addr); + thread__find_symbol(thread, sample->cpumode, from, &alf); + thread__find_symbol(thread, sample->cpumode, to, &alt); printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp); if (PRINT_FIELD(DSO)) { @@ -811,12 +819,12 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, from = br->entries[i].from; to = br->entries[i].to; - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); - if (alf.map && !alf.map->dso->adjust_symbols) + if (thread__find_map(thread, sample->cpumode, from, &alf) && + !alf.map->dso->adjust_symbols) from = map__map_ip(alf.map, from); - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); - if (alt.map && !alt.map->dso->adjust_symbols) + if (thread__find_map(thread, sample->cpumode, to, &alt) && + !alt.map->dso->adjust_symbols) to = map__map_ip(alt.map, to); printed += fprintf(fp, " 0x%"PRIx64, from); @@ -879,8 +887,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return 0; } - thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al); - if (!al.map || !al.map->dso) { + if (!thread__find_map(thread, *cpumode, start, &al) || !al.map->dso) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); return 0; } @@ -930,10 +937,8 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, memset(&al, 0, sizeof(al)); - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al); - if (!al.map) - thread__find_addr_map(thread, cpumode, MAP__VARIABLE, - addr, &al); + thread__find_map(thread, cpumode, addr, &al); + if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end) return 0; @@ -1489,6 +1494,7 @@ struct perf_script { bool show_switch_events; bool show_namespace_events; bool show_lost_events; + bool show_round_events; bool allocated; bool per_event_dump; struct cpu_map *cpus; @@ -1828,6 +1834,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, struct perf_evlist *evlist; struct perf_evsel *evsel, *pos; int err; + static struct perf_evsel_script *es; err = perf_event__process_attr(tool, event, pevlist); if (err) @@ -1836,6 +1843,19 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, evlist = *pevlist; evsel = perf_evlist__last(*pevlist); + if (!evsel->priv) { + if (scr->per_event_dump) { + evsel->priv = perf_evsel_script__new(evsel, + scr->session->data); + } else { + es = zalloc(sizeof(*es)); + if (!es) + return -ENOMEM; + es->fp = stdout; + evsel->priv = es; + } + } + if (evsel->attr.type >= PERF_TYPE_MAX && evsel->attr.type != PERF_TYPE_SYNTH) return 0; @@ -2104,6 +2124,16 @@ process_lost_event(struct perf_tool *tool, return 0; } +static int +process_finished_round_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct ordered_events *oe __maybe_unused) + +{ + perf_event__fprintf(event, stdout); + return 0; +} + static void sig_handler(int sig __maybe_unused) { session_done = 1; @@ -2200,6 +2230,10 @@ static int __cmd_script(struct perf_script *script) script->tool.namespaces = process_namespaces_event; if (script->show_lost_events) script->tool.lost = process_lost_event; + if (script->show_round_events) { + script->tool.ordered_events = false; + script->tool.finished_round = process_finished_round_event; + } if (perf_script__setup_per_event_dump(script)) { pr_err("Couldn't create the per event dump files\n"); @@ -2659,8 +2693,8 @@ static int list_available_scripts(const struct option *opt __maybe_unused, } for_each_lang(scripts_path, scripts_dir, lang_dirent) { - snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, - lang_dirent->d_name); + scnprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, + lang_dirent->d_name); lang_dir = opendir(lang_path); if (!lang_dir) continue; @@ -2669,8 +2703,8 @@ static int list_available_scripts(const struct option *opt __maybe_unused, script_root = get_script_root(script_dirent, REPORT_SUFFIX); if (script_root) { desc = script_desc__findnew(script_root); - snprintf(script_path, MAXPATHLEN, "%s/%s", - lang_path, script_dirent->d_name); + scnprintf(script_path, MAXPATHLEN, "%s/%s", + lang_path, script_dirent->d_name); read_script_info(desc, script_path); free(script_root); } @@ -2706,7 +2740,7 @@ static int check_ev_match(char *dir_name, char *scriptname, int match, len; FILE *fp; - sprintf(filename, "%s/bin/%s-record", dir_name, scriptname); + scnprintf(filename, MAXPATHLEN, "%s/bin/%s-record", dir_name, scriptname); fp = fopen(filename, "r"); if (!fp) @@ -2784,13 +2818,13 @@ int find_scripts(char **scripts_array, char **scripts_path_array) } for_each_lang(scripts_path, scripts_dir, lang_dirent) { - snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, - lang_dirent->d_name); -#ifdef NO_LIBPERL + scnprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, + lang_dirent->d_name); +#ifndef HAVE_LIBPERL_SUPPORT if (strstr(lang_path, "perl")) continue; #endif -#ifdef NO_LIBPYTHON +#ifndef HAVE_LIBPYTHON_SUPPORT if (strstr(lang_path, "python")) continue; #endif @@ -2840,8 +2874,8 @@ static char *get_script_path(const char *script_root, const char *suffix) return NULL; for_each_lang(scripts_path, scripts_dir, lang_dirent) { - snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, - lang_dirent->d_name); + scnprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, + lang_dirent->d_name); lang_dir = opendir(lang_path); if (!lang_dir) continue; @@ -2852,8 +2886,8 @@ static char *get_script_path(const char *script_root, const char *suffix) free(__script_root); closedir(lang_dir); closedir(scripts_dir); - snprintf(script_path, MAXPATHLEN, "%s/%s", - lang_path, script_dirent->d_name); + scnprintf(script_path, MAXPATHLEN, "%s/%s", + lang_path, script_dirent->d_name); return strdup(script_path); } free(__script_root); @@ -3010,6 +3044,15 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused, return set_maps(script); } +static int process_feature_event(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session) +{ + if (event->feat.feat_id < HEADER_LAST_FEATURE) + return perf_event__process_feature(tool, event, session); + return 0; +} + #ifdef HAVE_AUXTRACE_SUPPORT static int perf_script__process_auxtrace_info(struct perf_tool *tool, union perf_event *event, @@ -3054,7 +3097,7 @@ int cmd_script(int argc, const char **argv) .attr = process_attr, .event_update = perf_event__process_event_update, .tracing_data = perf_event__process_tracing_data, - .feature = perf_event__process_feature, + .feature = process_feature_event, .build_id = perf_event__process_build_id, .id_index = perf_event__process_id_index, .auxtrace_info = perf_script__process_auxtrace_info, @@ -3105,8 +3148,9 @@ int cmd_script(int argc, const char **argv) "+field to add and -field to remove." "Valid types: hw,sw,trace,raw,synth. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," - "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags," - "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr", + "addr,symoff,srcline,period,iregs,uregs,brstack," + "brstacksym,flags,bpf-output,brstackinsn,brstackoff," + "callindent,insn,insnlen,synth,phys_addr,metric,misc", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), @@ -3139,6 +3183,8 @@ int cmd_script(int argc, const char **argv) "Show namespace events (if recorded)"), OPT_BOOLEAN('\0', "show-lost-events", &script.show_lost_events, "Show lost events (if recorded)"), + OPT_BOOLEAN('\0', "show-round-events", &script.show_round_events, + "Show round events (if recorded)"), OPT_BOOLEAN('\0', "per-event-dump", &script.per_event_dump, "Dump trace output to files named by the monitored events"), OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"), @@ -3383,9 +3429,9 @@ int cmd_script(int argc, const char **argv) symbol_conf.use_callchain = false; if (session->tevent.pevent && - pevent_set_function_resolver(session->tevent.pevent, - machine__resolve_kernel_addr, - &session->machines.host) < 0) { + tep_set_function_resolver(session->tevent.pevent, + machine__resolve_kernel_addr, + &session->machines.host) < 0) { pr_err("%s: failed to set libtraceevent function resolver\n", __func__); err = -1; goto out_delete; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 54a4c152edb3..d097b5b47eb8 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -65,6 +65,7 @@ #include "util/tool.h" #include "util/string2.h" #include "util/metricgroup.h" +#include "util/top.h" #include "asm/bug.h" #include <linux/time64.h> @@ -80,6 +81,9 @@ #include <sys/stat.h> #include <sys/wait.h> #include <unistd.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <sys/wait.h> #include "sane_ctype.h" @@ -141,6 +145,8 @@ static struct target target = { typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu); +#define METRIC_ONLY_LEN 20 + static int run_count = 1; static bool no_inherit = false; static volatile pid_t child_pid = -1; @@ -164,13 +170,21 @@ static bool forever = false; static bool metric_only = false; static bool force_metric_only = false; static bool no_merge = false; +static bool walltime_run_table = false; static struct timespec ref_time; static struct cpu_map *aggr_map; static aggr_get_id_t aggr_get_id; static bool append_file; +static bool interval_count; +static bool interval_clear; static const char *output_name; static int output_fd; static int print_free_counters_hint; +static int print_mixed_hw_group_error; +static u64 *walltime_run; +static bool ru_display = false; +static struct rusage ru_data; +static unsigned int metric_only_len = METRIC_ONLY_LEN; struct perf_stat { bool record; @@ -282,18 +296,6 @@ static int create_perf_stat_counter(struct perf_evsel *evsel) return perf_evsel__open_per_thread(evsel, evsel_list->threads); } -/* - * Does the counter have nsecs as a unit? - */ -static inline int nsec_counter(struct perf_evsel *evsel) -{ - if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) || - perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) - return 1; - - return 0; -} - static int process_synthesized_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused, @@ -507,14 +509,13 @@ static int perf_stat_synthesize_config(bool is_pipe) #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) -static int __store_counter_ids(struct perf_evsel *counter, - struct cpu_map *cpus, - struct thread_map *threads) +static int __store_counter_ids(struct perf_evsel *counter) { int cpu, thread; - for (cpu = 0; cpu < cpus->nr; cpu++) { - for (thread = 0; thread < threads->nr; thread++) { + for (cpu = 0; cpu < xyarray__max_x(counter->fd); cpu++) { + for (thread = 0; thread < xyarray__max_y(counter->fd); + thread++) { int fd = FD(counter, cpu, thread); if (perf_evlist__id_add_fd(evsel_list, counter, @@ -534,7 +535,7 @@ static int store_counter_ids(struct perf_evsel *counter) if (perf_evsel__alloc_id(counter, cpus->nr, threads->nr)) return -ENOMEM; - return __store_counter_ids(counter, cpus, threads); + return __store_counter_ids(counter); } static bool perf_evsel__should_store_id(struct perf_evsel *counter) @@ -568,9 +569,11 @@ static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel) return leader; } -static int __run_perf_stat(int argc, const char **argv) +static int __run_perf_stat(int argc, const char **argv, int run_idx) { int interval = stat_config.interval; + int times = stat_config.times; + int timeout = stat_config.timeout; char msg[BUFSIZ]; unsigned long long t0, t1; struct perf_evsel *counter; @@ -584,6 +587,9 @@ static int __run_perf_stat(int argc, const char **argv) if (interval) { ts.tv_sec = interval / USEC_PER_MSEC; ts.tv_nsec = (interval % USEC_PER_MSEC) * NSEC_PER_MSEC; + } else if (timeout) { + ts.tv_sec = timeout / USEC_PER_MSEC; + ts.tv_nsec = (timeout % USEC_PER_MSEC) * NSEC_PER_MSEC; } else { ts.tv_sec = 1; ts.tv_nsec = 0; @@ -632,7 +638,19 @@ try_again: if (verbose > 0) ui__warning("%s\n", msg); goto try_again; - } + } else if (target__has_per_thread(&target) && + evsel_list->threads && + evsel_list->threads->err_thread != -1) { + /* + * For global --per-thread case, skip current + * error thread. + */ + if (!thread_map__remove(evsel_list->threads, + evsel_list->threads->err_thread)) { + evsel_list->threads->err_thread = -1; + goto try_again; + } + } perf_evsel__open_strerror(counter, &target, errno, msg, sizeof(msg)); @@ -696,13 +714,17 @@ try_again: perf_evlist__start_workload(evsel_list); enable_counters(); - if (interval) { + if (interval || timeout) { while (!waitpid(child_pid, &status, WNOHANG)) { nanosleep(&ts, NULL); + if (timeout) + break; process_interval(); + if (interval_count && !(--times)) + break; } } - waitpid(child_pid, &status, 0); + wait4(child_pid, &status, 0, &ru_data); if (workload_exec_errno) { const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg)); @@ -716,8 +738,13 @@ try_again: enable_counters(); while (!done) { nanosleep(&ts, NULL); - if (interval) + if (timeout) + break; + if (interval) { process_interval(); + if (interval_count && !(--times)) + break; + } } } @@ -725,6 +752,9 @@ try_again: t1 = rdclock(); + if (walltime_run_table) + walltime_run[run_idx] = t1 - t0; + update_stats(&walltime_nsecs_stats, t1 - t0); /* @@ -739,7 +769,7 @@ try_again: return WEXITSTATUS(status); } -static int run_perf_stat(int argc, const char **argv) +static int run_perf_stat(int argc, const char **argv, int run_idx) { int ret; @@ -752,7 +782,7 @@ static int run_perf_stat(int argc, const char **argv) if (sync_run) sync(); - ret = __run_perf_stat(argc, argv); + ret = __run_perf_stat(argc, argv, run_idx); if (ret) return ret; @@ -930,8 +960,6 @@ static void print_metric_csv(void *ctx, fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit); } -#define METRIC_ONLY_LEN 20 - /* Filter out some columns that don't work well in metrics only mode */ static bool valid_only_metric(const char *unit) @@ -962,22 +990,20 @@ static void print_metric_only(void *ctx, const char *color, const char *fmt, { struct outstate *os = ctx; FILE *out = os->fh; - int n; - char buf[1024]; - unsigned mlen = METRIC_ONLY_LEN; + char buf[1024], str[1024]; + unsigned mlen = metric_only_len; if (!valid_only_metric(unit)) return; unit = fixunit(buf, os->evsel, unit); - if (color) - n = color_fprintf(out, color, fmt, val); - else - n = fprintf(out, fmt, val); - if (n > METRIC_ONLY_LEN) - n = METRIC_ONLY_LEN; if (mlen < strlen(unit)) mlen = strlen(unit) + 1; - fprintf(out, "%*s", mlen - n, ""); + + if (color) + mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1; + + color_snprintf(str, sizeof(str), color ?: "", fmt, val); + fprintf(out, "%*s ", mlen, str); } static void print_metric_only_csv(void *ctx, const char *color __maybe_unused, @@ -1017,35 +1043,7 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused, if (csv_output) fprintf(os->fh, "%s%s", unit, csv_sep); else - fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit); -} - -static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) -{ - FILE *output = stat_config.output; - double msecs = avg / NSEC_PER_MSEC; - const char *fmt_v, *fmt_n; - char name[25]; - - fmt_v = csv_output ? "%.6f%s" : "%18.6f%s"; - fmt_n = csv_output ? "%s" : "%-25s"; - - aggr_printout(evsel, id, nr); - - scnprintf(name, sizeof(name), "%s%s", - perf_evsel__name(evsel), csv_output ? "" : " (msec)"); - - fprintf(output, fmt_v, msecs, csv_sep); - - if (csv_output) - fprintf(output, "%s%s", evsel->unit, csv_sep); - else - fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep); - - fprintf(output, fmt_n, name); - - if (evsel->cgrp) - fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); + fprintf(os->fh, "%*s ", metric_only_len, unit); } static int first_shadow_cpu(struct perf_evsel *evsel, int id) @@ -1100,6 +1098,30 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); } +static bool is_mixed_hw_group(struct perf_evsel *counter) +{ + struct perf_evlist *evlist = counter->evlist; + u32 pmu_type = counter->attr.type; + struct perf_evsel *pos; + + if (counter->nr_members < 2) + return false; + + evlist__for_each_entry(evlist, pos) { + /* software events can be part of any hardware group */ + if (pos->attr.type == PERF_TYPE_SOFTWARE) + continue; + if (pmu_type == PERF_TYPE_SOFTWARE) { + pmu_type = pos->attr.type; + continue; + } + if (pmu_type != pos->attr.type) + return true; + } + + return false; +} + static void printout(int id, int nr, struct perf_evsel *counter, double uval, char *prefix, u64 run, u64 ena, double noise, struct runtime_stat *st) @@ -1152,8 +1174,11 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep); - if (counter->supported) + if (counter->supported) { print_free_counters_hint = 1; + if (is_mixed_hw_group(counter)) + print_mixed_hw_group_error = 1; + } fprintf(stat_config.output, "%-*s%s", csv_output ? 0 : unit_width, @@ -1176,11 +1201,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, return; } - if (metric_only) - /* nothing */; - else if (nsec_counter(counter)) - nsec_printout(id, nr, counter, uval); - else + if (!metric_only) abs_printout(id, nr, counter, uval); out.print_metric = pm; @@ -1225,6 +1246,34 @@ static void aggr_update_shadow(void) } } +static void uniquify_event_name(struct perf_evsel *counter) +{ + char *new_name; + char *config; + + if (counter->uniquified_name || + !counter->pmu_name || !strncmp(counter->name, counter->pmu_name, + strlen(counter->pmu_name))) + return; + + config = strchr(counter->name, '/'); + if (config) { + if (asprintf(&new_name, + "%s%s", counter->pmu_name, config) > 0) { + free(counter->name); + counter->name = new_name; + } + } else { + if (asprintf(&new_name, + "%s [%s]", counter->name, counter->pmu_name) > 0) { + free(counter->name); + counter->name = new_name; + } + } + + counter->uniquified_name = true; +} + static void collect_all_aliases(struct perf_evsel *counter, void (*cb)(struct perf_evsel *counter, void *data, bool first), @@ -1238,7 +1287,7 @@ static void collect_all_aliases(struct perf_evsel *counter, alias->scale != counter->scale || alias->cgrp != counter->cgrp || strcmp(alias->unit, counter->unit) || - nsec_counter(alias) != nsec_counter(counter)) + perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter)) break; alias->merged_stat = true; cb(alias, data, false); @@ -1253,7 +1302,9 @@ static bool collect_data(struct perf_evsel *counter, if (counter->merged_stat) return false; cb(counter, data, true); - if (!no_merge && counter->auto_merge_stats) + if (no_merge) + uniquify_event_name(counter); + else if (counter->auto_merge_stats) collect_all_aliases(counter, cb, data); return true; } @@ -1610,9 +1661,12 @@ static void print_interval(char *prefix, struct timespec *ts) FILE *output = stat_config.output; static int num_print_interval; + if (interval_clear) + puts(CONSOLE_CLEAR); + sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep); - if (num_print_interval == 0 && !csv_output) { + if ((num_print_interval == 0 && !csv_output) || interval_clear) { switch (stat_config.aggr_mode) { case AGGR_SOCKET: fprintf(output, "# time socket cpus"); @@ -1625,7 +1679,7 @@ static void print_interval(char *prefix, struct timespec *ts) fprintf(output, " counts %*s events\n", unit_width, "unit"); break; case AGGR_NONE: - fprintf(output, "# time CPU"); + fprintf(output, "# time CPU "); if (!metric_only) fprintf(output, " counts %*s events\n", unit_width, "unit"); break; @@ -1644,7 +1698,7 @@ static void print_interval(char *prefix, struct timespec *ts) } } - if (num_print_interval == 0 && metric_only) + if ((num_print_interval == 0 || interval_clear) && metric_only) print_metric_headers(" ", true); if (++num_print_interval == 25) num_print_interval = 0; @@ -1680,19 +1734,81 @@ static void print_header(int argc, const char **argv) } } +static int get_precision(double num) +{ + if (num > 1) + return 0; + + return lround(ceil(-log10(num))); +} + +static void print_table(FILE *output, int precision, double avg) +{ + char tmp[64]; + int idx, indent = 0; + + scnprintf(tmp, 64, " %17.*f", precision, avg); + while (tmp[indent] == ' ') + indent++; + + fprintf(output, "%*s# Table of individual measurements:\n", indent, ""); + + for (idx = 0; idx < run_count; idx++) { + double run = (double) walltime_run[idx] / NSEC_PER_SEC; + int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5); + + fprintf(output, " %17.*f (%+.*f) ", + precision, run, precision, run - avg); + + for (h = 0; h < n; h++) + fprintf(output, "#"); + + fprintf(output, "\n"); + } + + fprintf(output, "\n%*s# Final result:\n", indent, ""); +} + +static double timeval2double(struct timeval *t) +{ + return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC; +} + static void print_footer(void) { + double avg = avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC; FILE *output = stat_config.output; int n; if (!null_run) fprintf(output, "\n"); - fprintf(output, " %17.9f seconds time elapsed", - avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC); - if (run_count > 1) { - fprintf(output, " "); - print_noise_pct(stddev_stats(&walltime_nsecs_stats), - avg_stats(&walltime_nsecs_stats)); + + if (run_count == 1) { + fprintf(output, " %17.9f seconds time elapsed", avg); + + if (ru_display) { + double ru_utime = timeval2double(&ru_data.ru_utime); + double ru_stime = timeval2double(&ru_data.ru_stime); + + fprintf(output, "\n\n"); + fprintf(output, " %17.9f seconds user\n", ru_utime); + fprintf(output, " %17.9f seconds sys\n", ru_stime); + } + } else { + double sd = stddev_stats(&walltime_nsecs_stats) / NSEC_PER_SEC; + /* + * Display at most 2 more significant + * digits than the stddev inaccuracy. + */ + int precision = get_precision(sd) + 2; + + if (walltime_run_table) + print_table(output, precision, avg); + + fprintf(output, " %17.*f +- %.*f seconds time elapsed", + precision, avg, precision, sd); + + print_noise_pct(sd, avg); } fprintf(output, "\n\n"); @@ -1704,6 +1820,11 @@ static void print_footer(void) " echo 0 > /proc/sys/kernel/nmi_watchdog\n" " perf stat ...\n" " echo 1 > /proc/sys/kernel/nmi_watchdog\n"); + + if (print_mixed_hw_group_error) + fprintf(output, + "The events in group usually have to be from " + "the same PMU. Try reorganizing the group.\n"); } static void print_counters(struct timespec *ts, int argc, const char **argv) @@ -1863,6 +1984,8 @@ static const struct option stat_options[] = { "be more verbose (show counter open errors, etc)"), OPT_INTEGER('r', "repeat", &run_count, "repeat command and print average + stddev (max: 100, forever: 0)"), + OPT_BOOLEAN(0, "table", &walltime_run_table, + "display details about each run (only with -r option)"), OPT_BOOLEAN('n', "null", &null_run, "null run - dont start any counters"), OPT_INCR('d', "detailed", &detailed_run, @@ -1890,7 +2013,14 @@ static const struct option stat_options[] = { OPT_STRING(0, "post", &post_cmd, "command", "command to run after to the measured command"), OPT_UINTEGER('I', "interval-print", &stat_config.interval, - "print counts at regular interval in ms (>= 10)"), + "print counts at regular interval in ms " + "(overhead is possible for values <= 100ms)"), + OPT_INTEGER(0, "interval-count", &stat_config.times, + "print counts for fixed number of times"), + OPT_BOOLEAN(0, "interval-clear", &interval_clear, + "clear screen in between new interval"), + OPT_UINTEGER(0, "timeout", &stat_config.timeout, + "stop workload and print counts after a timeout period in ms (>= 10ms)"), OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode, "aggregate counts per processor socket", AGGR_SOCKET), OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode, @@ -2268,19 +2398,36 @@ 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 (null_run) return 0; if (transaction_run) { + /* Handle -T as -M transaction. Once platform specific metrics + * support has been added to the json files, all archictures + * will use this approach. To determine transaction support + * on an architecture test for such a metric name. + */ + if (metricgroup__has_metric("transaction")) { + struct option opt = { .value = &evsel_list }; + + return metricgroup__parse_groups(&opt, "transaction", + &metric_events); + } + if (pmu_have_event("cpu", "cycles-ct") && pmu_have_event("cpu", "el-start")) - err = parse_events(evsel_list, transaction_attrs, NULL); + err = parse_events(evsel_list, transaction_attrs, + &errinfo); else - err = parse_events(evsel_list, transaction_limited_attrs, NULL); + err = parse_events(evsel_list, + transaction_limited_attrs, + &errinfo); if (err) { fprintf(stderr, "Cannot set up transaction events\n"); + parse_events_print_error(&errinfo, transaction_attrs); return -1; } return 0; @@ -2306,10 +2453,11 @@ static int add_default_attributes(void) pmu_have_event("msr", "smi")) { if (!force_metric_only) metric_only = true; - err = parse_events(evsel_list, smi_cost_attrs, NULL); + err = parse_events(evsel_list, smi_cost_attrs, &errinfo); } else { 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 (err) { @@ -2344,12 +2492,13 @@ static int add_default_attributes(void) if (topdown_attrs[0] && str) { if (warn) arch_topdown_group_warn(); - err = parse_events(evsel_list, str, NULL); + err = parse_events(evsel_list, str, &errinfo); if (err) { fprintf(stderr, "Cannot set up top down events %s: %d\n", str, err); free(str); + parse_events_print_error(&errinfo, str); return -1; } } else { @@ -2688,7 +2837,7 @@ int cmd_stat(int argc, const char **argv) int status = -EINVAL, run_idx; const char *mode; FILE *output = stderr; - unsigned int interval; + unsigned int interval, timeout; const char * const stat_subcommands[] = { "record", "report" }; setlocale(LC_ALL, ""); @@ -2719,6 +2868,7 @@ int cmd_stat(int argc, const char **argv) return __cmd_report(argc, argv); interval = stat_config.interval; + timeout = stat_config.timeout; /* * For record command the -o is already taken care of. @@ -2743,6 +2893,13 @@ int cmd_stat(int argc, const char **argv) goto out; } + if (walltime_run_table && run_count <= 1) { + fprintf(stderr, "--table is only supported with -r\n"); + parse_options_usage(stat_usage, stat_options, "r", 1); + parse_options_usage(NULL, stat_options, "table", 0); + goto out; + } + if (output_fd < 0) { fprintf(stderr, "argument to --log-fd must be a > 0\n"); parse_options_usage(stat_usage, stat_options, "log-fd", 0); @@ -2788,6 +2945,13 @@ int cmd_stat(int argc, const char **argv) setup_system_wide(argc); + /* + * Display user/system times only for single + * run and when there's specified tracee. + */ + if ((run_count == 1) && target__none(&target)) + ru_display = true; + if (run_count < 0) { pr_err("Run count must be a positive number\n"); parse_options_usage(stat_usage, stat_options, "r", 1); @@ -2797,6 +2961,14 @@ int cmd_stat(int argc, const char **argv) run_count = 1; } + if (walltime_run_table) { + walltime_run = zalloc(run_count * sizeof(walltime_run[0])); + if (!walltime_run) { + pr_err("failed to setup -r option"); + goto out; + } + } + if ((stat_config.aggr_mode == AGGR_THREAD) && !target__has_task(&target)) { if (!target.system_wide || target.cpu_list) { @@ -2860,16 +3032,32 @@ int cmd_stat(int argc, const char **argv) } } - if (interval && interval < 100) { - if (interval < 10) { - pr_err("print interval must be >= 10ms\n"); - parse_options_usage(stat_usage, stat_options, "I", 1); + if (stat_config.times && interval) + interval_count = true; + else if (stat_config.times && !interval) { + pr_err("interval-count option should be used together with " + "interval-print.\n"); + parse_options_usage(stat_usage, stat_options, "interval-count", 0); + parse_options_usage(stat_usage, stat_options, "I", 1); + goto out; + } + + if (timeout && timeout < 100) { + if (timeout < 10) { + pr_err("timeout must be >= 10ms.\n"); + parse_options_usage(stat_usage, stat_options, "timeout", 0); goto out; } else - pr_warning("print interval < 100ms. " + pr_warning("timeout < 100ms. " "The overhead percentage could be high in some cases. " "Please proceed with caution.\n"); } + if (timeout && interval) { + pr_err("timeout option is not supported with interval-print.\n"); + parse_options_usage(stat_usage, stat_options, "timeout", 0); + parse_options_usage(stat_usage, stat_options, "I", 1); + goto out; + } if (perf_evlist__alloc_stats(evsel_list, interval)) goto out; @@ -2896,7 +3084,7 @@ int cmd_stat(int argc, const char **argv) fprintf(output, "[ perf stat: executing run #%d ... ]\n", run_idx + 1); - status = run_perf_stat(argc, argv); + status = run_perf_stat(argc, argv, run_idx); if (forever && status != -1) { print_counters(NULL, argc, argv); perf_stat__reset_stats(); @@ -2944,6 +3132,8 @@ int cmd_stat(int argc, const char **argv) perf_stat__exit_aggr_mode(); perf_evlist__free_stats(evsel_list); out: + free(walltime_run); + if (smi_cost && smi_reset) sysfs__write_int(FREEZE_ON_SMI_PATH, 0); diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 813698a9b8c7..a827919c6263 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -533,12 +533,8 @@ static const char *cat_backtrace(union perf_event *event, } tal.filtered = 0; - thread__find_addr_location(al.thread, cpumode, - MAP__FUNCTION, ip, &tal); - - if (tal.sym) - fprintf(f, "..... %016" PRIx64 " %s\n", ip, - tal.sym->name); + if (thread__find_symbol(al.thread, cpumode, ip, &tal)) + fprintf(f, "..... %016" PRIx64 " %s\n", ip, tal.sym->name); else fprintf(f, "..... %016" PRIx64 "\n", ip); } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 35ac016fcb98..d21d8751e749 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -123,14 +123,9 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) } notes = symbol__annotation(sym); - if (notes->src != NULL) { - pthread_mutex_lock(¬es->lock); - goto out_assign; - } - pthread_mutex_lock(¬es->lock); - if (symbol__alloc_hist(sym) < 0) { + if (!symbol__hists(sym, top->evlist->nr_entries)) { pthread_mutex_unlock(¬es->lock); pr_err("Not enough memory for annotating '%s' symbol!\n", sym->name); @@ -138,9 +133,8 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) return err; } - err = symbol__annotate(sym, map, evsel, 0, NULL); + err = symbol__annotate(sym, map, evsel, 0, &top->annotation_opts, NULL); if (err == 0) { -out_assign: top->sym_filter_entry = he; } else { char msg[BUFSIZ]; @@ -188,7 +182,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip) static void perf_top__record_precise_ip(struct perf_top *top, struct hist_entry *he, struct perf_sample *sample, - int counter, u64 ip) + struct perf_evsel *evsel, u64 ip) { struct annotation *notes; struct symbol *sym = he->ms.sym; @@ -204,7 +198,7 @@ static void perf_top__record_precise_ip(struct perf_top *top, if (pthread_mutex_trylock(¬es->lock)) return; - err = hist_entry__inc_addr_samples(he, sample, counter, ip); + err = hist_entry__inc_addr_samples(he, sample, evsel, ip); pthread_mutex_unlock(¬es->lock); @@ -249,10 +243,9 @@ static void perf_top__show_details(struct perf_top *top) goto out_unlock; printf("Showing %s for %s\n", perf_evsel__name(top->sym_evsel), symbol->name); - printf(" Events Pcnt (>=%d%%)\n", top->sym_pcnt_filter); + printf(" Events Pcnt (>=%d%%)\n", top->annotation_opts.min_pcnt); - more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel, - 0, top->sym_pcnt_filter, top->print_entries, 4); + more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel, &top->annotation_opts); if (top->evlist->enabled) { if (top->zero) @@ -314,7 +307,7 @@ static void perf_top__print_sym_table(struct perf_top *top) hists__output_recalc_col_len(hists, top->print_entries - printed); putchar('\n'); hists__fprintf(hists, false, top->print_entries - printed, win_width, - top->min_percent, stdout, symbol_conf.use_callchain); + top->min_percent, stdout, !symbol_conf.use_callchain); } static void prompt_integer(int *target, const char *msg) @@ -412,7 +405,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top) fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top->count_filter); - fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", top->sym_pcnt_filter); + fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", top->annotation_opts.min_pcnt); fprintf(stdout, "\t[s] annotate symbol. \t(%s)\n", name?: "NULL"); fprintf(stdout, "\t[S] stop annotation.\n"); @@ -515,7 +508,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) prompt_integer(&top->count_filter, "Enter display event count filter"); break; case 'F': - prompt_percent(&top->sym_pcnt_filter, + prompt_percent(&top->annotation_opts.min_pcnt, "Enter details display event filter (percent)"); break; case 'K': @@ -613,7 +606,8 @@ static void *display_thread_tui(void *arg) perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, &top->session->header.env, - !top->record_opts.overwrite); + !top->record_opts.overwrite, + &top->annotation_opts); done = 1; return NULL; @@ -691,7 +685,7 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter, struct perf_evsel *evsel = iter->evsel; if (perf_hpp_list.sym && single) - perf_top__record_precise_ip(top, he, iter->sample, evsel->idx, al->addr); + perf_top__record_precise_ip(top, he, iter->sample, evsel, al->addr); hist__account_cycles(iter->sample->branch_stack, al, iter->sample, !(top->record_opts.branch_stack & PERF_SAMPLE_BRANCH_ANY)); @@ -742,7 +736,7 @@ static void perf_event__process_sample(struct perf_tool *tool, "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n" "Check /proc/sys/kernel/kptr_restrict.\n\n" "Kernel%s samples will not be resolved.\n", - al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ? + al.map && map__has_symbols(al.map) ? " modules" : ""); if (use_browser <= 0) sleep(5); @@ -750,7 +744,7 @@ static void perf_event__process_sample(struct perf_tool *tool, machine->kptr_restrict_warned = true; } - if (al.sym == NULL) { + if (al.sym == NULL && al.map != NULL) { const char *msg = "Kernel samples will not be resolved.\n"; /* * As we do lazy loading of symtabs we only will know if the @@ -764,8 +758,7 @@ static void perf_event__process_sample(struct perf_tool *tool, * invalid --vmlinux ;-) */ if (!machine->kptr_restrict_warned && !top->vmlinux_warned && - al.map == machine->vmlinux_maps[MAP__FUNCTION] && - RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) { + __map__is_kernel(al.map) && map__has_symbols(al.map)) { if (symbol_conf.vmlinux_name) { char serr[256]; dso__strerror_load(al.map->dso, serr, sizeof(serr)); @@ -817,14 +810,13 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) struct perf_session *session = top->session; union perf_event *event; struct machine *machine; - u64 end, start; int ret; md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx]; - if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0) + if (perf_mmap__read_init(md) < 0) return; - while ((event = perf_mmap__read_event(md, opts->overwrite, &start, end)) != NULL) { + while ((event = perf_mmap__read_event(md)) != NULL) { ret = perf_evlist__parse_sample(evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); @@ -879,7 +871,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) } else ++session->evlist->stats.nr_unknown_events; next_event: - perf_mmap__consume(md, opts->overwrite); + perf_mmap__consume(md); } perf_mmap__read_done(md); @@ -1085,8 +1077,9 @@ static int __cmd_top(struct perf_top *top) if (top->session == NULL) return -1; - if (!objdump_path) { - ret = perf_env__lookup_objdump(&top->session->header.env); + if (!top->annotation_opts.objdump_path) { + ret = perf_env__lookup_objdump(&top->session->header.env, + &top->annotation_opts.objdump_path); if (ret) goto out_delete; } @@ -1224,8 +1217,10 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset) static int perf_top_config(const char *var, const char *value, void *cb __maybe_unused) { - if (!strcmp(var, "top.call-graph")) - var = "call-graph.record-mode"; /* fall-through */ + if (!strcmp(var, "top.call-graph")) { + var = "call-graph.record-mode"; + return perf_default_config(var, value, cb); + } if (!strcmp(var, "top.children")) { symbol_conf.cumulate_callchain = perf_config_bool(var, value); return 0; @@ -1264,8 +1259,8 @@ int cmd_top(int argc, const char **argv) .proc_map_timeout = 500, .overwrite = 1, }, - .max_stack = sysctl_perf_event_max_stack, - .sym_pcnt_filter = 5, + .max_stack = sysctl__max_stack(), + .annotation_opts = annotation__default_options, .nr_threads_synthesize = UINT_MAX, }; struct record_opts *opts = &top.record_opts; @@ -1307,7 +1302,9 @@ int cmd_top(int argc, const char **argv) OPT_STRING(0, "sym-annotate", &top.sym_filter, "symbol name", "symbol to annotate"), OPT_BOOLEAN('z', "zero", &top.zero, "zero history across updates"), - OPT_UINTEGER('F', "freq", &opts->user_freq, "profile at this frequency"), + OPT_CALLBACK('F', "freq", &top.record_opts, "freq or 'max'", + "profile at this frequency", + record__parse_freq), OPT_INTEGER('E', "entries", &top.print_entries, "display this many functions"), OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols, @@ -1345,15 +1342,15 @@ int cmd_top(int argc, const char **argv) "only consider symbols in these comms"), OPT_STRING(0, "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", "only consider these symbols"), - OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src, + OPT_BOOLEAN(0, "source", &top.annotation_opts.annotate_src, "Interleave source code with assembly code (default)"), - OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw, + OPT_BOOLEAN(0, "asm-raw", &top.annotation_opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), - OPT_STRING(0, "objdump", &objdump_path, "path", + OPT_STRING(0, "objdump", &top.annotation_opts.objdump_path, "path", "objdump binary to use for disassembly and annotations"), - OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", + OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"), OPT_CALLBACK(0, "percent-limit", &top, "percent", @@ -1389,6 +1386,9 @@ int cmd_top(int argc, const char **argv) if (status < 0) return status; + top.annotation_opts.min_pcnt = 5; + top.annotation_opts.context = 4; + top.evlist = perf_evlist__new(); if (top.evlist == NULL) return -ENOMEM; @@ -1466,8 +1466,6 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } - symbol_conf.nr_events = top.evlist->nr_entries; - if (top.delay_secs < 1) top.delay_secs = 1; @@ -1490,6 +1488,8 @@ int cmd_top(int argc, const char **argv) if (status < 0) goto out_delete_evlist; + annotation_config__init(); + symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); if (symbol__init(NULL) < 0) return -1; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index e7f1b182fc15..22ab8e67c760 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -19,6 +19,7 @@ #include <traceevent/event-parse.h> #include <api/fs/tracing_path.h> #include "builtin.h" +#include "util/cgroup.h" #include "util/color.h" #include "util/debug.h" #include "util/env.h" @@ -76,13 +77,15 @@ struct trace { struct syscall *table; struct { struct perf_evsel *sys_enter, - *sys_exit; + *sys_exit, + *augmented; } events; } syscalls; struct record_opts opts; struct perf_evlist *evlist; struct machine *host; struct thread *current; + struct cgroup *cgroup; u64 base_time; FILE *output; unsigned long nr_events; @@ -110,6 +113,7 @@ struct trace { bool multiple_threads; bool summary; bool summary_only; + bool failure_only; bool show_comm; bool print_sample; bool show_tool_stats; @@ -118,7 +122,6 @@ struct trace { bool force; bool vfs_getname; int trace_pgfaults; - int open_id; }; struct tp_field { @@ -154,13 +157,11 @@ TP_UINT_FIELD__SWAPPED(16); TP_UINT_FIELD__SWAPPED(32); TP_UINT_FIELD__SWAPPED(64); -static int tp_field__init_uint(struct tp_field *field, - struct format_field *format_field, - bool needs_swap) +static int __tp_field__init_uint(struct tp_field *field, int size, int offset, bool needs_swap) { - field->offset = format_field->offset; + field->offset = offset; - switch (format_field->size) { + switch (size) { case 1: field->integer = tp_field__u8; break; @@ -180,18 +181,28 @@ static int tp_field__init_uint(struct tp_field *field, return 0; } +static int tp_field__init_uint(struct tp_field *field, struct format_field *format_field, bool needs_swap) +{ + return __tp_field__init_uint(field, format_field->size, format_field->offset, needs_swap); +} + static void *tp_field__ptr(struct tp_field *field, struct perf_sample *sample) { return sample->raw_data + field->offset; } -static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field) +static int __tp_field__init_ptr(struct tp_field *field, int offset) { - field->offset = format_field->offset; + field->offset = offset; field->pointer = tp_field__ptr; return 0; } +static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field) +{ + return __tp_field__init_ptr(field, format_field->offset); +} + struct syscall_tp { struct tp_field id; union { @@ -237,7 +248,47 @@ static void perf_evsel__delete_priv(struct perf_evsel *evsel) perf_evsel__delete(evsel); } -static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel, void *handler) +static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel) +{ + struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp)); + + if (evsel->priv != NULL) { + if (perf_evsel__init_tp_uint_field(evsel, &sc->id, "__syscall_nr")) + goto out_delete; + return 0; + } + + return -ENOMEM; +out_delete: + zfree(&evsel->priv); + return -ENOENT; +} + +static int perf_evsel__init_augmented_syscall_tp(struct perf_evsel *evsel) +{ + struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp)); + + if (evsel->priv != NULL) { /* field, sizeof_field, offsetof_field */ + if (__tp_field__init_uint(&sc->id, sizeof(long), sizeof(long long), evsel->needs_swap)) + goto out_delete; + + return 0; + } + + return -ENOMEM; +out_delete: + zfree(&evsel->priv); + return -EINVAL; +} + +static int perf_evsel__init_augmented_syscall_tp_args(struct perf_evsel *evsel) +{ + struct syscall_tp *sc = evsel->priv; + + return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64)); +} + +static int perf_evsel__init_raw_syscall_tp(struct perf_evsel *evsel, void *handler) { evsel->priv = malloc(sizeof(struct syscall_tp)); if (evsel->priv != NULL) { @@ -255,7 +306,7 @@ out_delete: return -ENOENT; } -static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void *handler) +static struct perf_evsel *perf_evsel__raw_syscall_newtp(const char *direction, void *handler) { struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction); @@ -266,7 +317,7 @@ static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void if (IS_ERR(evsel)) return NULL; - if (perf_evsel__init_syscall_tp(evsel, handler)) + if (perf_evsel__init_raw_syscall_tp(evsel, handler)) goto out_delete; return evsel; @@ -288,7 +339,7 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha { int idx = val - sa->offset; - if (idx < 0 || idx >= sa->nr_entries) + if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL) return scnprintf(bf, size, intfmt, val); return scnprintf(bf, size, "%s", sa->entries[idx]); @@ -758,10 +809,12 @@ static struct syscall_fmt { .arg = { [0] = STRARRAY(resource, rlimit_resources), }, }, { .name = "socket", .arg = { [0] = STRARRAY(family, socket_families), - [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, }, + [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, + [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, }, { .name = "socketpair", .arg = { [0] = STRARRAY(family, socket_families), - [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, }, + [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, + [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, }, { .name = "stat", .alias = "newstat", }, { .name = "statx", .arg = { [0] = { .scnprintf = SCA_FDAT, /* fdat */ }, @@ -800,12 +853,17 @@ static struct syscall_fmt *syscall_fmt__find(const char *name) return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp); } +/* + * is_exit: is this "exit" or "exit_group"? + * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter. + */ struct syscall { struct event_format *tp_format; int nr_args; + bool is_exit; + bool is_open; struct format_field *args; const char *name; - bool is_exit; struct syscall_fmt *fmt; struct syscall_arg_fmt *arg_fmt; }; @@ -1294,6 +1352,7 @@ static int trace__read_syscall_info(struct trace *trace, int id) } sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit"); + sc->is_open = !strcmp(name, "open") || !strcmp(name, "openat"); return syscall__set_arg_fmts(sc); } @@ -1563,7 +1622,7 @@ static int trace__printf_interrupted_entry(struct trace *trace) struct thread_trace *ttrace; size_t printed; - if (trace->current == NULL) + if (trace->failure_only || trace->current == NULL) return 0; ttrace = thread__priv(trace->current); @@ -1636,7 +1695,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, args, trace, thread); if (sc->is_exit) { - if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) { + if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) { trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output); fprintf(trace->output, "%-70s)\n", ttrace->entry_str); } @@ -1656,6 +1715,37 @@ out_put: return err; } +static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evsel, + struct perf_sample *sample) +{ + struct thread_trace *ttrace; + struct thread *thread; + int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1; + struct syscall *sc = trace__syscall_info(trace, evsel, id); + char msg[1024]; + void *args; + + if (sc == NULL) + return -1; + + thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); + ttrace = thread__trace(thread, trace->output); + /* + * We need to get ttrace just to make sure it is there when syscall__scnprintf_args() + * and the rest of the beautifiers accessing it via struct syscall_arg touches it. + */ + if (ttrace == NULL) + goto out_put; + + args = perf_evsel__sc_tp_ptr(evsel, args, sample); + syscall__scnprintf_args(sc, msg, sizeof(msg), args, trace, thread); + fprintf(trace->output, "%s", msg); + err = 0; +out_put: + thread__put(thread); + return err; +} + static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evsel, struct perf_sample *sample, struct callchain_cursor *cursor) @@ -1717,7 +1807,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, ret = perf_evsel__sc_tp_uint(evsel, ret, sample); - if (id == trace->open_id && ret >= 0 && ttrace->filename.pending_open) { + if (sc->is_open && ret >= 0 && ttrace->filename.pending_open) { trace__set_fd_pathname(thread, ret, ttrace->filename.name); ttrace->filename.pending_open = false; ++trace->stats.vfs_getname; @@ -1740,7 +1830,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, } } - if (trace->summary_only) + if (trace->summary_only || (ret >= 0 && trace->failure_only)) goto out; trace__fprintf_entry_head(trace, thread, duration, duration_calculated, ttrace->entry_time, trace->output); @@ -1952,14 +2042,20 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, fprintf(trace->output, "%s:", evsel->name); if (perf_evsel__is_bpf_output(evsel)) { - bpf_output__fprintf(trace, sample); + if (evsel == trace->syscalls.events.augmented) + trace__fprintf_sys_enter(trace, evsel, sample); + else + bpf_output__fprintf(trace, sample); } else if (evsel->tp_format) { - event_format__fprintf(evsel->tp_format, sample->cpu, - sample->raw_data, sample->raw_size, - trace->output); + if (strncmp(evsel->tp_format->name, "sys_enter_", 10) || + trace__fprintf_sys_enter(trace, evsel, sample)) { + event_format__fprintf(evsel->tp_format, sample->cpu, + sample->raw_data, sample->raw_size, + trace->output); + } } - fprintf(trace->output, ")\n"); + fprintf(trace->output, "\n"); if (callchain_ret > 0) trace__fprintf_callchain(trace, sample); @@ -2021,8 +2117,7 @@ static int trace__pgfault(struct trace *trace, if (trace->summary_only) goto out; - thread__find_addr_location(thread, sample->cpumode, MAP__FUNCTION, - sample->ip, &al); + thread__find_symbol(thread, sample->cpumode, sample->ip, &al); trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output); @@ -2034,12 +2129,10 @@ static int trace__pgfault(struct trace *trace, fprintf(trace->output, "] => "); - thread__find_addr_location(thread, sample->cpumode, MAP__VARIABLE, - sample->addr, &al); + thread__find_symbol(thread, sample->cpumode, sample->addr, &al); if (!al.map) { - thread__find_addr_location(thread, sample->cpumode, - MAP__FUNCTION, sample->addr, &al); + thread__find_symbol(thread, sample->cpumode, sample->addr, &al); if (al.map) map_type = 'x'; @@ -2240,14 +2333,14 @@ static int trace__add_syscall_newtp(struct trace *trace) struct perf_evlist *evlist = trace->evlist; struct perf_evsel *sys_enter, *sys_exit; - sys_enter = perf_evsel__syscall_newtp("sys_enter", trace__sys_enter); + sys_enter = perf_evsel__raw_syscall_newtp("sys_enter", trace__sys_enter); if (sys_enter == NULL) goto out; if (perf_evsel__init_sc_tp_ptr_field(sys_enter, args)) goto out_delete_sys_enter; - sys_exit = perf_evsel__syscall_newtp("sys_exit", trace__sys_exit); + sys_exit = perf_evsel__raw_syscall_newtp("sys_exit", trace__sys_exit); if (sys_exit == NULL) goto out_delete_sys_enter; @@ -2370,6 +2463,34 @@ static int trace__run(struct trace *trace, int argc, const char **argv) trace__sched_stat_runtime)) goto out_error_sched_stat_runtime; + /* + * If a global cgroup was set, apply it to all the events without an + * explicit cgroup. I.e.: + * + * trace -G A -e sched:*switch + * + * Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc + * _and_ sched:sched_switch to the 'A' cgroup, while: + * + * trace -e sched:*switch -G A + * + * will only set the sched:sched_switch event to the 'A' cgroup, all the + * other events (raw_syscalls:sys_{enter,exit}, etc are left "without" + * a cgroup (on the root cgroup, sys wide, etc). + * + * Multiple cgroups: + * + * trace -G A -e sched:*switch -G B + * + * the syscall ones go to the 'A' cgroup, the sched:sched_switch goes + * to the 'B' cgroup. + * + * evlist__set_default_cgroup() grabs a reference of the passed cgroup + * only for the evsels still without a cgroup, i.e. evsel->cgroup == NULL. + */ + if (trace->cgroup) + evlist__set_default_cgroup(trace->evlist, trace->cgroup); + err = perf_evlist__create_maps(evlist, &trace->opts.target); if (err < 0) { fprintf(trace->output, "Problems parsing the target to trace, check your options!\n"); @@ -2463,7 +2584,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) * to override an explicitely set --max-stack global setting. */ evlist__for_each_entry(evlist, evsel) { - if ((evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) && + if (evsel__has_callchain(evsel) && evsel->attr.sample_max_stack == 0) evsel->attr.sample_max_stack = trace->max_stack; } @@ -2472,8 +2593,13 @@ again: for (i = 0; i < evlist->nr_mmaps; i++) { union perf_event *event; + struct perf_mmap *md; - while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + md = &evlist->mmap[i]; + if (perf_mmap__read_init(md) < 0) + continue; + + while ((event = perf_mmap__read_event(md)) != NULL) { struct perf_sample sample; ++trace->nr_events; @@ -2486,7 +2612,7 @@ again: trace__handle_event(trace, event, &sample); next_event: - perf_evlist__mmap_consume(evlist, i); + perf_mmap__consume(md); if (interrupted) goto out_disable; @@ -2496,6 +2622,7 @@ next_event: draining = true; } } + perf_mmap__read_done(md); } if (trace->nr_events == before) { @@ -2533,6 +2660,7 @@ out_delete_evlist: trace__symbols__exit(trace); perf_evlist__delete(evlist); + cgroup__put(trace->cgroup); trace->evlist = NULL; trace->live = false; return err; @@ -2634,7 +2762,7 @@ static int trace__replay(struct trace *trace) "syscalls:sys_enter"); if (evsel && - (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 || + (perf_evsel__init_raw_syscall_tp(evsel, trace__sys_enter) < 0 || perf_evsel__init_sc_tp_ptr_field(evsel, args))) { pr_err("Error during initialize raw_syscalls:sys_enter event\n"); goto out; @@ -2646,7 +2774,7 @@ static int trace__replay(struct trace *trace) evsel = perf_evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_exit"); if (evsel && - (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 || + (perf_evsel__init_raw_syscall_tp(evsel, trace__sys_exit) < 0 || perf_evsel__init_sc_tp_uint_field(evsel, ret))) { pr_err("Error during initialize raw_syscalls:sys_exit event\n"); goto out; @@ -2886,6 +3014,36 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler) evsel->handler = handler; } +static int evlist__set_syscall_tp_fields(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->priv || !evsel->tp_format) + continue; + + if (strcmp(evsel->tp_format->system, "syscalls")) + continue; + + if (perf_evsel__init_syscall_tp(evsel)) + return -1; + + if (!strncmp(evsel->tp_format->name, "sys_enter_", 10)) { + struct syscall_tp *sc = evsel->priv; + + if (__tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64))) + return -1; + } else if (!strncmp(evsel->tp_format->name, "sys_exit_", 9)) { + struct syscall_tp *sc = evsel->priv; + + if (__tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap)) + return -1; + } + } + + return 0; +} + /* * XXX: Hackish, just splitting the combined -e+--event (syscalls * (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use @@ -2955,6 +3113,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str, if (trace__validate_ev_qualifier(trace)) goto out; + trace->trace_syscalls = true; } err = 0; @@ -2972,6 +3131,18 @@ out: return err; } +static int trace__parse_cgroups(const struct option *opt, const char *str, int unset) +{ + struct trace *trace = opt->value; + + if (!list_empty(&trace->evlist->entries)) + return parse_cgroups(opt, str, unset); + + trace->cgroup = evlist__findnew_cgroup(trace->evlist, str); + + return 0; +} + int cmd_trace(int argc, const char **argv) { const char *trace_usage[] = { @@ -2998,7 +3169,7 @@ int cmd_trace(int argc, const char **argv) }, .output = stderr, .show_comm = true, - .trace_syscalls = true, + .trace_syscalls = false, .kernel_syscallchains = false, .max_stack = UINT_MAX, }; @@ -3038,6 +3209,8 @@ int cmd_trace(int argc, const char **argv) OPT_INCR('v', "verbose", &verbose, "be more verbose"), OPT_BOOLEAN('T', "time", &trace.full_time, "Show full timestamp, not time relative to first start"), + OPT_BOOLEAN(0, "failure", &trace.failure_only, + "Show only syscalls that failed"), OPT_BOOLEAN('s', "summary", &trace.summary_only, "Show only syscall summary with statistics"), OPT_BOOLEAN('S', "with-summary", &trace.summary, @@ -3062,6 +3235,8 @@ int cmd_trace(int argc, const char **argv) "print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info, for debugging"), OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout, "per thread proc mmap processing timeout in ms"), + OPT_CALLBACK('G', "cgroup", &trace, "name", "monitor event in cgroup name only", + trace__parse_cgroups), OPT_UINTEGER('D', "delay", &trace.opts.initial_delay, "ms to wait before starting measurement after program " "start"), @@ -3069,8 +3244,9 @@ int cmd_trace(int argc, const char **argv) }; bool __maybe_unused max_stack_user_set = true; bool mmap_pages_user_set = true; + struct perf_evsel *evsel; const char * const trace_subcommands[] = { "record", NULL }; - int err; + int err = -1; char bf[BUFSIZ]; signal(SIGSEGV, sighandler_dump_stack); @@ -3088,6 +3264,25 @@ int cmd_trace(int argc, const char **argv) argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands, trace_usage, PARSE_OPT_STOP_AT_NON_OPTION); + if ((nr_cgroups || trace.cgroup) && !trace.opts.target.system_wide) { + usage_with_options_msg(trace_usage, trace_options, + "cgroup monitoring only available in system-wide mode"); + } + + evsel = bpf__setup_output_event(trace.evlist, "__augmented_syscalls__"); + if (IS_ERR(evsel)) { + bpf__strerror_setup_output_event(trace.evlist, PTR_ERR(evsel), bf, sizeof(bf)); + pr_err("ERROR: Setup trace syscalls enter failed: %s\n", bf); + goto out; + } + + if (evsel) { + if (perf_evsel__init_augmented_syscall_tp(evsel) || + perf_evsel__init_augmented_syscall_tp_args(evsel)) + goto out; + trace.syscalls.events.augmented = evsel; + } + err = bpf__setup_stdout(trace.evlist); if (err) { bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf)); @@ -3106,7 +3301,7 @@ int cmd_trace(int argc, const char **argv) mmap_pages_user_set = false; if (trace.max_stack == UINT_MAX) { - trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack; + trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl__max_stack(); max_stack_user_set = false; } @@ -3123,8 +3318,13 @@ int cmd_trace(int argc, const char **argv) symbol_conf.use_callchain = true; } - if (trace.evlist->nr_entries > 0) + if (trace.evlist->nr_entries > 0) { evlist__set_evsel_handler(trace.evlist, trace__event_handler); + if (evlist__set_syscall_tp_fields(trace.evlist)) { + perror("failed to set syscalls:* tracepoint fields"); + goto out; + } + } if ((argc >= 1) && (strcmp(argv[0], "record") == 0)) return trace__record(&trace, argc-1, &argv[1]); @@ -3135,13 +3335,7 @@ int cmd_trace(int argc, const char **argv) if (!trace.trace_syscalls && !trace.trace_pgfaults && trace.evlist->nr_entries == 0 /* Was --events used? */) { - pr_err("Please specify something to trace.\n"); - return -1; - } - - if (!trace.trace_syscalls && trace.ev_qualifier) { - pr_err("The -e option can't be used with --no-syscalls.\n"); - goto out; + trace.trace_syscalls = true; } if (output_name != NULL) { @@ -3152,8 +3346,6 @@ int cmd_trace(int argc, const char **argv) } } - trace.open_id = syscalltbl__id(trace.sctbl, "open"); - err = target__validate(&trace.opts.target); if (err) { target__strerror(&trace.opts.target, err, bf, sizeof(bf)); diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index 37019c5d675f..50df168be326 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -1,11 +1,94 @@ // SPDX-License-Identifier: GPL-2.0 #include "builtin.h" #include "perf.h" +#include "color.h" #include <linux/compiler.h> +#include <tools/config.h> #include <stdio.h> +#include <string.h> +#include <subcmd/parse-options.h> -int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused) +int version_verbose; + +struct version { + bool build_options; +}; + +static struct version version; + +static struct option version_options[] = { + OPT_BOOLEAN(0, "build-options", &version.build_options, + "display the build options"), +}; + +static const char * const version_usage[] = { + "perf version [<options>]", + NULL +}; + +static void on_off_print(const char *status) +{ + printf("[ "); + + if (!strcmp(status, "OFF")) + color_fprintf(stdout, PERF_COLOR_RED, "%-3s", status); + else + color_fprintf(stdout, PERF_COLOR_GREEN, "%-3s", status); + + printf(" ]"); +} + +static void status_print(const char *name, const char *macro, + const char *status) { + printf("%22s: ", name); + on_off_print(status); + printf(" # %s\n", macro); +} + +#define STATUS(__d, __m) \ +do { \ + if (IS_BUILTIN(__d)) \ + status_print(#__m, #__d, "on"); \ + else \ + status_print(#__m, #__d, "OFF"); \ +} while (0) + +static void library_status(void) +{ + STATUS(HAVE_DWARF_SUPPORT, dwarf); + STATUS(HAVE_DWARF_GETLOCATIONS_SUPPORT, dwarf_getlocations); + STATUS(HAVE_GLIBC_SUPPORT, glibc); + STATUS(HAVE_GTK2_SUPPORT, gtk2); +#ifndef HAVE_SYSCALL_TABLE_SUPPORT + STATUS(HAVE_LIBAUDIT_SUPPORT, libaudit); +#endif + STATUS(HAVE_SYSCALL_TABLE_SUPPORT, syscall_table); + STATUS(HAVE_LIBBFD_SUPPORT, libbfd); + STATUS(HAVE_LIBELF_SUPPORT, libelf); + STATUS(HAVE_LIBNUMA_SUPPORT, libnuma); + STATUS(HAVE_LIBNUMA_SUPPORT, numa_num_possible_cpus); + STATUS(HAVE_LIBPERL_SUPPORT, libperl); + STATUS(HAVE_LIBPYTHON_SUPPORT, libpython); + STATUS(HAVE_SLANG_SUPPORT, libslang); + STATUS(HAVE_LIBCRYPTO_SUPPORT, libcrypto); + STATUS(HAVE_LIBUNWIND_SUPPORT, libunwind); + STATUS(HAVE_DWARF_SUPPORT, libdw-dwarf-unwind); + STATUS(HAVE_ZLIB_SUPPORT, zlib); + STATUS(HAVE_LZMA_SUPPORT, lzma); + STATUS(HAVE_AUXTRACE_SUPPORT, get_cpuid); + STATUS(HAVE_LIBBPF_SUPPORT, bpf); +} + +int cmd_version(int argc, const char **argv) +{ + argc = parse_options(argc, argv, version_options, version_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + printf("perf version %s\n", perf_version_string); + + if (version.build_options || version_verbose == 1) + library_status(); + return 0; } diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 790ec25919a0..466540ee8ea7 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -7,6 +7,7 @@ include/uapi/drm/i915_drm.h include/uapi/linux/fcntl.h include/uapi/linux/kcmp.h include/uapi/linux/kvm.h +include/uapi/linux/in.h include/uapi/linux/perf_event.h include/uapi/linux/prctl.h include/uapi/linux/sched.h @@ -35,6 +36,7 @@ arch/s390/include/uapi/asm/ptrace.h arch/s390/include/uapi/asm/sie.h arch/arm/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h +arch/arm64/include/uapi/asm/unistd.h arch/alpha/include/uapi/asm/errno.h arch/mips/include/asm/errno.h arch/mips/include/uapi/asm/errno.h @@ -42,6 +44,7 @@ arch/parisc/include/uapi/asm/errno.h arch/powerpc/include/uapi/asm/errno.h arch/sparc/include/uapi/asm/errno.h arch/x86/include/uapi/asm/errno.h +arch/powerpc/include/uapi/asm/unistd.h include/asm-generic/bitops/arch_hweight.h include/asm-generic/bitops/const_hweight.h include/asm-generic/bitops/__fls.h @@ -52,36 +55,53 @@ include/uapi/asm-generic/errno.h include/uapi/asm-generic/errno-base.h include/uapi/asm-generic/ioctls.h include/uapi/asm-generic/mman-common.h +include/uapi/asm-generic/unistd.h ' -check () { - file=$1 +check_2 () { + file1=$1 + file2=$2 shift - while [ -n "$*" ]; do - opts="$opts \"$1\"" - shift - done + shift - cmd="diff $opts ../$file ../../$file > /dev/null" + cmd="diff $* $file1 $file2 > /dev/null" - test -f ../../$file && - eval $cmd || echo "Warning: Kernel ABI header at 'tools/$file' differs from latest version at '$file'" >&2 + test -f $file2 && { + eval $cmd || { + echo "Warning: Kernel ABI header at '$file1' differs from latest version at '$file2'" >&2 + echo diff -u $file1 $file2 + } + } } +check () { + file=$1 + + shift + + check_2 tools/$file $file $* +} # Check if we have the kernel headers (tools/perf/../../include), else # we're probably on a detached tarball, so no point in trying to check # differences. test -d ../../include || exit 0 +cd ../.. + # simple diff check for i in $HEADERS; do check $i -B done # diff with extra ignore lines -check arch/x86/lib/memcpy_64.S -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -check arch/x86/lib/memset_64.S -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -check include/uapi/asm-generic/mman.h -I "^#include <\(uapi/\)*asm-generic/mman-common.h>" -check include/uapi/linux/mman.h -I "^#include <\(uapi/\)*asm/mman.h>" +check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' +check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' +check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"' +check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' + +# diff non-symmetric files +check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl + +cd tools/perf diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c new file mode 100644 index 000000000000..b9c203219691 --- /dev/null +++ b/tools/perf/examples/bpf/5sec.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + Description: + + . Disable strace like syscall tracing (--no-syscalls), or try tracing + just some (-e *sleep). + + . Attach a filter function to a kernel function, returning when it should + be considered, i.e. appear on the output. + + . Run it system wide, so that any sleep of >= 5 seconds and < than 6 + seconds gets caught. + + . Ask for callgraphs using DWARF info, so that userspace can be unwound + + . While this is running, run something like "sleep 5s". + + . If we decide to add tv_nsec as well, then it becomes: + + int probe(hrtimer_nanosleep, rqtp->tv_sec rqtp->tv_nsec)(void *ctx, int err, long sec, long nsec) + + I.e. add where it comes from (rqtp->tv_nsec) and where it will be + accessible in the function body (nsec) + + # perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c/call-graph=dwarf/ + 0.000 perf_bpf_probe:func:(ffffffff9811b5f0) tv_sec=5 + hrtimer_nanosleep ([kernel.kallsyms]) + __x64_sys_nanosleep ([kernel.kallsyms]) + do_syscall_64 ([kernel.kallsyms]) + entry_SYSCALL_64 ([kernel.kallsyms]) + __GI___nanosleep (/usr/lib64/libc-2.26.so) + rpl_nanosleep (/usr/bin/sleep) + xnanosleep (/usr/bin/sleep) + main (/usr/bin/sleep) + __libc_start_main (/usr/lib64/libc-2.26.so) + _start (/usr/bin/sleep) + ^C# + + Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com> +*/ + +#include <bpf.h> + +int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec) +{ + return sec == 5; +} + +license(GPL); diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c new file mode 100644 index 000000000000..69a31386d8cd --- /dev/null +++ b/tools/perf/examples/bpf/augmented_syscalls.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Augment the openat syscall with the contents of the filename pointer argument. + * + * Test it with: + * + * perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null + * + * It'll catch some openat syscalls related to the dynamic linked and + * the last one should be the one for '/etc/passwd'. + * + * This matches what is marshalled into the raw_syscall:sys_enter payload + * expected by the 'perf trace' beautifiers, and can be used by them unmodified, + * which will be done as that feature is implemented in the next csets, for now + * it will appear in a dump done by the default tracepoint handler in 'perf trace', + * that uses bpf_output__fprintf() to just dump those contents, as done with + * the bpf-output event associated with the __bpf_output__ map declared in + * tools/perf/include/bpf/stdio.h. + */ + +#include <stdio.h> + +struct bpf_map SEC("maps") __augmented_syscalls__ = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(u32), + .max_entries = __NR_CPUS__, +}; + +struct syscall_enter_openat_args { + unsigned long long common_tp_fields; + long syscall_nr; + long dfd; + char *filename_ptr; + long flags; + long mode; +}; + +struct augmented_enter_openat_args { + struct syscall_enter_openat_args args; + char filename[64]; +}; + +int syscall_enter(openat)(struct syscall_enter_openat_args *args) +{ + struct augmented_enter_openat_args augmented_args; + + probe_read(&augmented_args.args, sizeof(augmented_args.args), args); + probe_read_str(&augmented_args.filename, sizeof(augmented_args.filename), args->filename_ptr); + perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, + &augmented_args, sizeof(augmented_args)); + return 1; +} + +license(GPL); diff --git a/tools/perf/examples/bpf/empty.c b/tools/perf/examples/bpf/empty.c new file mode 100644 index 000000000000..3776d26db9e7 --- /dev/null +++ b/tools/perf/examples/bpf/empty.c @@ -0,0 +1,3 @@ +#include <bpf.h> + +license(GPL); diff --git a/tools/perf/examples/bpf/hello.c b/tools/perf/examples/bpf/hello.c new file mode 100644 index 000000000000..cf3c2fdc7f79 --- /dev/null +++ b/tools/perf/examples/bpf/hello.c @@ -0,0 +1,9 @@ +#include <stdio.h> + +int syscall_enter(openat)(void *args) +{ + puts("Hello, world\n"); + return 0; +} + +license(GPL); diff --git a/tools/perf/examples/bpf/sys_enter_openat.c b/tools/perf/examples/bpf/sys_enter_openat.c new file mode 100644 index 000000000000..9cd124b09392 --- /dev/null +++ b/tools/perf/examples/bpf/sys_enter_openat.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hook into 'openat' syscall entry tracepoint + * + * Test it with: + * + * perf trace -e tools/perf/examples/bpf/sys_enter_openat.c cat /etc/passwd > /dev/null + * + * It'll catch some openat syscalls related to the dynamic linked and + * the last one should be the one for '/etc/passwd'. + * + * The syscall_enter_openat_args can be used to get the syscall fields + * and use them for filtering calls, i.e. use in expressions for + * the return value. + */ + +#include <bpf.h> + +struct syscall_enter_openat_args { + unsigned long long unused; + long syscall_nr; + long dfd; + char *filename_ptr; + long flags; + long mode; +}; + +int syscall_enter(openat)(struct syscall_enter_openat_args *args) +{ + return 1; +} + +license(GPL); diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h new file mode 100644 index 000000000000..47897d65e799 --- /dev/null +++ b/tools/perf/include/bpf/bpf.h @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _PERF_BPF_H +#define _PERF_BPF_H + +#include <uapi/linux/bpf.h> + +/* + * A helper structure used by eBPF C program to describe map attributes to + * elf_bpf loader, taken from tools/testing/selftests/bpf/bpf_helpers.h: + */ +struct bpf_map { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; + unsigned int map_flags; + unsigned int inner_map_idx; + unsigned int numa_node; +}; + +#define SEC(NAME) __attribute__((section(NAME), used)) + +#define probe(function, vars) \ + SEC(#function "=" #function " " #vars) function + +#define syscall_enter(name) \ + SEC("syscalls:sys_enter_" #name) syscall_enter_ ## name + +#define license(name) \ +char _license[] SEC("license") = #name; \ +int _version SEC("version") = LINUX_VERSION_CODE; + +static int (*probe_read)(void *dst, int size, const void *unsafe_addr) = (void *)BPF_FUNC_probe_read; +static int (*probe_read_str)(void *dst, int size, const void *unsafe_addr) = (void *)BPF_FUNC_probe_read_str; + +#endif /* _PERF_BPF_H */ diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h new file mode 100644 index 000000000000..2899cb7bfed8 --- /dev/null +++ b/tools/perf/include/bpf/stdio.h @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <bpf.h> + +struct bpf_map SEC("maps") __bpf_stdout__ = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(u32), + .max_entries = __NR_CPUS__, +}; + +static int (*perf_event_output)(void *, struct bpf_map *, int, void *, unsigned long) = + (void *)BPF_FUNC_perf_event_output; + +#define puts(from) \ + ({ const int __len = sizeof(from); \ + char __from[__len] = from; \ + perf_event_output(args, &__bpf_stdout__, BPF_F_CURRENT_CPU, \ + &__from, __len & (sizeof(from) - 1)); }) diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index 0c6d1002b524..ac1bcdc17dae 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -35,6 +35,7 @@ #include <sys/mman.h> #include <syscall.h> /* for gettid() */ #include <err.h> +#include <linux/kernel.h> #include "jvmti_agent.h" #include "../util/jitdump.h" @@ -249,7 +250,7 @@ void *jvmti_open(void) /* * jitdump file name */ - snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); + scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666); if (fd == -1) diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h index 36673f98d66b..3eb7a39169f6 100644 --- a/tools/perf/perf-sys.h +++ b/tools/perf/perf-sys.h @@ -46,10 +46,6 @@ #define CPUINFO_PROC {"Processor"} #endif -#ifdef __metag__ -#define CPUINFO_PROC {"CPU"} -#endif - #ifdef __xtensa__ #define CPUINFO_PROC {"core ID"} #endif diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 1b3fc8ec0fa2..a11cb006f968 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -12,7 +12,6 @@ #include "util/env.h" #include <subcmd/exec-cmd.h> #include "util/config.h" -#include "util/quote.h" #include <subcmd/run-command.h> #include "util/parse-events.h" #include <subcmd/parse-options.h> @@ -73,7 +72,7 @@ static struct cmd_struct commands[] = { { "lock", cmd_lock, 0 }, { "kvm", cmd_kvm, 0 }, { "test", cmd_test, 0 }, -#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE) +#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT) { "trace", cmd_trace, 0 }, #endif { "inject", cmd_inject, 0 }, @@ -190,6 +189,12 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) break; } + if (!strcmp(cmd, "-vv")) { + (*argv)[0] = "version"; + version_verbose = 1; + break; + } + /* * Check remaining flags. */ @@ -232,7 +237,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) (*argc)--; } else if (strstarts(cmd, CMD_DEBUGFS_DIR)) { tracing_path_set(cmd + strlen(CMD_DEBUGFS_DIR)); - fprintf(stderr, "dir: %s\n", tracing_path); + fprintf(stderr, "dir: %s\n", tracing_path_mount()); if (envchanged) *envchanged = 1; } else if (!strcmp(cmd, "--list-cmds")) { @@ -415,22 +420,11 @@ void pthread__unblock_sigwinch(void) pthread_sigmask(SIG_UNBLOCK, &set, NULL); } -#ifdef _SC_LEVEL1_DCACHE_LINESIZE -#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE) -#else -static void cache_line_size(int *cacheline_sizep) -{ - if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep)) - pr_debug("cannot determine cache line size"); -} -#endif - int main(int argc, const char **argv) { int err; const char *cmd; char sbuf[STRERR_BUFSIZE]; - int value; /* libsubcmd init */ exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT); @@ -438,13 +432,6 @@ int main(int argc, const char **argv) /* The page_size is placed in util object. */ page_size = sysconf(_SC_PAGE_SIZE); - cache_line_size(&cacheline_size); - - if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0) - sysctl_perf_event_max_stack = value; - - if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0) - sysctl_perf_event_max_contexts_per_stack = value; cmd = extract_argv0_path(argv[0]); if (!cmd) @@ -452,15 +439,11 @@ int main(int argc, const char **argv) srandom(time(NULL)); - perf_config__init(); err = perf_config(perf_default_config, NULL); if (err) return err; set_buildid_dir(NULL); - /* get debugfs/tracefs mount point from /proc/mounts */ - tracing_path_mount(); - /* * "perf-xxxx" is the same as "perf xxxx", but we obviously: * @@ -485,7 +468,7 @@ int main(int argc, const char **argv) argv[0] = cmd; } if (strstarts(cmd, "trace")) { -#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE) +#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT) setup_path(); argv[0] = "trace"; return cmd_trace(argc, argv); diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 57b9b342d533..21bf7f5a3cf5 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -5,6 +5,7 @@ #include <time.h> #include <stdbool.h> #include <linux/types.h> +#include <linux/stddef.h> #include <linux/perf_event.h> extern bool test_attr__enabled; @@ -24,7 +25,9 @@ static inline unsigned long long rdclock(void) return ts.tv_sec * 1000000000ULL + ts.tv_nsec; } +#ifndef MAX_NR_CPUS #define MAX_NR_CPUS 1024 +#endif extern const char *input_name; extern bool perf_host, perf_guest; @@ -61,6 +64,7 @@ struct record_opts { bool tail_synthesize; bool overwrite; bool ignore_missing_thread; + bool strict_freq; bool sample_id; unsigned int freq; unsigned int mmap_pages; @@ -83,4 +87,7 @@ struct record_opts { struct option; extern const char * const *record_usage; extern struct option *record_options; +extern int version_verbose; + +int record__parse_freq(const struct option *opt, const char *str, int unset); #endif diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index 999a4e878162..215ba30b8534 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -1,10 +1,12 @@ hostprogs := jevents jevents-y += json.o jsmn.o jevents.o +HOSTCFLAGS_jevents.o = -I$(srctree)/tools/include pmu-events-y += pmu-events.o JDIR = pmu-events/arch/$(SRCARCH) JSON = $(shell [ -d $(JDIR) ] && \ find $(JDIR) -name '*.json' -o -name 'mapfile.csv') + # # Locate/process JSON files in pmu-events/arch/ # directory and create tables in pmu-events.c. diff --git a/tools/perf/pmu-events/README b/tools/perf/pmu-events/README index c2ee3e4417fe..e62b09b6a844 100644 --- a/tools/perf/pmu-events/README +++ b/tools/perf/pmu-events/README @@ -11,12 +11,17 @@ tree tools/perf/pmu-events/arch/foo. - Regular files with '.json' extension in the name are assumed to be JSON files, each of which describes a set of PMU events. - - Regular files with basename starting with 'mapfile.csv' are assumed - to be a CSV file that maps a specific CPU to its set of PMU events. - (see below for mapfile format) + - The CSV file that maps a specific CPU to its set of PMU events is to + be named 'mapfile.csv' (see below for mapfile format). - Directories are traversed, but all other files are ignored. + - To reduce JSON event duplication per architecture, platform JSONs may + use "ArchStdEvent" keyword to dereference an "Architecture standard + events", defined in architecture standard JSONs. + Architecture standard JSONs must be located in the architecture root + folder. Matching is based on the "EventName" field. + The PMU events supported by a CPU model are expected to grouped into topics such as Pipelining, Cache, Memory, Floating-point etc. All events for a topic should be placed in a separate JSON file - where the file name identifies @@ -29,6 +34,10 @@ sub directory. Thus for the Silvermont X86 CPU: Cache.json Memory.json Virtual-Memory.json Frontend.json Pipeline.json +The JSONs folder for a CPU model/family may be placed in the root arch +folder, or may be placed in a vendor sub-folder under the arch folder +for instances where the arch and vendor are not the same. + Using the JSON files and the mapfile, 'jevents' generates the C source file, 'pmu-events.c', which encodes the two sets of tables: diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json new file mode 100644 index 000000000000..bc03c06c3918 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json @@ -0,0 +1,32 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_RD", + }, + { + "ArchStdEvent": "L1D_CACHE_WR", + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD", + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR", + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD", + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR", + }, + { + "ArchStdEvent": "L1D_TLB_RD", + }, + { + "ArchStdEvent": "L1D_TLB_WR", + }, + { + "ArchStdEvent": "BUS_ACCESS_RD", + }, + { + "ArchStdEvent": "BUS_ACCESS_WR", + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/branch.json index 3b6208763e50..0b0e6b26605b 100644 --- a/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/branch.json @@ -1,25 +1,23 @@ [ - {, - "EventCode": "0x7A", - "EventName": "BR_INDIRECT_SPEC", - "BriefDescription": "Branch speculatively executed - Indirect branch" + { + "ArchStdEvent": "BR_INDIRECT_SPEC", }, - {, + { "EventCode": "0xC9", "EventName": "BR_COND", "BriefDescription": "Conditional branch executed" }, - {, + { "EventCode": "0xCA", "EventName": "BR_INDIRECT_MISPRED", "BriefDescription": "Indirect branch mispredicted" }, - {, + { "EventCode": "0xCB", "EventName": "BR_INDIRECT_MISPRED_ADDR", "BriefDescription": "Indirect branch mispredicted because of address miscompare" }, - {, + { "EventCode": "0xCC", "EventName": "BR_COND_MISPRED", "BriefDescription": "Conditional branch mispredicted" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/bus.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/bus.json new file mode 100644 index 000000000000..ce33b2553277 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/bus.json @@ -0,0 +1,8 @@ +[ + { + "ArchStdEvent": "BUS_ACCESS_RD", + }, + { + "ArchStdEvent": "BUS_ACCESS_WR", + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/cache.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/cache.json new file mode 100644 index 000000000000..5dfbec43c9f9 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/cache.json @@ -0,0 +1,27 @@ +[ + { + "EventCode": "0xC2", + "EventName": "PREFETCH_LINEFILL", + "BriefDescription": "Linefill because of prefetch" + }, + { + "EventCode": "0xC3", + "EventName": "PREFETCH_LINEFILL_DROP", + "BriefDescription": "Instruction Cache Throttle occurred" + }, + { + "EventCode": "0xC4", + "EventName": "READ_ALLOC_ENTER", + "BriefDescription": "Entering read allocate mode" + }, + { + "EventCode": "0xC5", + "EventName": "READ_ALLOC", + "BriefDescription": "Read allocate mode" + }, + { + "EventCode": "0xC8", + "EventName": "EXT_SNOOP", + "BriefDescription": "SCU Snooped data from another CPU for this CPU" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/memory.json index 480d9f7460ab..25ae642ba381 100644 --- a/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/memory.json @@ -1,20 +1,10 @@ [ - {, - "EventCode": "0x60", - "EventName": "BUS_ACCESS_LD", - "BriefDescription": "Bus access - Read" - }, - {, - "EventCode": "0x61", - "EventName": "BUS_ACCESS_ST", - "BriefDescription": "Bus access - Write" - }, - {, + { "EventCode": "0xC0", "EventName": "EXT_MEM_REQ", "BriefDescription": "External memory request" }, - {, + { "EventCode": "0xC1", "EventName": "EXT_MEM_REQ_NC", "BriefDescription": "Non-cacheable external memory request" diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/other.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/other.json new file mode 100644 index 000000000000..6cc6cbd7bf0b --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/other.json @@ -0,0 +1,28 @@ +[ + { + "ArchStdEvent": "EXC_IRQ", + }, + { + "ArchStdEvent": "EXC_FIQ", + }, + { + "EventCode": "0xC6", + "EventName": "PRE_DECODE_ERR", + "BriefDescription": "Pre-decode error" + }, + { + "EventCode": "0xD0", + "EventName": "L1I_CACHE_ERR", + "BriefDescription": "L1 Instruction Cache (data or tag) memory error" + }, + { + "EventCode": "0xD1", + "EventName": "L1D_CACHE_ERR", + "BriefDescription": "L1 Data Cache (data, tag or dirty) memory error, correctable or non-correctable" + }, + { + "EventCode": "0xD2", + "EventName": "TLB_ERR", + "BriefDescription": "TLB memory error" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/pipeline.json index 3149fb90555a..f45a6b5d0025 100644 --- a/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json +++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/pipeline.json @@ -1,50 +1,50 @@ [ - {, + { "EventCode": "0xC7", "EventName": "STALL_SB_FULL", "BriefDescription": "Data Write operation that stalls the pipeline because the store buffer is full" }, - {, + { "EventCode": "0xE0", "EventName": "OTHER_IQ_DEP_STALL", "BriefDescription": "Cycles that the DPU IQ is empty and that is not because of a recent micro-TLB miss, instruction cache miss or pre-decode error" }, - {, + { "EventCode": "0xE1", "EventName": "IC_DEP_STALL", "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction cache miss being processed" }, - {, + { "EventCode": "0xE2", "EventName": "IUTLB_DEP_STALL", "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction micro-TLB miss being processed" }, - {, + { "EventCode": "0xE3", "EventName": "DECODE_DEP_STALL", "BriefDescription": "Cycles the DPU IQ is empty and there is a pre-decode error being processed" }, - {, + { "EventCode": "0xE4", "EventName": "OTHER_INTERLOCK_STALL", "BriefDescription": "Cycles there is an interlock other than Advanced SIMD/Floating-point instructions or load/store instruction" }, - {, + { "EventCode": "0xE5", "EventName": "AGU_DEP_STALL", "BriefDescription": "Cycles there is an interlock for a load/store instruction waiting for data to calculate the address in the AGU" }, - {, + { "EventCode": "0xE6", "EventName": "SIMD_DEP_STALL", "BriefDescription": "Cycles there is an interlock for an Advanced SIMD/Floating-point operation." }, - {, + { "EventCode": "0xE7", "EventName": "LD_DEP_STALL", "BriefDescription": "Cycles there is a stall in the Wr stage because of a load miss" }, - {, + { "EventCode": "0xE8", "EventName": "ST_DEP_STALL", "BriefDescription": "Cycles there is a stall in the Wr stage because of a store" diff --git a/tools/perf/pmu-events/arch/arm64/armv8-recommended.json b/tools/perf/pmu-events/arch/arm64/armv8-recommended.json new file mode 100644 index 000000000000..6328828c018c --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/armv8-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/arm64/cavium/thunderx2-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2-imp-def.json deleted file mode 100644 index 2db45c40ebc7..000000000000 --- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2-imp-def.json +++ /dev/null @@ -1,62 +0,0 @@ -[ - { - "PublicDescription": "Attributable Level 1 data cache access, read", - "EventCode": "0x40", - "EventName": "l1d_cache_rd", - "BriefDescription": "L1D cache read", - }, - { - "PublicDescription": "Attributable Level 1 data cache access, write ", - "EventCode": "0x41", - "EventName": "l1d_cache_wr", - "BriefDescription": "L1D cache 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 refill write", - }, - { - "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 read", - }, - { - "PublicDescription": "Attributable Level 1 data or unified TLB access, write", - "EventCode": "0x4F", - "EventName": "l1d_tlb_wr", - "BriefDescription": "L1D tlb 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", - } -] diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json new file mode 100644 index 000000000000..752e47eb6977 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json @@ -0,0 +1,113 @@ +[ + { + "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_TLB_REFILL_RD", + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR", + }, + { + "ArchStdEvent": "L2D_TLB_RD", + }, + { + "ArchStdEvent": "L2D_TLB_WR", + }, + { + "ArchStdEvent": "BUS_ACCESS_RD", + }, + { + "ArchStdEvent": "BUS_ACCESS_WR", + }, + { + "ArchStdEvent": "MEM_ACCESS_RD", + }, + { + "ArchStdEvent": "MEM_ACCESS_WR", + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC", + }, + { + "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/cortex-a53/bus.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json deleted file mode 100644 index 480d9f7460ab..000000000000 --- a/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json +++ /dev/null @@ -1,22 +0,0 @@ -[ - {, - "EventCode": "0x60", - "EventName": "BUS_ACCESS_LD", - "BriefDescription": "Bus access - Read" - }, - {, - "EventCode": "0x61", - "EventName": "BUS_ACCESS_ST", - "BriefDescription": "Bus access - Write" - }, - {, - "EventCode": "0xC0", - "EventName": "EXT_MEM_REQ", - "BriefDescription": "External memory request" - }, - {, - "EventCode": "0xC1", - "EventName": "EXT_MEM_REQ_NC", - "BriefDescription": "Non-cacheable external memory request" - } -] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json deleted file mode 100644 index 11baad6344b9..000000000000 --- a/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json +++ /dev/null @@ -1,27 +0,0 @@ -[ - {, - "EventCode": "0xC2", - "EventName": "PREFETCH_LINEFILL", - "BriefDescription": "Linefill because of prefetch" - }, - {, - "EventCode": "0xC3", - "EventName": "PREFETCH_LINEFILL_DROP", - "BriefDescription": "Instruction Cache Throttle occurred" - }, - {, - "EventCode": "0xC4", - "EventName": "READ_ALLOC_ENTER", - "BriefDescription": "Entering read allocate mode" - }, - {, - "EventCode": "0xC5", - "EventName": "READ_ALLOC", - "BriefDescription": "Read allocate mode" - }, - {, - "EventCode": "0xC8", - "EventName": "EXT_SNOOP", - "BriefDescription": "SCU Snooped data from another CPU for this CPU" - } -] diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json deleted file mode 100644 index 73a22402d003..000000000000 --- a/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json +++ /dev/null @@ -1,32 +0,0 @@ -[ - {, - "EventCode": "0x86", - "EventName": "EXC_IRQ", - "BriefDescription": "Exception taken, IRQ" - }, - {, - "EventCode": "0x87", - "EventName": "EXC_FIQ", - "BriefDescription": "Exception taken, FIQ" - }, - {, - "EventCode": "0xC6", - "EventName": "PRE_DECODE_ERR", - "BriefDescription": "Pre-decode error" - }, - {, - "EventCode": "0xD0", - "EventName": "L1I_CACHE_ERR", - "BriefDescription": "L1 Instruction Cache (data or tag) memory error" - }, - {, - "EventCode": "0xD1", - "EventName": "L1D_CACHE_ERR", - "BriefDescription": "L1 Data Cache (data, tag or dirty) memory error, correctable or non-correctable" - }, - {, - "EventCode": "0xD2", - "EventName": "TLB_ERR", - "BriefDescription": "TLB memory error" - } -] diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/core-imp-def.json new file mode 100644 index 000000000000..9f0f15d15f75 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/core-imp-def.json @@ -0,0 +1,122 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_RD", + }, + { + "ArchStdEvent": "L1D_CACHE_WR", + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD", + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR", + }, + { + "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", + }, + { + "PublicDescription": "Level 1 instruction cache prefetch access count", + "EventCode": "0x102e", + "EventName": "L1I_CACHE_PRF", + "BriefDescription": "L1I cache prefetch access count", + }, + { + "PublicDescription": "Level 1 instruction cache miss due to prefetch access count", + "EventCode": "0x102f", + "EventName": "L1I_CACHE_PRF_REFILL", + "BriefDescription": "L1I cache miss due to prefetch access count", + }, + { + "PublicDescription": "Instruction queue is empty", + "EventCode": "0x1043", + "EventName": "IQ_IS_EMPTY", + "BriefDescription": "Instruction queue is empty", + }, + { + "PublicDescription": "Instruction fetch stall cycles", + "EventCode": "0x1044", + "EventName": "IF_IS_STALL", + "BriefDescription": "Instruction fetch stall cycles", + }, + { + "PublicDescription": "Instructions can receive, but not send", + "EventCode": "0x2014", + "EventName": "FETCH_BUBBLE", + "BriefDescription": "Instructions can receive, but not send", + }, + { + "PublicDescription": "Prefetch request from LSU", + "EventCode": "0x6013", + "EventName": "PRF_REQ", + "BriefDescription": "Prefetch request from LSU", + }, + { + "PublicDescription": "Hit on prefetched data", + "EventCode": "0x6014", + "EventName": "HIT_ON_PRF", + "BriefDescription": "Hit on prefetched data", + }, + { + "PublicDescription": "Cycles of that the number of issuing micro operations are less than 4", + "EventCode": "0x7001", + "EventName": "EXE_STALL_CYCLE", + "BriefDescription": "Cycles of that the number of issue ups are less than 4", + }, + { + "PublicDescription": "No any micro operation is issued and meanwhile any load operation is not resolved", + "EventCode": "0x7004", + "EventName": "MEM_STALL_ANYLOAD", + "BriefDescription": "No any micro operation is issued and meanwhile any load operation is not resolved", + }, + { + "PublicDescription": "No any micro operation is issued and meanwhile there is any load operation missing L1 cache and pending data refill", + "EventCode": "0x7006", + "EventName": "MEM_STALL_L1MISS", + "BriefDescription": "No any micro operation is issued and meanwhile there is any load operation missing L1 cache and pending data refill", + }, + { + "PublicDescription": "No any micro operation is issued and meanwhile there is any load operation missing both L1 and L2 cache and pending data refill from L3 cache", + "EventCode": "0x7007", + "EventName": "MEM_STALL_L2MISS", + "BriefDescription": "No any micro operation is issued and meanwhile there is any load operation missing both L1 and L2 cache and pending data refill from L3 cache", + }, +] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index e61c9ca6cf9e..59cd8604b0bd 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -12,5 +12,8 @@ # # #Family-model,Version,Filename,EventType -0x00000000420f5160,v1,cavium,core -0x00000000410fd03[[:xdigit:]],v1,cortex-a53,core +0x00000000410fd03[[:xdigit:]],v1,arm/cortex-a53,core +0x00000000420f5160,v1,cavium/thunderx2,core +0x00000000430f0af0,v1,cavium/thunderx2,core +0x00000000480fd010,v1,hisilicon/hip08,core +0x00000000500f0000,v1,ampere/emag,core diff --git a/tools/perf/pmu-events/arch/powerpc/power9/cache.json b/tools/perf/pmu-events/arch/powerpc/power9/cache.json index 7945c5196c43..851072105054 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/cache.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/cache.json @@ -20,11 +20,6 @@ "BriefDescription": "Finish stall due to a scalar fixed point or CR instruction in the execution pipeline. These instructions get routed to the ALU, ALU2, and DIV pipes" }, {, - "EventCode": "0x1D15C", - "EventName": "PM_MRK_DTLB_MISS_1G", - "BriefDescription": "Marked Data TLB reload (after a miss) page size 2M. Implies radix translation was used" - }, - {, "EventCode": "0x4D12A", "EventName": "PM_MRK_DATA_FROM_RL4_CYC", "BriefDescription": "Duration in cycles to reload from another chip's L4 on the same Node or Group ( Remote) due to a marked load" @@ -80,21 +75,6 @@ "BriefDescription": "Threshold counter exceed a count of 4096" }, {, - "EventCode": "0x3D156", - "EventName": "PM_MRK_DTLB_MISS_64K", - "BriefDescription": "Marked Data TLB Miss page size 64K" - }, - {, - "EventCode": "0x4C15E", - "EventName": "PM_MRK_DTLB_MISS_16M", - "BriefDescription": "Marked Data TLB Miss page size 16M" - }, - {, - "EventCode": "0x2D15E", - "EventName": "PM_MRK_DTLB_MISS_16G", - "BriefDescription": "Marked Data TLB Miss page size 16G" - }, - {, "EventCode": "0x3F14A", "EventName": "PM_MRK_DPTEG_FROM_RMEM", "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" @@ -123,10 +103,5 @@ "EventCode": "0x1002A", "EventName": "PM_CMPLU_STALL_LARX", "BriefDescription": "Finish stall because the NTF instruction was a larx waiting to be satisfied" - }, - {, - "EventCode": "0x1C058", - "EventName": "PM_DTLB_MISS_16G", - "BriefDescription": "Data TLB Miss page size 16G" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json index bd8361b5fd6a..f9fa84b16fb5 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json @@ -155,11 +155,6 @@ "BriefDescription": "Duration in cycles to reload with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load" }, {, - "EventCode": "0x3C056", - "EventName": "PM_DTLB_MISS_64K", - "BriefDescription": "Data TLB Miss page size 64K" - }, - {, "EventCode": "0x30060", "EventName": "PM_TM_TRANS_RUN_INST", "BriefDescription": "Run instructions completed in transactional state (gated by the run latch)" @@ -345,11 +340,6 @@ "BriefDescription": "Larx finished" }, {, - "EventCode": "0x4C056", - "EventName": "PM_DTLB_MISS_16M", - "BriefDescription": "Data TLB Miss page size 16M" - }, - {, "EventCode": "0x1003A", "EventName": "PM_CMPLU_STALL_LSU_FIN", "BriefDescription": "Finish stall because the NTF instruction was an LSU op (other than a load or a store) with all its dependencies met and just going through the LSU pipe to finish" diff --git a/tools/perf/pmu-events/arch/powerpc/power9/marked.json b/tools/perf/pmu-events/arch/powerpc/power9/marked.json index 22f9f32060a8..b1954c38bab1 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/marked.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/marked.json @@ -530,11 +530,6 @@ "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch" }, {, - "EventCode": "0x4003C", - "EventName": "PM_DISP_HELD_SYNC_HOLD", - "BriefDescription": "Cycles in which dispatch is held because of a synchronizing instruction in the pipeline" - }, - {, "EventCode": "0x3003C", "EventName": "PM_CMPLU_STALL_NESTED_TEND", "BriefDescription": "Completion stall because the ISU is updating the TEXASR to keep track of the nested tend and decrement the TEXASR nested level. This is a short delay" diff --git a/tools/perf/pmu-events/arch/powerpc/power9/memory.json b/tools/perf/pmu-events/arch/powerpc/power9/memory.json index 9960d1c0dd44..2e2ebc700c74 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/memory.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/memory.json @@ -45,11 +45,6 @@ "BriefDescription": "count of Loads completed" }, {, - "EventCode": "0x2D156", - "EventName": "PM_MRK_DTLB_MISS_4K", - "BriefDescription": "Marked Data TLB Miss page size 4k" - }, - {, "EventCode": "0x4C042", "EventName": "PM_DATA_FROM_L3", "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a demand load" diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json index 5ce312973f1e..48cf4f920b3f 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/other.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json @@ -70,6 +70,11 @@ "BriefDescription": "Cycles thread running at priority level 0 or 1" }, {, + "EventCode": "0x4C054", + "EventName": "PM_DERAT_MISS_16G_1G", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16G (hpt mode) or 1G (radix mode)" + }, + {, "EventCode": "0x2084", "EventName": "PM_FLUSH_HB_RESTORE_CYC", "BriefDescription": "Cycles in which no new instructions can be dispatched to the ICT after a flush. History buffer recovery" @@ -107,12 +112,12 @@ {, "EventCode": "0x360B2", "EventName": "PM_L3_GRP_GUESS_WRONG_LOW", - "BriefDescription": "Initial scope=group (GS or NNS) but data from outside group (far or rem). Prediction too Low" + "BriefDescription": "Prefetch scope predictor selected GS or NNS, but was wrong because scope was LNS" }, {, "EventCode": "0x168A6", "EventName": "PM_TM_CAM_OVERFLOW", - "BriefDescription": "L3 TM cam overflow during L2 co of SC" + "BriefDescription": "L3 TM CAM is full when a L2 castout of TM_SC line occurs. Line is pushed to memory" }, {, "EventCode": "0xE8B0", @@ -150,11 +155,6 @@ "BriefDescription": "All ISU rejects" }, {, - "EventCode": "0x460A6", - "EventName": "PM_RD_FORMING_SC", - "BriefDescription": "Read forming SC" - }, - {, "EventCode": "0x468A0", "EventName": "PM_L3_PF_OFF_CHIP_MEM", "BriefDescription": "L3 PF from Off chip memory" @@ -187,7 +187,7 @@ {, "EventCode": "0x368A6", "EventName": "PM_SNP_TM_HIT_T", - "BriefDescription": "Snp TM sthit T/Tn/Te" + "BriefDescription": "TM snoop that is a store hits line in L3 in T, Tn or Te state (shared modified)" }, {, "EventCode": "0x3001A", @@ -205,6 +205,11 @@ "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's ECO L3 on the same chip due to a marked load" }, {, + "EventCode": "0xF0B4", + "EventName": "PM_DC_PREF_CONS_ALLOC", + "BriefDescription": "Prefetch stream allocated in the conservative phase by either the hardware prefetch mechanism or software prefetch. The sum of this pair subtracted from the total number of allocs will give the total allocs in normal phase" + }, + {, "EventCode": "0xF894", "EventName": "PM_LSU3_L1_CAM_CANCEL", "BriefDescription": "ls3 l1 tm cam cancel" @@ -227,7 +232,12 @@ {, "EventCode": "0x468A6", "EventName": "PM_RD_CLEARING_SC", - "BriefDescription": "Read clearing SC" + "BriefDescription": "Core TM load hits line in L3 in TM_SC state and causes it to be invalidated" + }, + {, + "EventCode": "0xD0B0", + "EventName": "PM_HWSYNC", + "BriefDescription": "" }, {, "EventCode": "0x168B0", @@ -265,6 +275,11 @@ "BriefDescription": "Prefetch stream allocated by the hardware prefetch mechanism" }, {, + "EventCode": "0xF0BC", + "EventName": "PM_LS2_UNALIGNED_ST", + "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size. If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, "EventCode": "0xD0AC", "EventName": "PM_SRQ_SYNC_CYC", "BriefDescription": "A sync is in the S2Q (edge detect to count)" @@ -275,6 +290,11 @@ "BriefDescription": "Marked instruction was reloaded from a location beyond the local chiplet" }, {, + "EventCode": "0x58A8", + "EventName": "PM_DECODE_HOLD_ICT_FULL", + "BriefDescription": "Counts the number of cycles in which the IFU was not able to decode and transmit one or more instructions because all itags were in use. This means the ICT is full for this thread" + }, + {, "EventCode": "0x26082", "EventName": "PM_L2_IC_INV", "BriefDescription": "I-cache Invalidates sent over the realod bus to the core" @@ -365,6 +385,16 @@ "BriefDescription": "Duration in cycles to reload either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked load" }, {, + "EventCode": "0xF888", + "EventName": "PM_LSU1_STORE_REJECT", + "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met" + }, + {, + "EventCode": "0xC098", + "EventName": "PM_LS2_UNALIGNED_LD", + "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size. If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, "EventCode": "0x20058", "EventName": "PM_DARQ1_10_12_ENTRIES", "BriefDescription": "Cycles in which 10 or more DARQ1 entries (out of 12) are in use" @@ -372,7 +402,7 @@ {, "EventCode": "0x360A6", "EventName": "PM_SNP_TM_HIT_M", - "BriefDescription": "Snp TM st hit M/Mu" + "BriefDescription": "TM snoop that is a store hits line in L3 in M or Mu state (exclusive modified)" }, {, "EventCode": "0x5898", @@ -395,9 +425,9 @@ "BriefDescription": "A data line was written to the L1 due to a hardware or software prefetch" }, {, - "EventCode": "0xF888", - "EventName": "PM_LSU1_STORE_REJECT", - "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met" + "EventCode": "0x2608E", + "EventName": "PM_TM_LD_CONF", + "BriefDescription": "TM Load (fav or non-fav) ran into conflict (failed)" }, {, "EventCode": "0x1D144", @@ -422,7 +452,7 @@ {, "EventCode": "0x26884", "EventName": "PM_DSIDE_MRU_TOUCH", - "BriefDescription": "D-side L2 MRU touch sent to L2" + "BriefDescription": "D-side L2 MRU touch commands sent to the L2" }, {, "EventCode": "0x30134", @@ -440,6 +470,16 @@ "BriefDescription": "XL-form branch was mispredicted due to the predicted target address missing from EAT. The EAT forces a mispredict in this case since there is no predicated target to validate. This is a rare case that may occur when the EAT is full and a branch is issued" }, {, + "EventCode": "0xC094", + "EventName": "PM_LS0_UNALIGNED_LD", + "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size. If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, + "EventCode": "0xF8BC", + "EventName": "PM_LS3_UNALIGNED_ST", + "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size. If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, "EventCode": "0x460AE", "EventName": "PM_L3_P2_CO_RTY", "BriefDescription": "L3 CO received retry port 2 (memory only), every retry counted" @@ -492,7 +532,7 @@ {, "EventCode": "0xC880", "EventName": "PM_LS1_LD_VECTOR_FIN", - "BriefDescription": "" + "BriefDescription": "LS1 finished load vector op" }, {, "EventCode": "0x2894", @@ -515,6 +555,11 @@ "BriefDescription": "Marked derat reload (miss) for any page size" }, {, + "EventCode": "0x160A0", + "EventName": "PM_L3_PF_MISS_L3", + "BriefDescription": "L3 PF missed in L3" + }, + {, "EventCode": "0x1C04A", "EventName": "PM_DATA_FROM_RL2L3_SHR", "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load" @@ -565,11 +610,21 @@ "BriefDescription": "L2 guess local (LNS) and guess was not correct (ie data not on chip)" }, {, + "EventCode": "0xC888", + "EventName": "PM_LSU_DTLB_MISS_64K", + "BriefDescription": "Data TLB Miss page size 64K" + }, + {, "EventCode": "0xE0A4", "EventName": "PM_TMA_REQ_L2", "BriefDescription": "addrs only req to L2 only on the first one,Indication that Load footprint is not expanding" }, {, + "EventCode": "0xC088", + "EventName": "PM_LSU_DTLB_MISS_4K", + "BriefDescription": "Data TLB Miss page size 4K" + }, + {, "EventCode": "0x3C042", "EventName": "PM_DATA_FROM_L3_DISP_CONFLICT", "BriefDescription": "The processor's data cache was reloaded from local core's L3 with dispatch conflict due to a demand load" @@ -602,7 +657,7 @@ {, "EventCode": "0x26084", "EventName": "PM_L2_RCLD_DISP_FAIL_OTHER", - "BriefDescription": "All I-or-D side load dispatch attempts for this thread that failed due to reason other than address collision (excludes i_l2mru_tch_reqs)" + "BriefDescription": "All D-side-Ld or I-side-instruction-fetch dispatch attempts for this thread that failed due to reasons other than an address collision conflicts with an L2 machines (e.g. Read-Claim/Snoop machine not available)" }, {, "EventCode": "0x101E4", @@ -647,12 +702,12 @@ {, "EventCode": "0x46080", "EventName": "PM_L2_DISP_ALL_L2MISS", - "BriefDescription": "All successful Ld/St dispatches for this thread that were an L2 miss (excludes i_l2mru_tch_reqs)" + "BriefDescription": "All successful D-side-Ld/St or I-side-instruction-fetch dispatches for this thread that were an L2 miss" }, {, - "EventCode": "0x160A0", - "EventName": "PM_L3_PF_MISS_L3", - "BriefDescription": "L3 PF missed in L3" + "EventCode": "0xF8B8", + "EventName": "PM_LS1_UNALIGNED_ST", + "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size. If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" }, {, "EventCode": "0x408C", @@ -667,7 +722,7 @@ {, "EventCode": "0x160B2", "EventName": "PM_L3_LOC_GUESS_CORRECT", - "BriefDescription": "initial scope=node/chip (LNS) and data from local node (local) (pred successful) - always PFs only" + "BriefDescription": "Prefetch scope predictor selected LNS and was correct" }, {, "EventCode": "0x48B4", @@ -767,7 +822,7 @@ {, "EventCode": "0x36082", "EventName": "PM_L2_LD_DISP", - "BriefDescription": "All successful I-or-D side load dispatches for this thread (excludes i_l2mru_tch_reqs)" + "BriefDescription": "All successful D-side-Ld or I-side-instruction-fetch dispatches for this thread" }, {, "EventCode": "0xF8B0", @@ -787,7 +842,7 @@ {, "EventCode": "0x16884", "EventName": "PM_L2_RCLD_DISP_FAIL_ADDR", - "BriefDescription": "All I-od-D side load dispatch attempts for this thread that failed due to address collision with RC/CO/SN/SQ machine (excludes i_l2mru_tch_reqs)" + "BriefDescription": "All D-side-Ld or I-side-instruction-fetch dispatch attempts for this thread that failed due to an address collision conflicts with an L2 machines already working on this line (e.g. ld-hit-stq or Read-claim/Castout/Snoop machines)" }, {, "EventCode": "0x460A0", @@ -830,6 +885,11 @@ "BriefDescription": "Instruction prefetch requests" }, {, + "EventCode": "0xC898", + "EventName": "PM_LS3_UNALIGNED_LD", + "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size. If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, "EventCode": "0x488C", "EventName": "PM_IC_PREF_WRITE", "BriefDescription": "Instruction prefetch written into IL1" @@ -837,7 +897,7 @@ {, "EventCode": "0xF89C", "EventName": "PM_XLATE_MISS", - "BriefDescription": "The LSU requested a line from L2 for translation. It may be satisfied from any source beyond L2. Includes speculative instructions" + "BriefDescription": "The LSU requested a line from L2 for translation. It may be satisfied from any source beyond L2. Includes speculative instructions. Includes instruction, prefetch and demand" }, {, "EventCode": "0x14158", @@ -850,9 +910,14 @@ "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L3 on the same chip due to a marked load" }, {, + "EventCode": "0xC88C", + "EventName": "PM_LSU_DTLB_MISS_16G_1G", + "BriefDescription": "Data TLB Miss page size 16G (HPT) or 1G (Radix)" + }, + {, "EventCode": "0x268A6", "EventName": "PM_TM_RST_SC", - "BriefDescription": "TM-snp rst RM SC" + "BriefDescription": "TM snoop hits line in L3 that is TM_SC state and causes it to be invalidated" }, {, "EventCode": "0x468A4", @@ -917,7 +982,7 @@ {, "EventCode": "0x46086", "EventName": "PM_L2_SN_M_RD_DONE", - "BriefDescription": "SNP dispatched for a read and was M (true M)" + "BriefDescription": "Snoop dispatched for a read and was M (true M)" }, {, "EventCode": "0x40154", @@ -980,14 +1045,9 @@ "BriefDescription": "Link stack predicts right address" }, {, - "EventCode": "0x4C05A", - "EventName": "PM_DTLB_MISS_1G", - "BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used" - }, - {, "EventCode": "0x36886", "EventName": "PM_L2_SN_SX_I_DONE", - "BriefDescription": "SNP dispatched and went from Sx to Ix" + "BriefDescription": "Snoop dispatched and went from Sx to Ix" }, {, "EventCode": "0x4E04A", @@ -1000,11 +1060,6 @@ "BriefDescription": "Duration in cycles to reload from another chip's L4 on a different Node or Group (Distant) due to a marked load" }, {, - "EventCode": "0x2608E", - "EventName": "PM_TM_LD_CONF", - "BriefDescription": "TM Load (fav or non-fav) ran into conflict (failed)" - }, - {, "EventCode": "0x4080", "EventName": "PM_INST_FROM_L1", "BriefDescription": "Instruction fetches from L1. L1 instruction hit" @@ -1037,7 +1092,7 @@ {, "EventCode": "0x260A6", "EventName": "PM_NON_TM_RST_SC", - "BriefDescription": "Non-TM snp rst TM SC" + "BriefDescription": "Non-TM snoop hits line in L3 that is TM_SC state and causes it to be invalidated" }, {, "EventCode": "0x3608A", @@ -1065,11 +1120,6 @@ "BriefDescription": "Branch mispredict flushes. Includes target and address misprecition" }, {, - "EventCode": "0x508C", - "EventName": "PM_SHL_CREATED", - "BriefDescription": "Store-Hit-Load Table Entry Created" - }, - {, "EventCode": "0x1504C", "EventName": "PM_IPTEG_FROM_LL4", "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a instruction side request" @@ -1107,7 +1157,7 @@ {, "EventCode": "0x2608A", "EventName": "PM_ISIDE_DISP_FAIL_ADDR", - "BriefDescription": "All I-side dispatch attempts for this thread that failed due to a addr collision with another machine (excludes i_l2mru_tch_reqs)" + "BriefDescription": "All I-side-instruction-fetch dispatch attempts for this thread that failed due to an address collision conflict with an L2 machine already working on this line (e.g. ld-hit-stq or RC/CO/SN machines)" }, {, "EventCode": "0x50B4", @@ -1180,9 +1230,9 @@ "BriefDescription": "Number of stcx instructions finished. This includes instructions in the speculative path of a branch that may be flushed" }, {, - "EventCode": "0xE0B8", - "EventName": "PM_LS2_TM_DISALLOW", - "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it" + "EventCode": "0xD8AC", + "EventName": "PM_LWSYNC", + "BriefDescription": "" }, {, "EventCode": "0x2094", @@ -1210,6 +1260,11 @@ "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF; CR; XVF (XER/VSCR/FPSCR)" }, {, + "EventCode": "0xC894", + "EventName": "PM_LS1_UNALIGNED_LD", + "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size. If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, "EventCode": "0x360A2", "EventName": "PM_L3_L2_CO_HIT", "BriefDescription": "L2 CO hits" @@ -1292,7 +1347,7 @@ {, "EventCode": "0xC084", "EventName": "PM_LS2_LD_VECTOR_FIN", - "BriefDescription": "" + "BriefDescription": "LS2 finished load vector op" }, {, "EventCode": "0x1608E", @@ -1345,6 +1400,11 @@ "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each SN machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running" }, {, + "EventCode": "0x36084", + "EventName": "PM_L2_RCST_DISP", + "BriefDescription": "All D-side store dispatch attempts for this thread" + }, + {, "EventCode": "0x46084", "EventName": "PM_L2_RCST_DISP_FAIL_OTHER", "BriefDescription": "All D-side store dispatch attempts for this thread that failed due to reason other than address collision" @@ -1355,11 +1415,6 @@ "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software." }, {, - "EventCode": "0x36084", - "EventName": "PM_L2_RCST_DISP", - "BriefDescription": "All D-side store dispatch attempts for this thread" - }, - {, "EventCode": "0x45054", "EventName": "PM_FMA_CMPL", "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only. " @@ -1372,7 +1427,7 @@ {, "EventCode": "0x36080", "EventName": "PM_L2_INST", - "BriefDescription": "All successful I-side dispatches for this thread (excludes i_l2mru_tch reqs)" + "BriefDescription": "All successful I-side-instruction-fetch (e.g. i-demand, i-prefetch) dispatches for this thread" }, {, "EventCode": "0x3504C", @@ -1387,7 +1442,7 @@ {, "EventCode": "0x1688A", "EventName": "PM_ISIDE_DISP", - "BriefDescription": "All I-side dispatch attempts for this thread (excludes i_l2mru_tch_reqs)" + "BriefDescription": "All I-side-instruction-fetch dispatch attempts for this thread" }, {, "EventCode": "0x468AA", @@ -1420,6 +1475,11 @@ "BriefDescription": "Load tm hit in L1" }, {, + "EventCode": "0xE0B8", + "EventName": "PM_LS2_TM_DISALLOW", + "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it" + }, + {, "EventCode": "0x44044", "EventName": "PM_INST_FROM_L31_ECO_MOD", "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to an instruction fetch (not prefetch)" @@ -1467,7 +1527,7 @@ {, "EventCode": "0x36086", "EventName": "PM_L2_RC_ST_DONE", - "BriefDescription": "RC did store to line that was Tx or Sx" + "BriefDescription": "Read-claim machine did store to line that was in Tx or Sx (Tagged or Shared state)" }, {, "EventCode": "0xE8AC", @@ -1500,6 +1560,11 @@ "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a instruction side request" }, {, + "EventCode": "0x460A6", + "EventName": "PM_RD_FORMING_SC", + "BriefDescription": "Doesn't occur" + }, + {, "EventCode": "0x35042", "EventName": "PM_IPTEG_FROM_L3_DISP_CONFLICT", "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a instruction side request" @@ -1527,7 +1592,7 @@ {, "EventCode": "0x36882", "EventName": "PM_L2_LD_HIT", - "BriefDescription": "All successful I-or-D side load dispatches for this thread that were L2 hits (excludes i_l2mru_tch_reqs)" + "BriefDescription": "All successful D-side-Ld or I-side-instruction-fetch dispatches for this thread that were L2 hits" }, {, "EventCode": "0x168AC", @@ -1555,11 +1620,6 @@ "BriefDescription": "ProbeNops dispatched" }, {, - "EventCode": "0x58A8", - "EventName": "PM_DECODE_HOLD_ICT_FULL", - "BriefDescription": "Counts the number of cycles in which the IFU was not able to decode and transmit one or more instructions because all itags were in use. This means the ICT is full for this thread" - }, - {, "EventCode": "0x10052", "EventName": "PM_GRP_PUMP_MPRED_RTY", "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)" @@ -1572,7 +1632,7 @@ {, "EventCode": "0x2688A", "EventName": "PM_ISIDE_DISP_FAIL_OTHER", - "BriefDescription": "All I-side dispatch attempts for this thread that failed due to a reason other than addrs collision (excludes i_l2mru_tch_reqs)" + "BriefDescription": "All I-side-instruction-fetch dispatch attempts for this thread that failed due to reasons other than an address collision conflict with an L2 machine (e.g. no available RC/CO machines)" }, {, "EventCode": "0x2001A", @@ -1652,12 +1712,12 @@ {, "EventCode": "0x46880", "EventName": "PM_ISIDE_MRU_TOUCH", - "BriefDescription": "I-side L2 MRU touch sent to L2 for this thread" + "BriefDescription": "I-side L2 MRU touch sent to L2 for this thread I-side L2 MRU touch commands sent to the L2 for this thread" }, {, - "EventCode": "0x1C05C", - "EventName": "PM_DTLB_MISS_2M", - "BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used" + "EventCode": "0x508C", + "EventName": "PM_SHL_CREATED", + "BriefDescription": "Store-Hit-Load Table Entry Created" }, {, "EventCode": "0x50B8", @@ -1672,7 +1732,7 @@ {, "EventCode": "0x268B2", "EventName": "PM_L3_LOC_GUESS_WRONG", - "BriefDescription": "Initial scope=node (LNS) but data from out side local node (near or far or rem). Prediction too Low" + "BriefDescription": "Prefetch scope predictor selected LNS, but was wrong" }, {, "EventCode": "0x36088", @@ -1685,6 +1745,11 @@ "BriefDescription": "L3 PF received retry port 2, every retry counted" }, {, + "EventCode": "0xD8B0", + "EventName": "PM_PTESYNC", + "BriefDescription": "" + }, + {, "EventCode": "0x26086", "EventName": "PM_CO_TM_SC_FOOTPRINT", "BriefDescription": "L2 did a cleanifdirty CO to the L3 (ie created an SC line in the L3) OR L2 TM_store hit dirty HPC line and L3 indicated SC line formed in L3 on RDR bus" @@ -1740,6 +1805,11 @@ "BriefDescription": "All successful D-Side Store dispatches that were an L2 miss for this thread" }, {, + "EventCode": "0xF8B4", + "EventName": "PM_DC_PREF_XCONS_ALLOC", + "BriefDescription": "Prefetch stream allocated in the Ultra conservative phase by either the hardware prefetch mechanism or software prefetch" + }, + {, "EventCode": "0x35048", "EventName": "PM_IPTEG_FROM_DL2L3_SHR", "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a instruction side request" @@ -1782,7 +1852,7 @@ {, "EventCode": "0x460B2", "EventName": "PM_L3_SYS_GUESS_WRONG", - "BriefDescription": "Initial scope=system (VGS or RNS) but data from local or near. Prediction too high" + "BriefDescription": "Prefetch scope predictor selected VGS or RNS, but was wrong" }, {, "EventCode": "0x58B8", @@ -1800,11 +1870,6 @@ "BriefDescription": "Completion time tabortnoncd, tabortcd, treclaim" }, {, - "EventCode": "0x4C054", - "EventName": "PM_DERAT_MISS_16G", - "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16G" - }, - {, "EventCode": "0x268A0", "EventName": "PM_L3_CO_L31", "BriefDescription": "L3 CO to L3.1 OR of port 0 and 1 (lossy = may undercount if two cresps come in the same cyc)" @@ -1862,7 +1927,7 @@ {, "EventCode": "0x368B2", "EventName": "PM_L3_GRP_GUESS_WRONG_HIGH", - "BriefDescription": "Initial scope=group (GS or NNS) but data from local node. Prediction too high" + "BriefDescription": "Prefetch scope predictor selected GS or NNS, but was wrong because scope was VGS or RNS" }, {, "EventCode": "0xE8BC", @@ -1897,7 +1962,7 @@ {, "EventCode": "0x260B2", "EventName": "PM_L3_SYS_GUESS_CORRECT", - "BriefDescription": "Initial scope=system (VGS or RNS) and data from outside group (far or rem)(pred successful)" + "BriefDescription": "Prefetch scope predictor selected VGS or RNS and was correct" }, {, "EventCode": "0x1D146", @@ -1915,6 +1980,11 @@ "BriefDescription": "RC requests that were on group (aka nodel) pump attempts" }, {, + "EventCode": "0xC08C", + "EventName": "PM_LSU_DTLB_MISS_16M_2M", + "BriefDescription": "Data TLB Miss page size 16M (HPT) or 2M (Radix)" + }, + {, "EventCode": "0x16080", "EventName": "PM_L2_LD", "BriefDescription": "All successful D-side Load dispatches for this thread (L2 miss + L2 hits)" @@ -1927,7 +1997,7 @@ {, "EventCode": "0xC080", "EventName": "PM_LS0_LD_VECTOR_FIN", - "BriefDescription": "" + "BriefDescription": "LS0 finished load vector op" }, {, "EventCode": "0x368B0", @@ -2000,6 +2070,11 @@ "BriefDescription": "Conditional Branch Completed in which the HW correctly predicted the direction as taken. Counted at completion time" }, {, + "EventCode": "0xF0B8", + "EventName": "PM_LS0_UNALIGNED_ST", + "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size. If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty" + }, + {, "EventCode": "0x20132", "EventName": "PM_MRK_DFU_FIN", "BriefDescription": "Decimal Unit marked Instruction Finish" @@ -2007,7 +2082,7 @@ {, "EventCode": "0x160A6", "EventName": "PM_TM_SC_CO", - "BriefDescription": "L3 castout TM SC line" + "BriefDescription": "L3 castout of line that was StoreCopy (original value of speculatively written line) in a Transaction" }, {, "EventCode": "0xC8B0", @@ -2017,7 +2092,7 @@ {, "EventCode": "0x16084", "EventName": "PM_L2_RCLD_DISP", - "BriefDescription": "All I-or-D side load dispatch attempts for this thread (excludes i_l2mru_tch_reqs)" + "BriefDescription": "All D-side-Ld or I-side-instruction-fetch dispatch attempts for this thread" }, {, "EventCode": "0x3F150", @@ -2122,12 +2197,12 @@ {, "EventCode": "0x46082", "EventName": "PM_L2_ST_DISP", - "BriefDescription": "All successful D-side store dispatches for this thread (L2 miss + L2 hits)" + "BriefDescription": "All successful D-side store dispatches for this thread" }, {, "EventCode": "0x36880", "EventName": "PM_L2_INST_MISS", - "BriefDescription": "All successful I-side dispatches that were an L2 miss for this thread (excludes i_l2mru_tch reqs)" + "BriefDescription": "All successful I-side-instruction-fetch (e.g. i-demand, i-prefetch) dispatches for this thread that were an L2 miss" }, {, "EventCode": "0xE084", @@ -2217,7 +2292,7 @@ {, "EventCode": "0xC884", "EventName": "PM_LS3_LD_VECTOR_FIN", - "BriefDescription": "" + "BriefDescription": "LS3 finished load vector op" }, {, "EventCode": "0x360A8", @@ -2242,7 +2317,7 @@ {, "EventCode": "0x168B2", "EventName": "PM_L3_GRP_GUESS_CORRECT", - "BriefDescription": "Initial scope=group (GS or NNS) and data from same group (near) (pred successful)" + "BriefDescription": "Prefetch scope predictor selected GS or NNS and was correct" }, {, "EventCode": "0x48A4", diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json index 5af1abbe82c4..b4772f54a271 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json @@ -65,11 +65,6 @@ "BriefDescription": "Dispatch Held" }, {, - "EventCode": "0x3D154", - "EventName": "PM_MRK_DERAT_MISS_16M", - "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16M" - }, - {, "EventCode": "0x200F8", "EventName": "PM_EXT_INT", "BriefDescription": "external interrupt" @@ -120,6 +115,11 @@ "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" }, {, + "EventCode": "0x4C15C", + "EventName": "PM_MRK_DERAT_MISS_16G_1G", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16G (hpt mode) and 1G (radix mode)" + }, + {, "EventCode": "0x10024", "EventName": "PM_PMC5_OVERFLOW", "BriefDescription": "Overflow from counter 5" @@ -155,11 +155,6 @@ "BriefDescription": "Ict empty for this thread due to Icache Miss" }, {, - "EventCode": "0x3D152", - "EventName": "PM_MRK_DERAT_MISS_1G", - "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation" - }, - {, "EventCode": "0x4F14A", "EventName": "PM_MRK_DPTEG_FROM_OFF_CHIP_CACHE", "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" @@ -185,11 +180,6 @@ "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" }, {, - "EventCode": "0x2C05A", - "EventName": "PM_DERAT_MISS_1G", - "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation" - }, - {, "EventCode": "0x1F058", "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L2", "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from the core's L2 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation" @@ -240,11 +230,6 @@ "BriefDescription": "Data PTEG reload" }, {, - "EventCode": "0x2D152", - "EventName": "PM_MRK_DERAT_MISS_2M", - "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation" - }, - {, "EventCode": "0x2C046", "EventName": "PM_DATA_FROM_RL2L3_MOD", "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load" @@ -290,6 +275,11 @@ "BriefDescription": "Finish stall because the NTF instruction was issued to the Decimal Floating Point execution pipe and waiting to finish. Includes decimal floating point instructions + 128 bit binary floating point instructions. Not qualified by multicycle" }, {, + "EventCode": "0x3C054", + "EventName": "PM_DERAT_MISS_16M_2M", + "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M (HPT mode) or 2M (Radix mode)" + }, + {, "EventCode": "0x4C04C", "EventName": "PM_DATA_FROM_DMEM", "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group (Distant) due to a demand load" @@ -360,11 +350,6 @@ "BriefDescription": "The processor's Instruction cache was reloaded from a memory location including L4 from local remote or distant due to an instruction fetch (not prefetch)" }, {, - "EventCode": "0x1C05A", - "EventName": "PM_DERAT_MISS_2M", - "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation" - }, - {, "EventCode": "0x30024", "EventName": "PM_PMC6_OVERFLOW", "BriefDescription": "Overflow from counter 6" @@ -375,6 +360,11 @@ "BriefDescription": "Branch Instruction Finished" }, {, + "EventCode": "0x3D154", + "EventName": "PM_MRK_DERAT_MISS_16M_2M", + "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16M (hpt mode) or 2M (radix mode)" + }, + {, "EventCode": "0x30020", "EventName": "PM_PMC2_REWIND", "BriefDescription": "PMC2 Rewind Event (did not match condition)" @@ -410,11 +400,6 @@ "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included" }, {, - "EventCode": "0x4C15C", - "EventName": "PM_MRK_DERAT_MISS_16G", - "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16G" - }, - {, "EventCode": "0x14052", "EventName": "PM_INST_GRP_PUMP_MPRED_RTY", "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for an instruction fetch" @@ -445,11 +430,6 @@ "BriefDescription": "Icache miss demand cycles" }, {, - "EventCode": "0x3C054", - "EventName": "PM_DERAT_MISS_16M", - "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M" - }, - {, "EventCode": "0x2D14E", "EventName": "PM_MRK_DATA_FROM_L21_SHR", "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L2 on the same chip due to a marked load" diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json index d0b89f930567..8b3b0f3be664 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json @@ -10,11 +10,6 @@ "BriefDescription": "Local memory above threshold for LSU medium" }, {, - "EventCode": "0x2C056", - "EventName": "PM_DTLB_MISS_4K", - "BriefDescription": "Data TLB Miss page size 4k" - }, - {, "EventCode": "0x40118", "EventName": "PM_MRK_DCACHE_RELOAD_INTV", "BriefDescription": "Combined Intervention event" diff --git a/tools/perf/pmu-events/arch/powerpc/power9/translation.json b/tools/perf/pmu-events/arch/powerpc/power9/translation.json index bc8e03d7a6b0..b27642676244 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/translation.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/translation.json @@ -30,11 +30,6 @@ "BriefDescription": "Store finish count. Includes speculative activity" }, {, - "EventCode": "0x44042", - "EventName": "PM_INST_FROM_L3", - "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 due to an instruction fetch (not prefetch)" - }, - {, "EventCode": "0x1504A", "EventName": "PM_IPTEG_FROM_RL2L3_SHR", "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a instruction side request" @@ -125,6 +120,11 @@ "BriefDescription": "PMC1 Rewind Value saved" }, {, + "EventCode": "0x44042", + "EventName": "PM_INST_FROM_L3", + "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 due to an instruction fetch (not prefetch)" + }, + {, "EventCode": "0x200FE", "EventName": "PM_DATA_FROM_L2MISS", "BriefDescription": "Demand LD - L2 Miss (not L2 hit)" diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json new file mode 100644 index 000000000000..2dd8dafff2ef --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json @@ -0,0 +1,86 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "0", + "EventName": "CPU_CYCLES", + "BriefDescription": "CPU Cycles", + "PublicDescription": "Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "1", + "EventName": "INSTRUCTIONS", + "BriefDescription": "Instructions", + "PublicDescription": "Instruction Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "2", + "EventName": "L1I_DIR_WRITES", + "BriefDescription": "L1I Directory Writes", + "PublicDescription": "Level-1 I-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "3", + "EventName": "L1I_PENALTY_CYCLES", + "BriefDescription": "L1I Penalty Cycles", + "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "4", + "EventName": "L1D_DIR_WRITES", + "BriefDescription": "L1D Directory Writes", + "PublicDescription": "Level-1 D-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "5", + "EventName": "L1D_PENALTY_CYCLES", + "BriefDescription": "L1D Penalty Cycles", + "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "32", + "EventName": "PROBLEM_STATE_CPU_CYCLES", + "BriefDescription": "Problem-State CPU Cycles", + "PublicDescription": "Problem-State Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "33", + "EventName": "PROBLEM_STATE_INSTRUCTIONS", + "BriefDescription": "Problem-State Instructions", + "PublicDescription": "Problem-State Instruction Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "34", + "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", + "BriefDescription": "Problem-State L1I Directory Writes", + "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "35", + "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", + "BriefDescription": "Problem-State L1I Penalty Cycles", + "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "36", + "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", + "BriefDescription": "Problem-State L1D Directory Writes", + "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "37", + "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 new file mode 100644 index 000000000000..db286f19e7b6 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json @@ -0,0 +1,114 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "64", + "EventName": "PRNG_FUNCTIONS", + "BriefDescription": "PRNG Functions", + "PublicDescription": "Total number of the PRNG functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "65", + "EventName": "PRNG_CYCLES", + "BriefDescription": "PRNG Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "66", + "EventName": "PRNG_BLOCKED_FUNCTIONS", + "BriefDescription": "PRNG Blocked Functions", + "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "67", + "EventName": "PRNG_BLOCKED_CYCLES", + "BriefDescription": "PRNG Blocked Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "68", + "EventName": "SHA_FUNCTIONS", + "BriefDescription": "SHA Functions", + "PublicDescription": "Total number of SHA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "69", + "EventName": "SHA_CYCLES", + "BriefDescription": "SHA Cycles", + "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "70", + "EventName": "SHA_BLOCKED_FUNCTIONS", + "BriefDescription": "SHA Blocked Functions", + "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "71", + "EventName": "SHA_BLOCKED_CYCLES", + "BriefDescription": "SHA Bloced Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "72", + "EventName": "DEA_FUNCTIONS", + "BriefDescription": "DEA Functions", + "PublicDescription": "Total number of the DEA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "73", + "EventName": "DEA_CYCLES", + "BriefDescription": "DEA Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "74", + "EventName": "DEA_BLOCKED_FUNCTIONS", + "BriefDescription": "DEA Blocked Functions", + "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "75", + "EventName": "DEA_BLOCKED_CYCLES", + "BriefDescription": "DEA Blocked Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "76", + "EventName": "AES_FUNCTIONS", + "BriefDescription": "AES Functions", + "PublicDescription": "Total number of AES functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "77", + "EventName": "AES_CYCLES", + "BriefDescription": "AES Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "78", + "EventName": "AES_BLOCKED_FUNCTIONS", + "BriefDescription": "AES Blocked Functions", + "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "79", + "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 new file mode 100644 index 000000000000..b6b7f29ca831 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json @@ -0,0 +1,128 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "128", + "EventName": "L1I_L2_SOURCED_WRITES", + "BriefDescription": "L1I L2 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 (L1.5) cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "129", + "EventName": "L1D_L2_SOURCED_WRITES", + "BriefDescription": "L1D L2 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from the Level-2 (L1.5) cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "130", + "EventName": "L1I_L3_LOCAL_WRITES", + "BriefDescription": "L1I L3 Local Writes", + "PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from the Level-3 cache that is on the same book as the Instruction cache (Local L2 cache)" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "131", + "EventName": "L1D_L3_LOCAL_WRITES", + "BriefDescription": "L1D L3 Local Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installtion cache line was source from the Level-3 cache that is on the same book as the Data cache (Local L2 cache)" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "132", + "EventName": "L1I_L3_REMOTE_WRITES", + "BriefDescription": "L1I L3 Remote Writes", + "PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Instruction cache (Remote L2 cache)" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "133", + "EventName": "L1D_L3_REMOTE_WRITES", + "BriefDescription": "L1D L3 Remote Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Data cache (Remote L2 cache)" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "134", + "EventName": "L1D_LMEM_SOURCED_WRITES", + "BriefDescription": "L1D Local Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "135", + "EventName": "L1I_LMEM_SOURCED_WRITES", + "BriefDescription": "L1I Local Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the s ame book as the Instruction cache (Local Memory)" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "136", + "EventName": "L1D_RO_EXCL_WRITES", + "BriefDescription": "L1D Read-only Exclusive Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "137", + "EventName": "L1I_CACHELINE_INVALIDATES", + "BriefDescription": "L1I Cacheline Invalidates", + "PublicDescription": "A cache line in the Level-1 I-Cache has been invalidated by a store on the same CPU as the Level-1 I-Cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "138", + "EventName": "ITLB1_WRITES", + "BriefDescription": "ITLB1 Writes", + "PublicDescription": "A translation entry has been written into the Level-1 Instruction Translation Lookaside Buffer" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "139", + "EventName": "DTLB1_WRITES", + "BriefDescription": "DTLB1 Writes", + "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "140", + "EventName": "TLB2_PTE_WRITES", + "BriefDescription": "TLB2 PTE Writes", + "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "141", + "EventName": "TLB2_CRSTE_WRITES", + "BriefDescription": "TLB2 CRSTE Writes", + "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "142", + "EventName": "TLB2_CRSTE_HPAGE_WRITES", + "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", + "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "145", + "EventName": "ITLB1_MISSES", + "BriefDescription": "ITLB1 Misses", + "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "146", + "EventName": "DTLB1_MISSES", + "BriefDescription": "DTLB1 Misses", + "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle an DTLB1 miss is in progress" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "147", + "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 new file mode 100644 index 000000000000..2dd8dafff2ef --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json @@ -0,0 +1,86 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "0", + "EventName": "CPU_CYCLES", + "BriefDescription": "CPU Cycles", + "PublicDescription": "Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "1", + "EventName": "INSTRUCTIONS", + "BriefDescription": "Instructions", + "PublicDescription": "Instruction Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "2", + "EventName": "L1I_DIR_WRITES", + "BriefDescription": "L1I Directory Writes", + "PublicDescription": "Level-1 I-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "3", + "EventName": "L1I_PENALTY_CYCLES", + "BriefDescription": "L1I Penalty Cycles", + "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "4", + "EventName": "L1D_DIR_WRITES", + "BriefDescription": "L1D Directory Writes", + "PublicDescription": "Level-1 D-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "5", + "EventName": "L1D_PENALTY_CYCLES", + "BriefDescription": "L1D Penalty Cycles", + "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "32", + "EventName": "PROBLEM_STATE_CPU_CYCLES", + "BriefDescription": "Problem-State CPU Cycles", + "PublicDescription": "Problem-State Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "33", + "EventName": "PROBLEM_STATE_INSTRUCTIONS", + "BriefDescription": "Problem-State Instructions", + "PublicDescription": "Problem-State Instruction Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "34", + "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", + "BriefDescription": "Problem-State L1I Directory Writes", + "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "35", + "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", + "BriefDescription": "Problem-State L1I Penalty Cycles", + "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "36", + "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", + "BriefDescription": "Problem-State L1D Directory Writes", + "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "37", + "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 new file mode 100644 index 000000000000..db286f19e7b6 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json @@ -0,0 +1,114 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "64", + "EventName": "PRNG_FUNCTIONS", + "BriefDescription": "PRNG Functions", + "PublicDescription": "Total number of the PRNG functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "65", + "EventName": "PRNG_CYCLES", + "BriefDescription": "PRNG Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "66", + "EventName": "PRNG_BLOCKED_FUNCTIONS", + "BriefDescription": "PRNG Blocked Functions", + "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "67", + "EventName": "PRNG_BLOCKED_CYCLES", + "BriefDescription": "PRNG Blocked Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "68", + "EventName": "SHA_FUNCTIONS", + "BriefDescription": "SHA Functions", + "PublicDescription": "Total number of SHA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "69", + "EventName": "SHA_CYCLES", + "BriefDescription": "SHA Cycles", + "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "70", + "EventName": "SHA_BLOCKED_FUNCTIONS", + "BriefDescription": "SHA Blocked Functions", + "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "71", + "EventName": "SHA_BLOCKED_CYCLES", + "BriefDescription": "SHA Bloced Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "72", + "EventName": "DEA_FUNCTIONS", + "BriefDescription": "DEA Functions", + "PublicDescription": "Total number of the DEA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "73", + "EventName": "DEA_CYCLES", + "BriefDescription": "DEA Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "74", + "EventName": "DEA_BLOCKED_FUNCTIONS", + "BriefDescription": "DEA Blocked Functions", + "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "75", + "EventName": "DEA_BLOCKED_CYCLES", + "BriefDescription": "DEA Blocked Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "76", + "EventName": "AES_FUNCTIONS", + "BriefDescription": "AES Functions", + "PublicDescription": "Total number of AES functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "77", + "EventName": "AES_CYCLES", + "BriefDescription": "AES Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "78", + "EventName": "AES_BLOCKED_FUNCTIONS", + "BriefDescription": "AES Blocked Functions", + "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "79", + "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 new file mode 100644 index 000000000000..436ce33f1182 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json @@ -0,0 +1,394 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "128", + "EventName": "L1D_RO_EXCL_WRITES", + "BriefDescription": "L1D Read-only Exclusive Writes", + "PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line." + }, + { + "Unit": "CPU-M-CF", + "EventCode": "129", + "EventName": "DTLB1_WRITES", + "BriefDescription": "DTLB1 Writes", + "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "130", + "EventName": "DTLB1_MISSES", + "BriefDescription": "DTLB1 Misses", + "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress." + }, + { + "Unit": "CPU-M-CF", + "EventCode": "131", + "EventName": "DTLB1_HPAGE_WRITES", + "BriefDescription": "DTLB1 One-Megabyte Page Writes", + "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "132", + "EventName": "DTLB1_GPAGE_WRITES", + "BriefDescription": "DTLB1 Two-Gigabyte Page Writes", + "PublicDescription": "Counter:132 Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page." + }, + { + "Unit": "CPU-M-CF", + "EventCode": "133", + "EventName": "L1D_L2D_SOURCED_WRITES", + "BriefDescription": "L1D L2D Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "134", + "EventName": "ITLB1_WRITES", + "BriefDescription": "ITLB1 Writes", + "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "135", + "EventName": "ITLB1_MISSES", + "BriefDescription": "ITLB1 Misses", + "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "136", + "EventName": "L1I_L2I_SOURCED_WRITES", + "BriefDescription": "L1I L2I Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "137", + "EventName": "TLB2_PTE_WRITES", + "BriefDescription": "TLB2 PTE Writes", + "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "138", + "EventName": "TLB2_CRSTE_HPAGE_WRITES", + "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", + "PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays for a one-megabyte large page translation" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "139", + "EventName": "TLB2_CRSTE_WRITES", + "BriefDescription": "TLB2 CRSTE Writes", + "PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "140", + "EventName": "TX_C_TEND", + "BriefDescription": "Completed TEND instructions in constrained TX mode", + "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "141", + "EventName": "TX_NC_TEND", + "BriefDescription": "Completed TEND instructions in non-constrained TX mode", + "PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "143", + "EventName": "L1C_TLB1_MISSES", + "BriefDescription": "L1C TLB1 Misses", + "PublicDescription": "Increments by one for any cycle where a Level-1 cache or Level-1 TLB miss is in progress." + }, + { + "Unit": "CPU-M-CF", + "EventCode": "144", + "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", + "BriefDescription": "L1D On-Chip L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "145", + "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "146", + "EventName": "L1D_ONNODE_L4_SOURCED_WRITES", + "BriefDescription": "L1D On-Node L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "147", + "EventName": "L1D_ONNODE_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1D On-Node L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "148", + "EventName": "L1D_ONNODE_L3_SOURCED_WRITES", + "BriefDescription": "L1D On-Node L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "149", + "EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES", + "BriefDescription": "L1D On-Drawer L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "150", + "EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1D On-Drawer L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "151", + "EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES", + "BriefDescription": "L1D On-Drawer L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "152", + "EventName": "L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES", + "BriefDescription": "L1D Off-Drawer Same-Column L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "153", + "EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "154", + "EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES", + "BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "155", + "EventName": "L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES", + "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "156", + "EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "157", + "EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES", + "BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "158", + "EventName": "L1D_ONNODE_MEM_SOURCED_WRITES", + "BriefDescription": "L1D On-Node Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Node memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "159", + "EventName": "L1D_ONDRAWER_MEM_SOURCED_WRITES", + "BriefDescription": "L1D On-Drawer Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "160", + "EventName": "L1D_OFFDRAWER_MEM_SOURCED_WRITES", + "BriefDescription": "L1D Off-Drawer Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "161", + "EventName": "L1D_ONCHIP_MEM_SOURCED_WRITES", + "BriefDescription": "L1D On-Chip Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "162", + "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", + "BriefDescription": "L1I On-Chip L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "163", + "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "164", + "EventName": "L1I_ONNODE_L4_SOURCED_WRITES", + "BriefDescription": "L1I On-Chip L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "165", + "EventName": "L1I_ONNODE_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1I On-Node L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "166", + "EventName": "L1I_ONNODE_L3_SOURCED_WRITES", + "BriefDescription": "L1I On-Node L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "167", + "EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES", + "BriefDescription": "L1I On-Drawer L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "168", + "EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1I On-Drawer L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "169", + "EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES", + "BriefDescription": "L1I On-Drawer L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "170", + "EventName": "L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES", + "BriefDescription": "L1I Off-Drawer Same-Column L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "171", + "EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "172", + "EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES", + "BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "173", + "EventName": "L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES", + "BriefDescription": "L1I Off-Drawer Far-Column L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "174", + "EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "175", + "EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES", + "BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "176", + "EventName": "L1I_ONNODE_MEM_SOURCED_WRITES", + "BriefDescription": "L1I On-Node Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Node memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "177", + "EventName": "L1I_ONDRAWER_MEM_SOURCED_WRITES", + "BriefDescription": "L1I On-Drawer Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "178", + "EventName": "L1I_OFFDRAWER_MEM_SOURCED_WRITES", + "BriefDescription": "L1I Off-Drawer Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "179", + "EventName": "L1I_ONCHIP_MEM_SOURCED_WRITES", + "BriefDescription": "L1I On-Chip Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Chip memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "218", + "EventName": "TX_NC_TABORT", + "BriefDescription": "Aborted transactions in non-constrained TX mode", + "PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "219", + "EventName": "TX_C_TABORT_NO_SPECIAL", + "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic", + "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "220", + "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" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "448", + "EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE", + "BriefDescription": "Cycle count with one thread active", + "PublicDescription": "Cycle count with one thread active" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "449", + "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_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json new file mode 100644 index 000000000000..1a0034f79f73 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json @@ -0,0 +1,7 @@ +[ + { + "BriefDescription": "Transaction count", + "MetricName": "transaction", + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + } +] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json new file mode 100644 index 000000000000..17fb5241928b --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json @@ -0,0 +1,58 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "0", + "EventName": "CPU_CYCLES", + "BriefDescription": "CPU Cycles", + "PublicDescription": "Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "1", + "EventName": "INSTRUCTIONS", + "BriefDescription": "Instructions", + "PublicDescription": "Instruction Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "2", + "EventName": "L1I_DIR_WRITES", + "BriefDescription": "L1I Directory Writes", + "PublicDescription": "Level-1 I-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "3", + "EventName": "L1I_PENALTY_CYCLES", + "BriefDescription": "L1I Penalty Cycles", + "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "4", + "EventName": "L1D_DIR_WRITES", + "BriefDescription": "L1D Directory Writes", + "PublicDescription": "Level-1 D-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "5", + "EventName": "L1D_PENALTY_CYCLES", + "BriefDescription": "L1D Penalty Cycles", + "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "32", + "EventName": "PROBLEM_STATE_CPU_CYCLES", + "BriefDescription": "Problem-State CPU Cycles", + "PublicDescription": "Problem-State Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "33", + "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 new file mode 100644 index 000000000000..db286f19e7b6 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json @@ -0,0 +1,114 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "64", + "EventName": "PRNG_FUNCTIONS", + "BriefDescription": "PRNG Functions", + "PublicDescription": "Total number of the PRNG functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "65", + "EventName": "PRNG_CYCLES", + "BriefDescription": "PRNG Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "66", + "EventName": "PRNG_BLOCKED_FUNCTIONS", + "BriefDescription": "PRNG Blocked Functions", + "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "67", + "EventName": "PRNG_BLOCKED_CYCLES", + "BriefDescription": "PRNG Blocked Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "68", + "EventName": "SHA_FUNCTIONS", + "BriefDescription": "SHA Functions", + "PublicDescription": "Total number of SHA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "69", + "EventName": "SHA_CYCLES", + "BriefDescription": "SHA Cycles", + "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "70", + "EventName": "SHA_BLOCKED_FUNCTIONS", + "BriefDescription": "SHA Blocked Functions", + "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "71", + "EventName": "SHA_BLOCKED_CYCLES", + "BriefDescription": "SHA Bloced Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "72", + "EventName": "DEA_FUNCTIONS", + "BriefDescription": "DEA Functions", + "PublicDescription": "Total number of the DEA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "73", + "EventName": "DEA_CYCLES", + "BriefDescription": "DEA Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "74", + "EventName": "DEA_BLOCKED_FUNCTIONS", + "BriefDescription": "DEA Blocked Functions", + "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "75", + "EventName": "DEA_BLOCKED_CYCLES", + "BriefDescription": "DEA Blocked Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "76", + "EventName": "AES_FUNCTIONS", + "BriefDescription": "AES Functions", + "PublicDescription": "Total number of AES functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "77", + "EventName": "AES_CYCLES", + "BriefDescription": "AES Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "78", + "EventName": "AES_BLOCKED_FUNCTIONS", + "BriefDescription": "AES Blocked Functions", + "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "79", + "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 new file mode 100644 index 000000000000..e7a3524b748f --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json @@ -0,0 +1,373 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "128", + "EventName": "L1D_RO_EXCL_WRITES", + "BriefDescription": "L1D Read-only Exclusive Writes", + "PublicDescription": "Counter:128 Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "129", + "EventName": "DTLB2_WRITES", + "BriefDescription": "DTLB2 Writes", + "PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "130", + "EventName": "DTLB2_MISSES", + "BriefDescription": "DTLB2 Misses", + "PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "131", + "EventName": "DTLB2_HPAGE_WRITES", + "BriefDescription": "DTLB2 One-Megabyte Page Writes", + "PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "132", + "EventName": "DTLB2_GPAGE_WRITES", + "BriefDescription": "DTLB2 Two-Gigabyte Page Writes", + "PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "133", + "EventName": "L1D_L2D_SOURCED_WRITES", + "BriefDescription": "L1D L2D Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "134", + "EventName": "ITLB2_WRITES", + "BriefDescription": "ITLB2 Writes", + "PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "135", + "EventName": "ITLB2_MISSES", + "BriefDescription": "ITLB2 Misses", + "PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "136", + "EventName": "L1I_L2I_SOURCED_WRITES", + "BriefDescription": "L1I L2I Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "137", + "EventName": "TLB2_PTE_WRITES", + "BriefDescription": "TLB2 PTE Writes", + "PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "138", + "EventName": "TLB2_CRSTE_WRITES", + "BriefDescription": "TLB2 CRSTE Writes", + "PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "139", + "EventName": "TLB2_ENGINES_BUSY", + "BriefDescription": "TLB2 Engines Busy", + "PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "140", + "EventName": "TX_C_TEND", + "BriefDescription": "Completed TEND instructions in constrained TX mode", + "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "141", + "EventName": "TX_NC_TEND", + "BriefDescription": "Completed TEND instructions in non-constrained TX mode", + "PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "143", + "EventName": "L1C_TLB2_MISSES", + "BriefDescription": "L1C TLB2 Misses", + "PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "144", + "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", + "BriefDescription": "L1D On-Chip L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "145", + "EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES", + "BriefDescription": "L1D On-Chip Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "146", + "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "147", + "EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES", + "BriefDescription": "L1D On-Cluster L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "148", + "EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES", + "BriefDescription": "L1D On-Cluster Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "149", + "EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "150", + "EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES", + "BriefDescription": "L1D Off-Cluster L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "151", + "EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES", + "BriefDescription": "L1D Off-Cluster Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "152", + "EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "153", + "EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES", + "BriefDescription": "L1D Off-Drawer L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "154", + "EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES", + "BriefDescription": "L1D Off-Drawer Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "155", + "EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "156", + "EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES", + "BriefDescription": "L1D On-Drawer L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "157", + "EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES", + "BriefDescription": "L1D Off-Drawer L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "158", + "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO", + "BriefDescription": "L1D On-Chip L3 Sourced Writes read-only", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "162", + "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", + "BriefDescription": "L1I On-Chip L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "163", + "EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES", + "BriefDescription": "L1I On-Chip Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "164", + "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "165", + "EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES", + "BriefDescription": "L1I On-Cluster L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "166", + "EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES", + "BriefDescription": "L1I On-Cluster Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "167", + "EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "168", + "EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES", + "BriefDescription": "L1I Off-Cluster L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "169", + "EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES", + "BriefDescription": "L1I Off-Cluster Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "170", + "EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "171", + "EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES", + "BriefDescription": "L1I Off-Drawer L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "172", + "EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES", + "BriefDescription": "L1I Off-Drawer Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "173", + "EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "174", + "EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES", + "BriefDescription": "L1I On-Drawer L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "175", + "EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES", + "BriefDescription": "L1I Off-Drawer L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "224", + "EventName": "BCD_DFP_EXECUTION_SLOTS", + "BriefDescription": "BCD DFP Execution Slots", + "PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "225", + "EventName": "VX_BCD_EXECUTION_SLOTS", + "BriefDescription": "VX BCD Execution Slots", + "PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "226", + "EventName": "DECIMAL_INSTRUCTIONS", + "BriefDescription": "Decimal Instructions", + "PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "232", + "EventName": "LAST_HOST_TRANSLATIONS", + "BriefDescription": "Last host translation done", + "PublicDescription": "Last Host Translation done" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "243", + "EventName": "TX_NC_TABORT", + "BriefDescription": "Aborted transactions in non-constrained TX mode", + "PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "244", + "EventName": "TX_C_TABORT_NO_SPECIAL", + "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic", + "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "245", + "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" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "448", + "EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE", + "BriefDescription": "Cycle count with one thread active", + "PublicDescription": "Cycle count with one thread active" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "449", + "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/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json new file mode 100644 index 000000000000..1a0034f79f73 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json @@ -0,0 +1,7 @@ +[ + { + "BriefDescription": "Transaction count", + "MetricName": "transaction", + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + } +] diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json new file mode 100644 index 000000000000..2dd8dafff2ef --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json @@ -0,0 +1,86 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "0", + "EventName": "CPU_CYCLES", + "BriefDescription": "CPU Cycles", + "PublicDescription": "Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "1", + "EventName": "INSTRUCTIONS", + "BriefDescription": "Instructions", + "PublicDescription": "Instruction Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "2", + "EventName": "L1I_DIR_WRITES", + "BriefDescription": "L1I Directory Writes", + "PublicDescription": "Level-1 I-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "3", + "EventName": "L1I_PENALTY_CYCLES", + "BriefDescription": "L1I Penalty Cycles", + "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "4", + "EventName": "L1D_DIR_WRITES", + "BriefDescription": "L1D Directory Writes", + "PublicDescription": "Level-1 D-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "5", + "EventName": "L1D_PENALTY_CYCLES", + "BriefDescription": "L1D Penalty Cycles", + "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "32", + "EventName": "PROBLEM_STATE_CPU_CYCLES", + "BriefDescription": "Problem-State CPU Cycles", + "PublicDescription": "Problem-State Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "33", + "EventName": "PROBLEM_STATE_INSTRUCTIONS", + "BriefDescription": "Problem-State Instructions", + "PublicDescription": "Problem-State Instruction Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "34", + "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", + "BriefDescription": "Problem-State L1I Directory Writes", + "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "35", + "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", + "BriefDescription": "Problem-State L1I Penalty Cycles", + "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "36", + "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", + "BriefDescription": "Problem-State L1D Directory Writes", + "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "37", + "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 new file mode 100644 index 000000000000..db286f19e7b6 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json @@ -0,0 +1,114 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "64", + "EventName": "PRNG_FUNCTIONS", + "BriefDescription": "PRNG Functions", + "PublicDescription": "Total number of the PRNG functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "65", + "EventName": "PRNG_CYCLES", + "BriefDescription": "PRNG Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "66", + "EventName": "PRNG_BLOCKED_FUNCTIONS", + "BriefDescription": "PRNG Blocked Functions", + "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "67", + "EventName": "PRNG_BLOCKED_CYCLES", + "BriefDescription": "PRNG Blocked Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "68", + "EventName": "SHA_FUNCTIONS", + "BriefDescription": "SHA Functions", + "PublicDescription": "Total number of SHA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "69", + "EventName": "SHA_CYCLES", + "BriefDescription": "SHA Cycles", + "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "70", + "EventName": "SHA_BLOCKED_FUNCTIONS", + "BriefDescription": "SHA Blocked Functions", + "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "71", + "EventName": "SHA_BLOCKED_CYCLES", + "BriefDescription": "SHA Bloced Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "72", + "EventName": "DEA_FUNCTIONS", + "BriefDescription": "DEA Functions", + "PublicDescription": "Total number of the DEA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "73", + "EventName": "DEA_CYCLES", + "BriefDescription": "DEA Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "74", + "EventName": "DEA_BLOCKED_FUNCTIONS", + "BriefDescription": "DEA Blocked Functions", + "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "75", + "EventName": "DEA_BLOCKED_CYCLES", + "BriefDescription": "DEA Blocked Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "76", + "EventName": "AES_FUNCTIONS", + "BriefDescription": "AES Functions", + "PublicDescription": "Total number of AES functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "77", + "EventName": "AES_CYCLES", + "BriefDescription": "AES Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "78", + "EventName": "AES_BLOCKED_FUNCTIONS", + "BriefDescription": "AES Blocked Functions", + "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "79", + "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 new file mode 100644 index 000000000000..b7b42a870bb0 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json @@ -0,0 +1,170 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "128", + "EventName": "L1D_L2_SOURCED_WRITES", + "BriefDescription": "L1D L2 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from the Level-2 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "129", + "EventName": "L1I_L2_SOURCED_WRITES", + "BriefDescription": "L1I L2 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "130", + "EventName": "DTLB1_MISSES", + "BriefDescription": "DTLB1 Misses", + "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress." + }, + { + "Unit": "CPU-M-CF", + "EventCode": "131", + "EventName": "ITLB1_MISSES", + "BriefDescription": "ITLB1 Misses", + "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress." + }, + { + "Unit": "CPU-M-CF", + "EventCode": "133", + "EventName": "L2C_STORES_SENT", + "BriefDescription": "L2C Stores Sent", + "PublicDescription": "Incremented by one for every store sent to Level-2 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "134", + "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES", + "BriefDescription": "L1D Off-Book L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "135", + "EventName": "L1D_ONBOOK_L4_SOURCED_WRITES", + "BriefDescription": "L1D On-Book L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Book Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "136", + "EventName": "L1I_ONBOOK_L4_SOURCED_WRITES", + "BriefDescription": "L1I On-Book L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Book Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "137", + "EventName": "L1D_RO_EXCL_WRITES", + "BriefDescription": "L1D Read-only Exclusive Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "138", + "EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES", + "BriefDescription": "L1D Off-Book L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "139", + "EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES", + "BriefDescription": "L1I Off-Book L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "140", + "EventName": "DTLB1_HPAGE_WRITES", + "BriefDescription": "DTLB1 One-Megabyte Page Writes", + "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "141", + "EventName": "L1D_LMEM_SOURCED_WRITES", + "BriefDescription": "L1D Local Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "142", + "EventName": "L1I_LMEM_SOURCED_WRITES", + "BriefDescription": "L1I Local Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "143", + "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES", + "BriefDescription": "L1I Off-Book L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "144", + "EventName": "DTLB1_WRITES", + "BriefDescription": "DTLB1 Writes", + "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "145", + "EventName": "ITLB1_WRITES", + "BriefDescription": "ITLB1 Writes", + "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "146", + "EventName": "TLB2_PTE_WRITES", + "BriefDescription": "TLB2 PTE Writes", + "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "147", + "EventName": "TLB2_CRSTE_HPAGE_WRITES", + "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", + "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "148", + "EventName": "TLB2_CRSTE_WRITES", + "BriefDescription": "TLB2 CRSTE Writes", + "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "150", + "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", + "BriefDescription": "L1D On-Chip L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "152", + "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES", + "BriefDescription": "L1D Off-Chip L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "153", + "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", + "BriefDescription": "L1I On-Chip L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "155", + "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 new file mode 100644 index 000000000000..2dd8dafff2ef --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json @@ -0,0 +1,86 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "0", + "EventName": "CPU_CYCLES", + "BriefDescription": "CPU Cycles", + "PublicDescription": "Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "1", + "EventName": "INSTRUCTIONS", + "BriefDescription": "Instructions", + "PublicDescription": "Instruction Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "2", + "EventName": "L1I_DIR_WRITES", + "BriefDescription": "L1I Directory Writes", + "PublicDescription": "Level-1 I-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "3", + "EventName": "L1I_PENALTY_CYCLES", + "BriefDescription": "L1I Penalty Cycles", + "PublicDescription": "Level-1 I-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "4", + "EventName": "L1D_DIR_WRITES", + "BriefDescription": "L1D Directory Writes", + "PublicDescription": "Level-1 D-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "5", + "EventName": "L1D_PENALTY_CYCLES", + "BriefDescription": "L1D Penalty Cycles", + "PublicDescription": "Level-1 D-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "32", + "EventName": "PROBLEM_STATE_CPU_CYCLES", + "BriefDescription": "Problem-State CPU Cycles", + "PublicDescription": "Problem-State Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "33", + "EventName": "PROBLEM_STATE_INSTRUCTIONS", + "BriefDescription": "Problem-State Instructions", + "PublicDescription": "Problem-State Instruction Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "34", + "EventName": "PROBLEM_STATE_L1I_DIR_WRITES", + "BriefDescription": "Problem-State L1I Directory Writes", + "PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "35", + "EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES", + "BriefDescription": "Problem-State L1I Penalty Cycles", + "PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "36", + "EventName": "PROBLEM_STATE_L1D_DIR_WRITES", + "BriefDescription": "Problem-State L1D Directory Writes", + "PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "37", + "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 new file mode 100644 index 000000000000..db286f19e7b6 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json @@ -0,0 +1,114 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "64", + "EventName": "PRNG_FUNCTIONS", + "BriefDescription": "PRNG Functions", + "PublicDescription": "Total number of the PRNG functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "65", + "EventName": "PRNG_CYCLES", + "BriefDescription": "PRNG Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "66", + "EventName": "PRNG_BLOCKED_FUNCTIONS", + "BriefDescription": "PRNG Blocked Functions", + "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "67", + "EventName": "PRNG_BLOCKED_CYCLES", + "BriefDescription": "PRNG Blocked Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "68", + "EventName": "SHA_FUNCTIONS", + "BriefDescription": "SHA Functions", + "PublicDescription": "Total number of SHA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "69", + "EventName": "SHA_CYCLES", + "BriefDescription": "SHA Cycles", + "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "70", + "EventName": "SHA_BLOCKED_FUNCTIONS", + "BriefDescription": "SHA Blocked Functions", + "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "71", + "EventName": "SHA_BLOCKED_CYCLES", + "BriefDescription": "SHA Bloced Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "72", + "EventName": "DEA_FUNCTIONS", + "BriefDescription": "DEA Functions", + "PublicDescription": "Total number of the DEA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "73", + "EventName": "DEA_CYCLES", + "BriefDescription": "DEA Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "74", + "EventName": "DEA_BLOCKED_FUNCTIONS", + "BriefDescription": "DEA Blocked Functions", + "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "75", + "EventName": "DEA_BLOCKED_CYCLES", + "BriefDescription": "DEA Blocked Cycles", + "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "76", + "EventName": "AES_FUNCTIONS", + "BriefDescription": "AES Functions", + "PublicDescription": "Total number of AES functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "77", + "EventName": "AES_CYCLES", + "BriefDescription": "AES Cycles", + "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "78", + "EventName": "AES_BLOCKED_FUNCTIONS", + "BriefDescription": "AES Blocked Functions", + "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "79", + "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 new file mode 100644 index 000000000000..162251037219 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json @@ -0,0 +1,247 @@ +[ + { + "Unit": "CPU-M-CF", + "EventCode": "128", + "EventName": "DTLB1_MISSES", + "BriefDescription": "DTLB1 Misses", + "PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress." + }, + { + "Unit": "CPU-M-CF", + "EventCode": "129", + "EventName": "ITLB1_MISSES", + "BriefDescription": "ITLB1 Misses", + "PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress." + }, + { + "Unit": "CPU-M-CF", + "EventCode": "130", + "EventName": "L1D_L2I_SOURCED_WRITES", + "BriefDescription": "L1D L2I Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Instruction cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "131", + "EventName": "L1I_L2I_SOURCED_WRITES", + "BriefDescription": "L1I L2I Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "132", + "EventName": "L1D_L2D_SOURCED_WRITES", + "BriefDescription": "L1D L2D Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "133", + "EventName": "DTLB1_WRITES", + "BriefDescription": "DTLB1 Writes", + "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "135", + "EventName": "L1D_LMEM_SOURCED_WRITES", + "BriefDescription": "L1D Local Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "137", + "EventName": "L1I_LMEM_SOURCED_WRITES", + "BriefDescription": "L1I Local Memory Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "138", + "EventName": "L1D_RO_EXCL_WRITES", + "BriefDescription": "L1D Read-only Exclusive Writes", + "PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "139", + "EventName": "DTLB1_HPAGE_WRITES", + "BriefDescription": "DTLB1 One-Megabyte Page Writes", + "PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "140", + "EventName": "ITLB1_WRITES", + "BriefDescription": "ITLB1 Writes", + "PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "141", + "EventName": "TLB2_PTE_WRITES", + "BriefDescription": "TLB2 PTE Writes", + "PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "142", + "EventName": "TLB2_CRSTE_HPAGE_WRITES", + "BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes", + "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "143", + "EventName": "TLB2_CRSTE_WRITES", + "BriefDescription": "TLB2 CRSTE Writes", + "PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "144", + "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES", + "BriefDescription": "L1D On-Chip L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "145", + "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES", + "BriefDescription": "L1D Off-Chip L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "146", + "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES", + "BriefDescription": "L1D Off-Book L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "147", + "EventName": "L1D_ONBOOK_L4_SOURCED_WRITES", + "BriefDescription": "L1D On-Book L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Book Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "148", + "EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES", + "BriefDescription": "L1D Off-Book L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "149", + "EventName": "TX_NC_TEND", + "BriefDescription": "Completed TEND instructions in non-constrained TX mode", + "PublicDescription": "A TEND instruction has completed in a nonconstrained transactional-execution mode" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "150", + "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from a On Chip Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "151", + "EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1D Off-Chip L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "152", + "EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1D Off-Book L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "153", + "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES", + "BriefDescription": "L1I On-Chip L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "154", + "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES", + "BriefDescription": "L1I Off-Chip L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "155", + "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES", + "BriefDescription": "L1I Off-Book L3 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "156", + "EventName": "L1I_ONBOOK_L4_SOURCED_WRITES", + "BriefDescription": "L1I On-Book L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Book Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "157", + "EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES", + "BriefDescription": "L1I Off-Book L4 Sourced Writes", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-4 cache" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "158", + "EventName": "TX_C_TEND", + "BriefDescription": "Completed TEND instructions in constrained TX mode", + "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "159", + "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "160", + "EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1I Off-Chip L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "161", + "EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES_IV", + "BriefDescription": "L1I Off-Book L3 Sourced Writes with Intervention", + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "177", + "EventName": "TX_NC_TABORT", + "BriefDescription": "Aborted transactions in non-constrained TX mode", + "PublicDescription": "A transaction abort has occurred in a nonconstrained transactional-execution mode" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "178", + "EventName": "TX_C_TABORT_NO_SPECIAL", + "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic", + "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete" + }, + { + "Unit": "CPU-M-CF", + "EventCode": "179", + "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/s390/cf_zec12/transaction.json b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json new file mode 100644 index 000000000000..1a0034f79f73 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json @@ -0,0 +1,7 @@ +[ + { + "BriefDescription": "Transaction count", + "MetricName": "transaction", + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + } +] diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv new file mode 100644 index 000000000000..78bcf7f8e206 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/mapfile.csv @@ -0,0 +1,6 @@ +Family-model,Version,Filename,EventType +^IBM.209[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z10,core +^IBM.281[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z196,core +^IBM.282[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_zec12,core +^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core +^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 93656f2fd53a..7e3cce3bcf3b 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -29,7 +29,6 @@ GenuineIntel-6-4D,v13,silvermont,core GenuineIntel-6-4C,v13,silvermont,core GenuineIntel-6-2A,v15,sandybridge,core GenuineIntel-6-2C,v2,westmereep-dp,core -GenuineIntel-6-2C,v2,westmereep-dp,core GenuineIntel-6-25,v2,westmereep-sp,core GenuineIntel-6-2F,v2,westmereex,core GenuineIntel-6-55,v1,skylakex,core diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index b578aa26e375..68c92bb599ee 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -39,11 +39,13 @@ #include <unistd.h> #include <stdarg.h> #include <libgen.h> +#include <limits.h> #include <dirent.h> #include <sys/time.h> /* getrlimit */ #include <sys/resource.h> /* getrlimit */ #include <ftw.h> #include <sys/stat.h> +#include <linux/list.h> #include "jsmn.h" #include "json.h" #include "jevents.h" @@ -231,6 +233,8 @@ static struct map { { "QPI LL", "uncore_qpi" }, { "SBO", "uncore_sbox" }, { "iMPH-U", "uncore_arb" }, + { "CPU-M-CF", "cpum_cf" }, + { "CPU-M-SF", "cpum_sf" }, {} }; @@ -249,31 +253,25 @@ static const char *field_to_perf(struct map *table, char *map, jsmntok_t *val) jsmntok_t *loc = (t); \ if (!(t)->start && (t) > tokens) \ loc = (t) - 1; \ - pr_err("%s:%d: " m ", got %s\n", fn, \ - json_line(map, loc), \ - json_name(t)); \ + pr_err("%s:%d: " m ", got %s\n", fn, \ + json_line(map, loc), \ + json_name(t)); \ + err = -EIO; \ goto out_free; \ } } while (0) -#define TOPIC_DEPTH 256 -static char *topic_array[TOPIC_DEPTH]; -static int topic_level; +static char *topic; static char *get_topic(void) { - char *tp_old, *tp = NULL; + char *tp; int i; - for (i = 0; i < topic_level + 1; i++) { - int n; - - tp_old = tp; - n = asprintf(&tp, "%s%s", tp ?: "", topic_array[i]); - if (n < 0) { - pr_info("%s: asprintf() error %s\n", prog); - return NULL; - } - free(tp_old); + /* tp is free'd in process_one_file() */ + i = asprintf(&tp, "%s", topic); + if (i < 0) { + pr_info("%s: asprintf() error %s\n", prog); + return NULL; } for (i = 0; i < (int) strlen(tp); i++) { @@ -290,25 +288,15 @@ static char *get_topic(void) return tp; } -static int add_topic(int level, char *bname) +static int add_topic(char *bname) { - char *topic; - - level -= 2; - - if (level >= TOPIC_DEPTH) - return -EINVAL; - + free(topic); topic = strdup(bname); if (!topic) { pr_info("%s: strdup() error %s for file %s\n", prog, strerror(errno), bname); return -ENOMEM; } - - free(topic_array[topic_level]); - topic_array[topic_level] = topic; - topic_level = level; return 0; } @@ -366,6 +354,81 @@ static int print_events_table_entry(void *data, char *name, char *event, return 0; } +struct event_struct { + struct list_head list; + char *name; + char *event; + char *desc; + char *long_desc; + char *pmu; + char *unit; + char *perpkg; + char *metric_expr; + char *metric_name; + char *metric_group; +}; + +#define ADD_EVENT_FIELD(field) do { if (field) { \ + es->field = strdup(field); \ + if (!es->field) \ + goto out_free; \ +} } while (0) + +#define FREE_EVENT_FIELD(field) free(es->field) + +#define TRY_FIXUP_FIELD(field) do { if (es->field && !*field) {\ + *field = strdup(es->field); \ + if (!*field) \ + return -ENOMEM; \ +} } while (0) + +#define FOR_ALL_EVENT_STRUCT_FIELDS(op) do { \ + op(name); \ + op(event); \ + op(desc); \ + op(long_desc); \ + op(pmu); \ + op(unit); \ + op(perpkg); \ + op(metric_expr); \ + op(metric_name); \ + op(metric_group); \ +} while (0) + +static LIST_HEAD(arch_std_events); + +static void free_arch_std_events(void) +{ + struct event_struct *es, *next; + + list_for_each_entry_safe(es, next, &arch_std_events, list) { + FOR_ALL_EVENT_STRUCT_FIELDS(FREE_EVENT_FIELD); + list_del(&es->list); + free(es); + } +} + +static int save_arch_std_events(void *data, char *name, char *event, + char *desc, char *long_desc, char *pmu, + char *unit, char *perpkg, char *metric_expr, + char *metric_name, char *metric_group) +{ + struct event_struct *es; + struct stat *sb = data; + + es = malloc(sizeof(*es)); + if (!es) + return -ENOMEM; + memset(es, 0, sizeof(*es)); + FOR_ALL_EVENT_STRUCT_FIELDS(ADD_EVENT_FIELD); + list_add_tail(&es->list, &arch_std_events); + return 0; +out_free: + FOR_ALL_EVENT_STRUCT_FIELDS(FREE_EVENT_FIELD); + free(es); + return -ENOMEM; +} + static void print_events_table_suffix(FILE *outfp) { fprintf(outfp, "{\n"); @@ -407,6 +470,32 @@ static char *real_event(const char *name, char *event) return event; } +static int +try_fixup(const char *fn, char *arch_std, char **event, char **desc, + char **name, char **long_desc, char **pmu, char **filter, + char **perpkg, char **unit, char **metric_expr, char **metric_name, + char **metric_group, unsigned long long eventcode) +{ + /* try to find matching event from arch standard values */ + struct event_struct *es; + + list_for_each_entry(es, &arch_std_events, list) { + if (!strcmp(arch_std, es->name)) { + if (!eventcode && es->event) { + /* allow EventCode to be overridden */ + free(*event); + *event = NULL; + } + FOR_ALL_EVENT_STRUCT_FIELDS(TRY_FIXUP_FIELD); + return 0; + } + } + + pr_err("%s: could not find matching %s for %s\n", + prog, arch_std, fn); + return -1; +} + /* Call func with each event in the json file */ int json_events(const char *fn, int (*func)(void *data, char *name, char *event, char *desc, @@ -416,7 +505,7 @@ int json_events(const char *fn, char *metric_name, char *metric_group), void *data) { - int err = -EIO; + int err; size_t size; jsmntok_t *tokens, *tok; int i, j, len; @@ -442,6 +531,7 @@ int json_events(const char *fn, char *metric_expr = NULL; char *metric_name = NULL; char *metric_group = NULL; + char *arch_std = NULL; unsigned long long eventcode = 0; struct msrmap *msr = NULL; jsmntok_t *msrval = NULL; @@ -527,6 +617,10 @@ int json_events(const char *fn, addfield(map, &metric_expr, "", "", val); for (s = 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++) + *s = tolower(*s); } /* ignore unknown fields */ } @@ -551,8 +645,21 @@ int json_events(const char *fn, if (name) fixname(name); + if (arch_std) { + /* + * An arch standard event is referenced, so try to + * fixup any unassigned values. + */ + err = try_fixup(fn, arch_std, &event, &desc, &name, + &long_desc, &pmu, &filter, &perpkg, + &unit, &metric_expr, &metric_name, + &metric_group, eventcode); + if (err) + goto free_strings; + } err = func(data, name, real_event(name, event), desc, long_desc, pmu, unit, perpkg, metric_expr, metric_name, metric_group); +free_strings: free(event); free(desc); free(name); @@ -565,6 +672,8 @@ int json_events(const char *fn, free(metric_expr); free(metric_name); free(metric_group); + free(arch_std); + if (err) break; tok += j; @@ -588,7 +697,7 @@ static char *file_name_to_table_name(char *fname) * Derive rest of table name from basename of the JSON file, * replacing hyphens and stripping out .json suffix. */ - n = asprintf(&tblname, "pme_%s", basename(fname)); + n = asprintf(&tblname, "pme_%s", fname); if (n < 0) { pr_info("%s: asprintf() error %s for file %s\n", prog, strerror(errno), fname); @@ -598,7 +707,7 @@ static char *file_name_to_table_name(char *fname) for (i = 0; i < strlen(tblname); i++) { c = tblname[i]; - if (c == '-') + if (c == '-' || c == '/') tblname[i] = '_'; else if (c == '.') { tblname[i] = '\0'; @@ -755,25 +864,106 @@ static int get_maxfds(void) static FILE *eventsfp; static char *mapfile; +static int is_leaf_dir(const char *fpath) +{ + DIR *d; + struct dirent *dir; + int res = 1; + + d = opendir(fpath); + if (!d) + return 0; + + while ((dir = readdir(d)) != NULL) { + if (!strcmp(dir->d_name, ".") || !strcmp(dir->d_name, "..")) + continue; + + if (dir->d_type == DT_DIR) { + res = 0; + break; + } else if (dir->d_type == DT_UNKNOWN) { + char path[PATH_MAX]; + struct stat st; + + sprintf(path, "%s/%s", fpath, dir->d_name); + if (stat(path, &st)) + break; + + if (S_ISDIR(st.st_mode)) { + res = 0; + break; + } + } + } + + closedir(d); + + return res; +} + +static int is_json_file(const char *name) +{ + const char *suffix; + + if (strlen(name) < 5) + return 0; + + suffix = name + strlen(name) - 5; + + if (strncmp(suffix, ".json", 5) == 0) + return 1; + return 0; +} + +static int preprocess_arch_std_files(const char *fpath, const struct stat *sb, + int typeflag, struct FTW *ftwbuf) +{ + int level = ftwbuf->level; + int is_file = typeflag == FTW_F; + + if (level == 1 && is_file && is_json_file(fpath)) + return json_events(fpath, save_arch_std_events, (void *)sb); + + return 0; +} + static int process_one_file(const char *fpath, const struct stat *sb, int typeflag, struct FTW *ftwbuf) { - char *tblname, *bname = (char *) fpath + ftwbuf->base; + char *tblname, *bname; int is_dir = typeflag == FTW_D; int is_file = typeflag == FTW_F; int level = ftwbuf->level; int err = 0; + if (level == 2 && is_dir) { + /* + * For level 2 directory, bname will include parent name, + * like vendor/platform. So search back from platform dir + * to find this. + */ + bname = (char *) fpath + ftwbuf->base - 2; + for (;;) { + if (*bname == '/') + break; + bname--; + } + bname++; + } else + bname = (char *) fpath + ftwbuf->base; + pr_debug("%s %d %7jd %-20s %s\n", is_file ? "f" : is_dir ? "d" : "x", level, sb->st_size, bname, fpath); - /* base dir */ - if (level == 0) + /* base dir or too deep */ + if (level == 0 || level > 3) return 0; + /* model directory, reset topic */ - if (level == 1 && is_dir) { + if ((level == 1 && is_dir && is_leaf_dir(fpath)) || + (level == 2 && is_dir)) { if (close_table) print_events_table_suffix(eventsfp); @@ -798,16 +988,10 @@ static int process_one_file(const char *fpath, const struct stat *sb, * after processing all JSON files (so we can write out the * mapping table after all PMU events tables). * - * TODO: Allow for multiple mapfiles? Punt for now. */ if (level == 1 && is_file) { - if (!strncmp(bname, "mapfile.csv", 11)) { - if (mapfile) { - pr_info("%s: Many mapfiles? Using %s, ignoring %s\n", - prog, mapfile, fpath); - } else { - mapfile = strdup(fpath); - } + if (!strcmp(bname, "mapfile.csv")) { + mapfile = strdup(fpath); return 0; } @@ -820,16 +1004,14 @@ static int process_one_file(const char *fpath, const struct stat *sb, * ignore it. It could be a readme.txt for instance. */ if (is_file) { - char *suffix = bname + strlen(bname) - 5; - - if (strncmp(suffix, ".json", 5)) { + if (!is_json_file(bname)) { pr_info("%s: Ignoring file without .json suffix %s\n", prog, fpath); return 0; } } - if (level > 1 && add_topic(level, bname)) + if (level > 1 && add_topic(bname)) return -ENOMEM; /* @@ -928,12 +1110,26 @@ int main(int argc, char *argv[]) maxfds = get_maxfds(); mapfile = NULL; + rc = nftw(ldirname, preprocess_arch_std_files, maxfds, 0); + if (rc && verbose) { + pr_info("%s: Error preprocessing arch standard files %s\n", + prog, ldirname); + goto empty_map; + } else if (rc < 0) { + /* Make build fail */ + free_arch_std_events(); + return 1; + } else if (rc) { + goto empty_map; + } + rc = nftw(ldirname, process_one_file, maxfds, 0); if (rc && verbose) { pr_info("%s: Error walking file tree %s\n", prog, ldirname); goto empty_map; } else if (rc < 0) { /* Make build fail */ + free_arch_std_events(); return 1; } else if (rc) { goto empty_map; @@ -958,5 +1154,6 @@ int main(int argc, char *argv[]) empty_map: fclose(eventsfp); create_empty_mapping(output_file); + free_arch_std_events(); return 0; } diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py index c235c22b107a..0a29c5c3079f 100755 --- a/tools/perf/python/twatch.py +++ b/tools/perf/python/twatch.py @@ -42,10 +42,10 @@ def main(context_switch = 0, thread = -1): event = evlist.read_on_cpu(cpu) if not event: continue - print "cpu: %2d, pid: %4d, tid: %4d" % (event.sample_cpu, - event.sample_pid, - event.sample_tid), - print event + print("cpu: {0}, pid: {1}, tid: {2} {3}".format(event.sample_cpu, + event.sample_pid, + event.sample_tid, + event)) if __name__ == '__main__': """ diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c index fcd1dd667906..1a0d27757eec 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c +++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c @@ -23,7 +23,17 @@ #include "../../../perf.h" #include "../../../util/trace-event.h" +#if PY_MAJOR_VERSION < 3 +#define _PyCapsule_GetPointer(arg1, arg2) \ + PyCObject_AsVoidPtr(arg1) + PyMODINIT_FUNC initperf_trace_context(void); +#else +#define _PyCapsule_GetPointer(arg1, arg2) \ + PyCapsule_GetPointer((arg1), (arg2)) + +PyMODINIT_FUNC PyInit_perf_trace_context(void); +#endif static PyObject *perf_trace_context_common_pc(PyObject *obj, PyObject *args) { @@ -34,7 +44,7 @@ static PyObject *perf_trace_context_common_pc(PyObject *obj, PyObject *args) if (!PyArg_ParseTuple(args, "O", &context)) return NULL; - scripting_context = PyCObject_AsVoidPtr(context); + scripting_context = _PyCapsule_GetPointer(context, NULL); retval = common_pc(scripting_context); return Py_BuildValue("i", retval); @@ -50,7 +60,7 @@ static PyObject *perf_trace_context_common_flags(PyObject *obj, if (!PyArg_ParseTuple(args, "O", &context)) return NULL; - scripting_context = PyCObject_AsVoidPtr(context); + scripting_context = _PyCapsule_GetPointer(context, NULL); retval = common_flags(scripting_context); return Py_BuildValue("i", retval); @@ -66,7 +76,7 @@ static PyObject *perf_trace_context_common_lock_depth(PyObject *obj, if (!PyArg_ParseTuple(args, "O", &context)) return NULL; - scripting_context = PyCObject_AsVoidPtr(context); + scripting_context = _PyCapsule_GetPointer(context, NULL); retval = common_lock_depth(scripting_context); return Py_BuildValue("i", retval); @@ -82,7 +92,25 @@ static PyMethodDef ContextMethods[] = { { NULL, NULL, 0, NULL} }; +#if PY_MAJOR_VERSION < 3 PyMODINIT_FUNC initperf_trace_context(void) { (void) Py_InitModule("perf_trace_context", ContextMethods); } +#else +PyMODINIT_FUNC PyInit_perf_trace_context(void) +{ + static struct PyModuleDef moduledef = { + PyModuleDef_HEAD_INIT, + "perf_trace_context", /* m_name */ + "", /* m_doc */ + -1, /* m_size */ + ContextMethods, /* m_methods */ + NULL, /* m_reload */ + NULL, /* m_traverse */ + NULL, /* m_clear */ + NULL, /* m_free */ + }; + return PyModule_Create(&moduledef); +} +#endif diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py index 38dfb720fb6f..54ace2f6bc36 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py @@ -31,10 +31,8 @@ def flag_str(event_name, field_name, value): string = "" if flag_fields[event_name][field_name]: - print_delim = 0 - keys = flag_fields[event_name][field_name]['values'].keys() - keys.sort() - for idx in keys: + print_delim = 0 + for idx in sorted(flag_fields[event_name][field_name]['values']): if not value and not idx: string += flag_fields[event_name][field_name]['values'][idx] break @@ -51,14 +49,12 @@ def symbol_str(event_name, field_name, value): string = "" if symbolic_fields[event_name][field_name]: - keys = symbolic_fields[event_name][field_name]['values'].keys() - keys.sort() - for idx in keys: + for idx in sorted(symbolic_fields[event_name][field_name]['values']): if not value and not idx: - string = symbolic_fields[event_name][field_name]['values'][idx] + string = symbolic_fields[event_name][field_name]['values'][idx] break - if (value == idx): - string = symbolic_fields[event_name][field_name]['values'][idx] + if (value == idx): + string = symbolic_fields[event_name][field_name]['values'][idx] break return string @@ -74,19 +70,17 @@ def trace_flag_str(value): string = "" print_delim = 0 - keys = trace_flags.keys() - - for idx in keys: - if not value and not idx: - string += "NONE" - break - - if idx and (value & idx) == idx: - if print_delim: - string += " | "; - string += trace_flags[idx] - print_delim = 1 - value &= ~idx + for idx in trace_flags: + if not value and not idx: + string += "NONE" + break + + if idx and (value & idx) == idx: + if print_delim: + string += " | "; + string += trace_flags[idx] + print_delim = 1 + value &= ~idx return string diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py index 81a56cd2b3c1..21a7a1298094 100755 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py @@ -8,6 +8,7 @@ # PerfEvent is the base class for all perf event sample, PebsEvent # is a HW base Intel x86 PEBS event, and user could add more SW/HW # event classes based on requirements. +from __future__ import print_function import struct @@ -44,7 +45,8 @@ class PerfEvent(object): PerfEvent.event_num += 1 def show(self): - print "PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % (self.name, self.symbol, self.comm, self.dso) + print("PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % + (self.name, self.symbol, self.comm, self.dso)) # # Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py index fdd92f699055..cac7b2542ee8 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py @@ -11,7 +11,7 @@ try: import wx except ImportError: - raise ImportError, "You need to install the wxpython lib for this script" + raise ImportError("You need to install the wxpython lib for this script") class RootFrame(wx.Frame): diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py index f6c84966e4f8..7384dcb628c4 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py @@ -5,6 +5,7 @@ # This software may be distributed under the terms of the GNU General # Public License ("GPL") version 2 as published by the Free Software # Foundation. +from __future__ import print_function import errno, os @@ -33,7 +34,7 @@ def nsecs_str(nsecs): return str def add_stats(dict, key, value): - if not dict.has_key(key): + if key not in dict: dict[key] = (value, value, value, 1) else: min, max, avg, count = dict[key] @@ -72,10 +73,10 @@ try: except: if not audit_package_warned: audit_package_warned = True - print "Install the audit-libs-python package to get syscall names.\n" \ - "For example:\n # apt-get install python-audit (Ubuntu)" \ - "\n # yum install audit-libs-python (Fedora)" \ - "\n etc.\n" + print("Install the audit-libs-python package to get syscall names.\n" + "For example:\n # apt-get install python-audit (Ubuntu)" + "\n # yum install audit-libs-python (Fedora)" + "\n etc.\n") def syscall_name(id): try: diff --git a/tools/perf/scripts/python/bin/powerpc-hcalls-record b/tools/perf/scripts/python/bin/powerpc-hcalls-record new file mode 100644 index 000000000000..b7402aa9147d --- /dev/null +++ b/tools/perf/scripts/python/bin/powerpc-hcalls-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -e "{powerpc:hcall_entry,powerpc:hcall_exit}" $@ diff --git a/tools/perf/scripts/python/bin/powerpc-hcalls-report b/tools/perf/scripts/python/bin/powerpc-hcalls-report new file mode 100644 index 000000000000..dd32ad7465f6 --- /dev/null +++ b/tools/perf/scripts/python/bin/powerpc-hcalls-report @@ -0,0 +1,2 @@ +#!/bin/bash +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/powerpc-hcalls.py diff --git a/tools/perf/scripts/python/powerpc-hcalls.py b/tools/perf/scripts/python/powerpc-hcalls.py new file mode 100644 index 000000000000..00e0e7476e55 --- /dev/null +++ b/tools/perf/scripts/python/powerpc-hcalls.py @@ -0,0 +1,200 @@ +# SPDX-License-Identifier: GPL-2.0+ +# +# Copyright (C) 2018 Ravi Bangoria, IBM Corporation +# +# Hypervisor call statisics + +import os +import sys + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from Util import * + +# output: { +# opcode: { +# 'min': minimum time nsec +# 'max': maximum time nsec +# 'time': average time nsec +# 'cnt': counter +# } ... +# } +output = {} + +# d_enter: { +# cpu: { +# opcode: nsec +# } ... +# } +d_enter = {} + +hcall_table = { + 4: 'H_REMOVE', + 8: 'H_ENTER', + 12: 'H_READ', + 16: 'H_CLEAR_MOD', + 20: 'H_CLEAR_REF', + 24: 'H_PROTECT', + 28: 'H_GET_TCE', + 32: 'H_PUT_TCE', + 36: 'H_SET_SPRG0', + 40: 'H_SET_DABR', + 44: 'H_PAGE_INIT', + 48: 'H_SET_ASR', + 52: 'H_ASR_ON', + 56: 'H_ASR_OFF', + 60: 'H_LOGICAL_CI_LOAD', + 64: 'H_LOGICAL_CI_STORE', + 68: 'H_LOGICAL_CACHE_LOAD', + 72: 'H_LOGICAL_CACHE_STORE', + 76: 'H_LOGICAL_ICBI', + 80: 'H_LOGICAL_DCBF', + 84: 'H_GET_TERM_CHAR', + 88: 'H_PUT_TERM_CHAR', + 92: 'H_REAL_TO_LOGICAL', + 96: 'H_HYPERVISOR_DATA', + 100: 'H_EOI', + 104: 'H_CPPR', + 108: 'H_IPI', + 112: 'H_IPOLL', + 116: 'H_XIRR', + 120: 'H_MIGRATE_DMA', + 124: 'H_PERFMON', + 220: 'H_REGISTER_VPA', + 224: 'H_CEDE', + 228: 'H_CONFER', + 232: 'H_PROD', + 236: 'H_GET_PPP', + 240: 'H_SET_PPP', + 244: 'H_PURR', + 248: 'H_PIC', + 252: 'H_REG_CRQ', + 256: 'H_FREE_CRQ', + 260: 'H_VIO_SIGNAL', + 264: 'H_SEND_CRQ', + 272: 'H_COPY_RDMA', + 276: 'H_REGISTER_LOGICAL_LAN', + 280: 'H_FREE_LOGICAL_LAN', + 284: 'H_ADD_LOGICAL_LAN_BUFFER', + 288: 'H_SEND_LOGICAL_LAN', + 292: 'H_BULK_REMOVE', + 304: 'H_MULTICAST_CTRL', + 308: 'H_SET_XDABR', + 312: 'H_STUFF_TCE', + 316: 'H_PUT_TCE_INDIRECT', + 332: 'H_CHANGE_LOGICAL_LAN_MAC', + 336: 'H_VTERM_PARTNER_INFO', + 340: 'H_REGISTER_VTERM', + 344: 'H_FREE_VTERM', + 348: 'H_RESET_EVENTS', + 352: 'H_ALLOC_RESOURCE', + 356: 'H_FREE_RESOURCE', + 360: 'H_MODIFY_QP', + 364: 'H_QUERY_QP', + 368: 'H_REREGISTER_PMR', + 372: 'H_REGISTER_SMR', + 376: 'H_QUERY_MR', + 380: 'H_QUERY_MW', + 384: 'H_QUERY_HCA', + 388: 'H_QUERY_PORT', + 392: 'H_MODIFY_PORT', + 396: 'H_DEFINE_AQP1', + 400: 'H_GET_TRACE_BUFFER', + 404: 'H_DEFINE_AQP0', + 408: 'H_RESIZE_MR', + 412: 'H_ATTACH_MCQP', + 416: 'H_DETACH_MCQP', + 420: 'H_CREATE_RPT', + 424: 'H_REMOVE_RPT', + 428: 'H_REGISTER_RPAGES', + 432: 'H_DISABLE_AND_GETC', + 436: 'H_ERROR_DATA', + 440: 'H_GET_HCA_INFO', + 444: 'H_GET_PERF_COUNT', + 448: 'H_MANAGE_TRACE', + 468: 'H_FREE_LOGICAL_LAN_BUFFER', + 472: 'H_POLL_PENDING', + 484: 'H_QUERY_INT_STATE', + 580: 'H_ILLAN_ATTRIBUTES', + 592: 'H_MODIFY_HEA_QP', + 596: 'H_QUERY_HEA_QP', + 600: 'H_QUERY_HEA', + 604: 'H_QUERY_HEA_PORT', + 608: 'H_MODIFY_HEA_PORT', + 612: 'H_REG_BCMC', + 616: 'H_DEREG_BCMC', + 620: 'H_REGISTER_HEA_RPAGES', + 624: 'H_DISABLE_AND_GET_HEA', + 628: 'H_GET_HEA_INFO', + 632: 'H_ALLOC_HEA_RESOURCE', + 644: 'H_ADD_CONN', + 648: 'H_DEL_CONN', + 664: 'H_JOIN', + 676: 'H_VASI_STATE', + 688: 'H_ENABLE_CRQ', + 696: 'H_GET_EM_PARMS', + 720: 'H_SET_MPP', + 724: 'H_GET_MPP', + 748: 'H_HOME_NODE_ASSOCIATIVITY', + 756: 'H_BEST_ENERGY', + 764: 'H_XIRR_X', + 768: 'H_RANDOM', + 772: 'H_COP', + 788: 'H_GET_MPP_X', + 796: 'H_SET_MODE', + 61440: 'H_RTAS', +} + +def hcall_table_lookup(opcode): + if (hcall_table.has_key(opcode)): + return hcall_table[opcode] + else: + return opcode + +print_ptrn = '%-28s%10s%10s%10s%10s' + +def trace_end(): + print print_ptrn % ('hcall', 'count', 'min(ns)', 'max(ns)', 'avg(ns)') + print '-' * 68 + for opcode in output: + h_name = hcall_table_lookup(opcode) + time = output[opcode]['time'] + cnt = output[opcode]['cnt'] + min_t = output[opcode]['min'] + max_t = output[opcode]['max'] + + print print_ptrn % (h_name, cnt, min_t, max_t, time/cnt) + +def powerpc__hcall_exit(name, context, cpu, sec, nsec, pid, comm, callchain, + opcode, retval): + if (d_enter.has_key(cpu) and d_enter[cpu].has_key(opcode)): + diff = nsecs(sec, nsec) - d_enter[cpu][opcode] + + if (output.has_key(opcode)): + output[opcode]['time'] += diff + output[opcode]['cnt'] += 1 + if (output[opcode]['min'] > diff): + output[opcode]['min'] = diff + if (output[opcode]['max'] < diff): + output[opcode]['max'] = diff + else: + output[opcode] = { + 'time': diff, + 'cnt': 1, + 'min': diff, + 'max': diff, + } + + del d_enter[cpu][opcode] +# else: +# print "Can't find matching hcall_enter event. Ignoring sample" + +def powerpc__hcall_entry(event_name, context, cpu, sec, nsec, pid, comm, + callchain, opcode): + if (d_enter.has_key(cpu)): + d_enter[cpu][opcode] = nsecs(sec, nsec) + else: + d_enter[cpu] = {opcode: nsecs(sec, nsec)} diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py index de66cb3b72c9..3473e7f66081 100644 --- a/tools/perf/scripts/python/sched-migration.py +++ b/tools/perf/scripts/python/sched-migration.py @@ -9,13 +9,17 @@ # This software is distributed under the terms of the GNU General # Public License ("GPL") version 2 as published by the Free Software # Foundation. - +from __future__ import print_function import os import sys from collections import defaultdict -from UserList import UserList +try: + from UserList import UserList +except ImportError: + # Python 3: UserList moved to the collections package + from collections import UserList sys.path.append(os.environ['PERF_EXEC_PATH'] + \ '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') @@ -300,7 +304,7 @@ class TimeSliceList(UserList): if i == -1: return - for i in xrange(i, len(self.data)): + for i in range(i, len(self.data)): timeslice = self.data[i] if timeslice.start > end: return @@ -336,8 +340,8 @@ class SchedEventProxy: on_cpu_task = self.current_tsk[headers.cpu] if on_cpu_task != -1 and on_cpu_task != prev_pid: - print "Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \ - (headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid) + print("Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \ + headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid) threads[prev_pid] = prev_comm threads[next_pid] = next_comm diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 87bf3edb037c..6c108fa79ae3 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -20,6 +20,7 @@ perf-y += hists_cumulate.o perf-y += python-use.o perf-y += bp_signal.o perf-y += bp_signal_overflow.o +perf-y += bp_account.o perf-y += task-exit.o perf-y += sw-clock.o perf-y += mmap-thread-lookup.o @@ -47,6 +48,7 @@ perf-y += bitmap.o perf-y += perf-hooks.o perf-y += clang.o perf-y += unit_number__scnprintf.o +perf-y += mem2node.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 97f64ad7fa08..05dfe11c2f9e 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -170,8 +170,8 @@ static int run_dir(const char *d, const char *perf) if (verbose > 0) vcnt++; - snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s", - d, d, perf, vcnt, v); + scnprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s", + d, d, perf, vcnt, v); return system(cmd) ? TEST_FAIL : TEST_OK; } diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index f906b793196f..8a33ca4f9e1f 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -35,3 +35,6 @@ inherit=0 # sampling disabled sample_freq=0 sample_period=0 +freq=0 +write_backward=0 +sample_id_all=0 diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index e0b1b414d466..6d598cc071ae 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -33,10 +33,9 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count, for (i = 0; i < evlist->nr_mmaps; i++) { struct perf_mmap *map = &evlist->overwrite_mmap[i]; union perf_event *event; - u64 start, end; - perf_mmap__read_init(map, true, &start, &end); - while ((event = perf_mmap__read_event(map, true, &start, end)) != NULL) { + perf_mmap__read_init(map); + while ((event = perf_mmap__read_event(map)) != NULL) { const u32 type = event->header.type; switch (type) { diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c index 47bedf25ba69..96e7fc1ad3f9 100644 --- a/tools/perf/tests/bitmap.c +++ b/tools/perf/tests/bitmap.c @@ -16,8 +16,6 @@ static unsigned long *get_bitmap(const char *str, int nbits) bm = bitmap_alloc(nbits); if (map && bm) { - bitmap_zero(bm, nbits); - for (i = 0; i < map->nr; i++) set_bit(map->map[i], bm); } diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c new file mode 100644 index 000000000000..a20cbc445426 --- /dev/null +++ b/tools/perf/tests/bp_account.c @@ -0,0 +1,193 @@ +/* + * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select + * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu. + */ +#define __SANE_USERSPACE_TYPES__ + +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <string.h> +#include <sys/ioctl.h> +#include <time.h> +#include <fcntl.h> +#include <signal.h> +#include <sys/mman.h> +#include <linux/compiler.h> +#include <linux/hw_breakpoint.h> +#include <sys/ioctl.h> + +#include "tests.h" +#include "debug.h" +#include "perf.h" +#include "cloexec.h" + +volatile long the_var; + +static noinline int test_function(void) +{ + return 0; +} + +static int __event(bool is_x, void *addr, struct perf_event_attr *attr) +{ + int fd; + + memset(attr, 0, sizeof(struct perf_event_attr)); + attr->type = PERF_TYPE_BREAKPOINT; + attr->size = sizeof(struct perf_event_attr); + + attr->config = 0; + attr->bp_type = is_x ? HW_BREAKPOINT_X : HW_BREAKPOINT_W; + attr->bp_addr = (unsigned long) addr; + attr->bp_len = sizeof(long); + + attr->sample_period = 1; + attr->sample_type = PERF_SAMPLE_IP; + + attr->exclude_kernel = 1; + attr->exclude_hv = 1; + + fd = sys_perf_event_open(attr, -1, 0, -1, + perf_event_open_cloexec_flag()); + if (fd < 0) { + pr_debug("failed opening event %llx\n", attr->config); + return TEST_FAIL; + } + + return fd; +} + +static int wp_event(void *addr, struct perf_event_attr *attr) +{ + return __event(false, addr, attr); +} + +static int bp_event(void *addr, struct perf_event_attr *attr) +{ + return __event(true, addr, attr); +} + +static int bp_accounting(int wp_cnt, int share) +{ + struct perf_event_attr attr, attr_mod, attr_new; + int i, fd[wp_cnt], fd_wp, ret; + + for (i = 0; i < wp_cnt; i++) { + fd[i] = wp_event((void *)&the_var, &attr); + TEST_ASSERT_VAL("failed to create wp\n", fd[i] != -1); + pr_debug("wp %d created\n", i); + } + + attr_mod = attr; + attr_mod.bp_type = HW_BREAKPOINT_X; + attr_mod.bp_addr = (unsigned long) test_function; + + ret = ioctl(fd[0], PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &attr_mod); + TEST_ASSERT_VAL("failed to modify wp\n", ret == 0); + + pr_debug("wp 0 modified to bp\n"); + + if (!share) { + fd_wp = wp_event((void *)&the_var, &attr_new); + TEST_ASSERT_VAL("failed to create max wp\n", fd_wp != -1); + pr_debug("wp max created\n"); + } + + for (i = 0; i < wp_cnt; i++) + close(fd[i]); + + return 0; +} + +static int detect_cnt(bool is_x) +{ + struct perf_event_attr attr; + void *addr = is_x ? (void *)test_function : (void *)&the_var; + int fd[100], cnt = 0, i; + + while (1) { + if (cnt == 100) { + pr_debug("way too many debug registers, fix the test\n"); + return 0; + } + fd[cnt] = __event(is_x, addr, &attr); + + if (fd[cnt] < 0) + break; + cnt++; + } + + for (i = 0; i < cnt; i++) + close(fd[i]); + + return cnt; +} + +static int detect_ioctl(void) +{ + struct perf_event_attr attr; + int fd, ret = 1; + + fd = wp_event((void *) &the_var, &attr); + if (fd > 0) { + ret = ioctl(fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &attr); + close(fd); + } + + return ret ? 0 : 1; +} + +static int detect_share(int wp_cnt, int bp_cnt) +{ + struct perf_event_attr attr; + int i, fd[wp_cnt + bp_cnt], ret; + + for (i = 0; i < wp_cnt; i++) { + fd[i] = wp_event((void *)&the_var, &attr); + TEST_ASSERT_VAL("failed to create wp\n", fd[i] != -1); + } + + for (; i < (bp_cnt + wp_cnt); i++) { + fd[i] = bp_event((void *)test_function, &attr); + if (fd[i] == -1) + break; + } + + ret = i != (bp_cnt + wp_cnt); + + while (i--) + close(fd[i]); + + return ret; +} + +/* + * This test does following: + * - detects the number of watch/break-points, + * skip test if any is missing + * - detects PERF_EVENT_IOC_MODIFY_ATTRIBUTES ioctl, + * skip test if it's missing + * - detects if watchpoints and breakpoints share + * same slots + * - create all possible watchpoints on cpu 0 + * - change one of it to breakpoint + * - in case wp and bp do not share slots, + * we create another watchpoint to ensure + * the slot accounting is correct + */ +int test__bp_accounting(struct test *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); + + pr_debug("watchpoints count %d, breakpoints count %d, has_ioctl %d, share %d\n", + wp_cnt, bp_cnt, has_ioctl, share); + + if (!wp_cnt || !bp_cnt || !has_ioctl) + return TEST_SKIP; + + return bp_accounting(wp_cnt, share); +} diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c index e4123c1b0e88..1ca5106df5f1 100644 --- a/tools/perf/tests/bpf-script-example.c +++ b/tools/perf/tests/bpf-script-example.c @@ -31,7 +31,7 @@ struct bpf_map_def SEC("maps") flip_table = { .max_entries = 1, }; -SEC("func=SyS_epoll_pwait") +SEC("func=do_epoll_wait") int bpf_func__SyS_epoll_pwait(void *ctx) { int ind =0; diff --git a/tools/perf/tests/bpf-script-test-kbuild.c b/tools/perf/tests/bpf-script-test-kbuild.c index 3626924740d8..ff3ec8337f0a 100644 --- a/tools/perf/tests/bpf-script-test-kbuild.c +++ b/tools/perf/tests/bpf-script-test-kbuild.c @@ -9,7 +9,6 @@ #define SEC(NAME) __attribute__((section(NAME), used)) #include <uapi/linux/fs.h> -#include <uapi/asm/ptrace.h> SEC("func=vfs_llseek") int bpf_func__vfs_llseek(void *ctx) diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index e8399beca62b..79b54f8ddebf 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -176,13 +176,19 @@ static int do_test(struct bpf_object *obj, int (*func)(void), for (i = 0; i < evlist->nr_mmaps; i++) { union perf_event *event; + struct perf_mmap *md; - while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + md = &evlist->mmap[i]; + if (perf_mmap__read_init(md) < 0) + continue; + + while ((event = perf_mmap__read_event(md)) != NULL) { const u32 type = event->header.type; if (type == PERF_RECORD_SAMPLE) count ++; } + perf_mmap__read_done(md); } if (count != expect) { diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index fafa014240cd..d7a5e1b9aa6f 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -116,6 +116,11 @@ static struct test generic_tests[] = { .is_supported = test__bp_signal_is_supported, }, { + .desc = "Breakpoint accounting", + .func = test__bp_accounting, + .is_supported = test__bp_signal_is_supported, + }, + { .desc = "Number of exit events of a simple workload", .func = test__task_exit, }, @@ -271,6 +276,10 @@ static struct test generic_tests[] = { .func = test__unit_number__scnprint, }, { + .desc = "mem2node", + .func = test__mem2node, + }, + { .func = NULL, }, }; @@ -376,7 +385,7 @@ static int test_and_print(struct test *t, bool force_skip, int subtest) if (!t->subtest.get_nr) pr_debug("%s:", t->desc); else - pr_debug("%s subtest %d:", t->desc, subtest); + pr_debug("%s subtest %d:", t->desc, subtest + 1); switch (err) { case TEST_OK: @@ -413,7 +422,7 @@ static const char *shell_test__description(char *description, size_t size, #define for_each_shell_test(dir, base, ent) \ while ((ent = readdir(dir)) != NULL) \ - if (!is_directory(base, ent)) + if (!is_directory(base, ent) && ent->d_name[0] != '.') static const char *shell_tests__dir(char *path, size_t size) { @@ -645,6 +654,15 @@ static int perf_test__list(int argc, const char **argv) continue; pr_info("%2d: %s\n", i, t->desc); + + if (t->subtest.get_nr) { + int subn = t->subtest.get_nr(); + int subi; + + for (subi = 0; subi < subn; subi++) + pr_info("%2d:%1d: %s\n", i, subi + 1, + t->subtest.get_desc(subi)); + } } perf_test__list_shell(argc, argv, i); diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 3bf7b145b826..6b049f3f5cf4 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -232,18 +232,18 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, u64 objdump_addr; const char *objdump_name; char decomp_name[KMOD_DECOMP_LEN]; + bool decomp = false; int ret; pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr); - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al); - if (!al.map || !al.map->dso) { + if (!thread__find_map(thread, cpumode, addr, &al) || !al.map->dso) { if (cpumode == PERF_RECORD_MISC_HYPERVISOR) { pr_debug("Hypervisor address can not be resolved - skipping\n"); return 0; } - pr_debug("thread__find_addr_map failed\n"); + pr_debug("thread__find_map failed\n"); return -1; } @@ -306,6 +306,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, return -1; } + decomp = true; objdump_name = decomp_name; } @@ -313,7 +314,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, objdump_addr = map__rip_2objdump(al.map, al.addr); ret = read_via_objdump(objdump_name, objdump_addr, buf2, len); - if (dso__needs_decompress(al.map->dso)) + if (decomp) unlink(objdump_name); if (ret > 0) { @@ -409,15 +410,21 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist, struct state *state) { union perf_event *event; + struct perf_mmap *md; int i, ret; for (i = 0; i < evlist->nr_mmaps; i++) { - while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + md = &evlist->mmap[i]; + if (perf_mmap__read_init(md) < 0) + continue; + + while ((event = perf_mmap__read_event(md)) != NULL) { ret = process_event(machine, evlist, event, state); - perf_evlist__mmap_consume(evlist, i); + perf_mmap__consume(md); if (ret < 0) return ret; } + perf_mmap__read_done(md); } return 0; } @@ -482,6 +489,34 @@ static void fs_something(void) } } +static const char *do_determine_event(bool excl_kernel) +{ + const char *event = excl_kernel ? "cycles:u" : "cycles"; + +#ifdef __s390x__ + char cpuid[128], model[16], model_c[16], cpum_cf_v[16]; + unsigned int family; + int ret, cpum_cf_a; + + if (get_cpuid(cpuid, sizeof(cpuid))) + goto out_clocks; + ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%x", &family, model_c, + model, cpum_cf_v, &cpum_cf_a); + if (ret != 5) /* Not available */ + goto out_clocks; + if (excl_kernel && (cpum_cf_a & 4)) + return event; + if (!excl_kernel && (cpum_cf_a & 2)) + return event; + + /* Fall through: missing authorization */ +out_clocks: + event = excl_kernel ? "cpu-clock:u" : "cpu-clock"; + +#endif + return event; +} + static void do_something(void) { fs_something(); @@ -527,6 +562,7 @@ static int do_test_code_reading(bool try_kcore) pid = getpid(); machine = machine__new_host(); + machine->env = &perf_env; ret = machine__create_kernel_maps(machine); if (ret < 0) { @@ -592,10 +628,7 @@ static int do_test_code_reading(bool try_kcore) perf_evlist__set_maps(evlist, cpus, threads); - if (excl_kernel) - str = "cycles:u"; - else - str = "cycles"; + str = do_determine_event(excl_kernel); pr_debug("Parsing event '%s'\n", str); ret = parse_events(evlist, str, NULL); if (ret < 0) { diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 260418969120..2f008067d989 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -37,6 +37,19 @@ static int init_live_machine(struct machine *machine) mmap_handler, machine, true, 500); } +/* + * We need to keep these functions global, despite the + * fact that they are used only locally in this object, + * in order to keep them around even if the binary is + * stripped. If they are gone, the unwind check for + * symbol fails. + */ +int test_dwarf_unwind__thread(struct thread *thread); +int test_dwarf_unwind__compare(void *p1, void *p2); +int test_dwarf_unwind__krava_3(struct thread *thread); +int test_dwarf_unwind__krava_2(struct thread *thread); +int test_dwarf_unwind__krava_1(struct thread *thread); + #define MAX_STACK 8 static int unwind_entry(struct unwind_entry *entry, void *arg) @@ -45,12 +58,12 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) char *symbol = entry->sym ? entry->sym->name : NULL; static const char *funcs[MAX_STACK] = { "test__arch_unwind_sample", - "unwind_thread", - "compare", + "test_dwarf_unwind__thread", + "test_dwarf_unwind__compare", "bsearch", - "krava_3", - "krava_2", - "krava_1", + "test_dwarf_unwind__krava_3", + "test_dwarf_unwind__krava_2", + "test_dwarf_unwind__krava_1", "test__dwarf_unwind" }; /* @@ -77,7 +90,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return strcmp((const char *) symbol, funcs[idx]); } -static noinline int unwind_thread(struct thread *thread) +noinline int test_dwarf_unwind__thread(struct thread *thread) { struct perf_sample sample; unsigned long cnt = 0; @@ -108,7 +121,7 @@ static noinline int unwind_thread(struct thread *thread) static int global_unwind_retval = -INT_MAX; -static noinline int compare(void *p1, void *p2) +noinline int test_dwarf_unwind__compare(void *p1, void *p2) { /* Any possible value should be 'thread' */ struct thread *thread = *(struct thread **)p1; @@ -117,17 +130,17 @@ static noinline int compare(void *p1, void *p2) /* Call unwinder twice for both callchain orders. */ callchain_param.order = ORDER_CALLER; - global_unwind_retval = unwind_thread(thread); + global_unwind_retval = test_dwarf_unwind__thread(thread); if (!global_unwind_retval) { callchain_param.order = ORDER_CALLEE; - global_unwind_retval = unwind_thread(thread); + global_unwind_retval = test_dwarf_unwind__thread(thread); } } return p1 - p2; } -static noinline int krava_3(struct thread *thread) +noinline int test_dwarf_unwind__krava_3(struct thread *thread) { struct thread *array[2] = {thread, thread}; void *fp = &bsearch; @@ -141,18 +154,19 @@ static noinline int krava_3(struct thread *thread) size_t, int (*)(void *, void *)); _bsearch = fp; - _bsearch(array, &thread, 2, sizeof(struct thread **), compare); + _bsearch(array, &thread, 2, sizeof(struct thread **), + test_dwarf_unwind__compare); return global_unwind_retval; } -static noinline int krava_2(struct thread *thread) +noinline int test_dwarf_unwind__krava_2(struct thread *thread) { - return krava_3(thread); + return test_dwarf_unwind__krava_3(thread); } -static noinline int krava_1(struct thread *thread) +noinline int test_dwarf_unwind__krava_1(struct thread *thread) { - return krava_2(thread); + return test_dwarf_unwind__krava_2(thread); } int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused) @@ -189,7 +203,7 @@ int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unu goto out; } - err = krava_1(thread); + err = test_dwarf_unwind__krava_1(thread); thread__put(thread); out: diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c index f7c5b613d667..b889a28fd80b 100644 --- a/tools/perf/tests/hists_common.c +++ b/tools/perf/tests/hists_common.c @@ -131,20 +131,20 @@ struct machine *setup_fake_machine(struct machines *machines) goto out; /* emulate dso__load() */ - dso__set_loaded(dso, MAP__FUNCTION); + dso__set_loaded(dso); for (k = 0; k < fake_symbols[i].nr_syms; k++) { struct symbol *sym; struct fake_sym *fsym = &fake_symbols[i].syms[k]; sym = symbol__new(fsym->start, fsym->length, - STB_GLOBAL, fsym->name); + STB_GLOBAL, STT_FUNC, fsym->name); if (sym == NULL) { dso__put(dso); goto out; } - symbols__insert(&dso->symbols[MAP__FUNCTION], sym); + symbols__insert(&dso->symbols, sym); } dso__put(dso); diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index c46530918938..17c46f3e6f1e 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -27,18 +27,23 @@ static int find_comm(struct perf_evlist *evlist, const char *comm) { union perf_event *event; + struct perf_mmap *md; int i, found; found = 0; for (i = 0; i < evlist->nr_mmaps; i++) { - while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + md = &evlist->mmap[i]; + if (perf_mmap__read_init(md) < 0) + continue; + while ((event = perf_mmap__read_event(md)) != NULL) { if (event->header.type == PERF_RECORD_COMM && (pid_t)event->comm.pid == getpid() && (pid_t)event->comm.tid == getpid() && strcmp(event->comm.comm, comm) == 0) found += 1; - perf_evlist__mmap_consume(evlist, i); + perf_mmap__consume(md); } + perf_mmap__read_done(md); } return found; } diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index 8e57d46109de..0579a70bbbff 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -5,34 +5,28 @@ #include "dso.h" #include "debug.h" -static int test(const char *path, bool alloc_name, bool alloc_ext, - bool kmod, bool comp, const char *name, const char *ext) +static int test(const char *path, bool alloc_name, bool kmod, + int comp, const char *name) { struct kmod_path m; memset(&m, 0x0, sizeof(m)); TEST_ASSERT_VAL("kmod_path__parse", - !__kmod_path__parse(&m, path, alloc_name, alloc_ext)); + !__kmod_path__parse(&m, path, alloc_name)); - pr_debug("%s - alloc name %d, alloc ext %d, kmod %d, comp %d, name '%s', ext '%s'\n", - path, alloc_name, alloc_ext, m.kmod, m.comp, m.name, m.ext); + pr_debug("%s - alloc name %d, kmod %d, comp %d, name '%s'\n", + path, alloc_name, m.kmod, m.comp, m.name); TEST_ASSERT_VAL("wrong kmod", m.kmod == kmod); TEST_ASSERT_VAL("wrong comp", m.comp == comp); - if (ext) - TEST_ASSERT_VAL("wrong ext", m.ext && !strcmp(ext, m.ext)); - else - TEST_ASSERT_VAL("wrong ext", !m.ext); - if (name) TEST_ASSERT_VAL("wrong name", m.name && !strcmp(name, m.name)); else TEST_ASSERT_VAL("wrong name", !m.name); free(m.name); - free(m.ext); return 0; } @@ -45,102 +39,118 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect) return 0; } -#define T(path, an, ae, k, c, n, e) \ - TEST_ASSERT_VAL("failed", !test(path, an, ae, k, c, n, e)) +#define T(path, an, k, c, n) \ + TEST_ASSERT_VAL("failed", !test(path, an, k, c, n)) #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) { - /* path alloc_name alloc_ext kmod comp name ext */ - T("/xxxx/xxxx/x-x.ko", true , true , true, false, "[x_x]", NULL); - T("/xxxx/xxxx/x-x.ko", false , true , true, false, NULL , NULL); - T("/xxxx/xxxx/x-x.ko", true , false , true, false, "[x_x]", NULL); - T("/xxxx/xxxx/x-x.ko", false , false , true, false, NULL , NULL); + /* path alloc_name kmod comp name */ + T("/xxxx/xxxx/x-x.ko", true , true, 0 , "[x_x]"); + T("/xxxx/xxxx/x-x.ko", false , true, 0 , NULL ); + T("/xxxx/xxxx/x-x.ko", true , true, 0 , "[x_x]"); + T("/xxxx/xxxx/x-x.ko", false , true, 0 , NULL ); M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_KERNEL, true); M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_USER, false); #ifdef HAVE_ZLIB_SUPPORT - /* path alloc_name alloc_ext kmod comp name ext */ - T("/xxxx/xxxx/x.ko.gz", true , true , true, true, "[x]", "gz"); - T("/xxxx/xxxx/x.ko.gz", false , true , true, true, NULL , "gz"); - T("/xxxx/xxxx/x.ko.gz", true , false , true, true, "[x]", NULL); - T("/xxxx/xxxx/x.ko.gz", false , false , true, true, NULL , NULL); + /* path alloc_name kmod comp name */ + T("/xxxx/xxxx/x.ko.gz", true , true, 1 , "[x]"); + T("/xxxx/xxxx/x.ko.gz", false , true, 1 , NULL ); + T("/xxxx/xxxx/x.ko.gz", true , true, 1 , "[x]"); + T("/xxxx/xxxx/x.ko.gz", false , true, 1 , NULL ); M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_KERNEL, true); M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("/xxxx/xxxx/x.gz", true , true , false, true, "x.gz" ,"gz"); - T("/xxxx/xxxx/x.gz", false , true , false, true, NULL ,"gz"); - T("/xxxx/xxxx/x.gz", true , false , false, true, "x.gz" , NULL); - T("/xxxx/xxxx/x.gz", false , false , false, true, NULL , NULL); + /* path alloc_name kmod comp name */ + T("/xxxx/xxxx/x.gz", true , false, 1 , "x.gz"); + T("/xxxx/xxxx/x.gz", false , false, 1 , NULL ); + T("/xxxx/xxxx/x.gz", true , false, 1 , "x.gz"); + T("/xxxx/xxxx/x.gz", false , false, 1 , NULL ); M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_KERNEL, false); M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("x.gz", true , true , false, true, "x.gz", "gz"); - T("x.gz", false , true , false, true, NULL , "gz"); - T("x.gz", true , false , false, true, "x.gz", NULL); - T("x.gz", false , false , false, true, NULL , NULL); + /* path alloc_name kmod comp name */ + T("x.gz", true , false, 1 , "x.gz"); + T("x.gz", false , false, 1 , NULL ); + T("x.gz", true , false, 1 , "x.gz"); + T("x.gz", false , false, 1 , NULL ); M("x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); M("x.gz", PERF_RECORD_MISC_KERNEL, false); M("x.gz", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("x.ko.gz", true , true , true, true, "[x]", "gz"); - T("x.ko.gz", false , true , true, true, NULL , "gz"); - T("x.ko.gz", true , false , true, true, "[x]", NULL); - T("x.ko.gz", false , false , true, true, NULL , NULL); + /* path alloc_name kmod comp name */ + T("x.ko.gz", true , true, 1 , "[x]"); + T("x.ko.gz", false , true, 1 , NULL ); + T("x.ko.gz", true , true, 1 , "[x]"); + T("x.ko.gz", false , true, 1 , NULL ); M("x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("x.ko.gz", PERF_RECORD_MISC_KERNEL, true); M("x.ko.gz", PERF_RECORD_MISC_USER, false); #endif - /* path alloc_name alloc_ext kmod comp name ext */ - T("[test_module]", true , true , true, false, "[test_module]", NULL); - T("[test_module]", false , true , true, false, NULL , NULL); - T("[test_module]", true , false , true, false, "[test_module]", NULL); - T("[test_module]", false , false , true, false, NULL , NULL); + /* path alloc_name kmod comp name */ + T("[test_module]", true , true, false, "[test_module]"); + T("[test_module]", false , true, false, NULL ); + T("[test_module]", true , true, false, "[test_module]"); + T("[test_module]", false , true, false, NULL ); M("[test_module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("[test_module]", PERF_RECORD_MISC_KERNEL, true); M("[test_module]", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("[test.module]", true , true , true, false, "[test.module]", NULL); - T("[test.module]", false , true , true, false, NULL , NULL); - T("[test.module]", true , false , true, false, "[test.module]", NULL); - T("[test.module]", false , false , true, false, NULL , NULL); + /* path alloc_name kmod comp name */ + T("[test.module]", true , true, false, "[test.module]"); + T("[test.module]", false , true, false, NULL ); + T("[test.module]", true , true, false, "[test.module]"); + T("[test.module]", false , true, false, NULL ); M("[test.module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("[test.module]", PERF_RECORD_MISC_KERNEL, true); M("[test.module]", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("[vdso]", true , true , false, false, "[vdso]", NULL); - T("[vdso]", false , true , false, false, NULL , NULL); - T("[vdso]", true , false , false, false, "[vdso]", NULL); - T("[vdso]", false , false , false, false, NULL , NULL); + /* path alloc_name kmod comp name */ + T("[vdso]", true , false, false, "[vdso]"); + T("[vdso]", false , false, false, NULL ); + T("[vdso]", true , false, false, "[vdso]"); + T("[vdso]", false , false, false, NULL ); M("[vdso]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); M("[vdso]", PERF_RECORD_MISC_KERNEL, false); M("[vdso]", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("[vsyscall]", true , true , false, false, "[vsyscall]", NULL); - T("[vsyscall]", false , true , false, false, NULL , NULL); - T("[vsyscall]", true , false , false, false, "[vsyscall]", NULL); - T("[vsyscall]", false , false , false, false, NULL , NULL); + T("[vdso32]", true , false, false, "[vdso32]"); + T("[vdso32]", false , false, false, NULL ); + T("[vdso32]", true , false, false, "[vdso32]"); + T("[vdso32]", false , false, false, NULL ); + M("[vdso32]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); + M("[vdso32]", PERF_RECORD_MISC_KERNEL, false); + M("[vdso32]", PERF_RECORD_MISC_USER, false); + + T("[vdsox32]", true , false, false, "[vdsox32]"); + T("[vdsox32]", false , false, false, NULL ); + T("[vdsox32]", true , false, false, "[vdsox32]"); + T("[vdsox32]", false , false, false, NULL ); + M("[vdsox32]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); + M("[vdsox32]", PERF_RECORD_MISC_KERNEL, false); + M("[vdsox32]", PERF_RECORD_MISC_USER, false); + + /* path alloc_name kmod comp name */ + T("[vsyscall]", true , false, false, "[vsyscall]"); + T("[vsyscall]", false , false, false, NULL ); + T("[vsyscall]", true , false, false, "[vsyscall]"); + T("[vsyscall]", false , false, false, NULL ); M("[vsyscall]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); M("[vsyscall]", PERF_RECORD_MISC_KERNEL, false); M("[vsyscall]", PERF_RECORD_MISC_USER, false); - /* path alloc_name alloc_ext kmod comp name ext */ - T("[kernel.kallsyms]", true , true , false, false, "[kernel.kallsyms]", NULL); - T("[kernel.kallsyms]", false , true , false, false, NULL , NULL); - T("[kernel.kallsyms]", true , false , false, false, "[kernel.kallsyms]", NULL); - T("[kernel.kallsyms]", false , false , false, false, NULL , NULL); + /* path alloc_name kmod comp name */ + T("[kernel.kallsyms]", true , false, false, "[kernel.kallsyms]"); + T("[kernel.kallsyms]", false , false, false, NULL ); + T("[kernel.kallsyms]", true , false, false, "[kernel.kallsyms]"); + T("[kernel.kallsyms]", false , false, false, NULL ); M("[kernel.kallsyms]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false); M("[kernel.kallsyms]", PERF_RECORD_MISC_KERNEL, false); M("[kernel.kallsyms]", PERF_RECORD_MISC_USER, false); diff --git a/tools/perf/tests/mem.c b/tools/perf/tests/mem.c index 21952e1e6e6d..0f82ee9fd3f7 100644 --- a/tools/perf/tests/mem.c +++ b/tools/perf/tests/mem.c @@ -16,7 +16,7 @@ static int check(union perf_mem_data_src data_src, n = perf_mem__snp_scnprintf(out, sizeof out, &mi); n += perf_mem__lvl_scnprintf(out + n, sizeof out - n, &mi); - snprintf(failure, sizeof failure, "unexpected %s", out); + scnprintf(failure, sizeof failure, "unexpected %s", out); TEST_ASSERT_VAL(failure, !strcmp(string, out)); return 0; } diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c new file mode 100644 index 000000000000..9e9e4d37cc77 --- /dev/null +++ b/tools/perf/tests/mem2node.c @@ -0,0 +1,73 @@ +#include <linux/compiler.h> +#include <linux/bitmap.h> +#include "cpumap.h" +#include "mem2node.h" +#include "tests.h" + +static struct node { + int node; + const char *map; +} test_nodes[] = { + { .node = 0, .map = "0" }, + { .node = 1, .map = "1-2" }, + { .node = 3, .map = "5-7,9" }, +}; + +#define T TEST_ASSERT_VAL + +static unsigned long *get_bitmap(const char *str, int nbits) +{ + struct cpu_map *map = cpu_map__new(str); + unsigned long *bm = NULL; + int i; + + bm = bitmap_alloc(nbits); + + if (map && bm) { + for (i = 0; i < map->nr; i++) { + set_bit(map->map[i], bm); + } + } + + if (map) + cpu_map__put(map); + else + free(bm); + + return bm && map ? bm : NULL; +} + +int test__mem2node(struct test *t __maybe_unused, int subtest __maybe_unused) +{ + struct mem2node map; + struct memory_node nodes[3]; + struct perf_env env = { + .memory_nodes = (struct memory_node *) &nodes[0], + .nr_memory_nodes = ARRAY_SIZE(nodes), + .memory_bsize = 0x100, + }; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(nodes); i++) { + nodes[i].node = test_nodes[i].node; + nodes[i].size = 10; + + T("failed: alloc bitmap", + (nodes[i].set = get_bitmap(test_nodes[i].map, 10))); + } + + T("failed: mem2node__init", !mem2node__init(&map, &env)); + T("failed: mem2node__node", 0 == mem2node__node(&map, 0x50)); + T("failed: mem2node__node", 1 == mem2node__node(&map, 0x100)); + T("failed: mem2node__node", 1 == mem2node__node(&map, 0x250)); + T("failed: mem2node__node", 3 == mem2node__node(&map, 0x500)); + T("failed: mem2node__node", 3 == mem2node__node(&map, 0x650)); + T("failed: mem2node__node", -1 == mem2node__node(&map, 0x450)); + T("failed: mem2node__node", -1 == mem2node__node(&map, 0x1050)); + + for (i = 0; i < ARRAY_SIZE(nodes); i++) + free(nodes[i].set); + + mem2node__exit(&map); + return 0; +} diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index c0e971da965c..0919b0793e5b 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -38,6 +38,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse expected_nr_events[nsyscalls], i, j; struct perf_evsel *evsels[nsyscalls], *evsel; char sbuf[STRERR_BUFSIZE]; + struct perf_mmap *md; threads = thread_map__new(-1, getpid(), UINT_MAX); if (threads == NULL) { @@ -74,7 +75,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]); evsels[i] = perf_evsel__newtp("syscalls", name); if (IS_ERR(evsels[i])) { - pr_debug("perf_evsel__new\n"); + pr_debug("perf_evsel__new(%s)\n", name); goto out_delete_evlist; } @@ -106,7 +107,11 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse ++foo; } - while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { + md = &evlist->mmap[0]; + if (perf_mmap__read_init(md) < 0) + goto out_init; + + while ((event = perf_mmap__read_event(md)) != NULL) { struct perf_sample sample; if (event->header.type != PERF_RECORD_SAMPLE) { @@ -129,9 +134,11 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse goto out_delete_evlist; } nr_events[evsel->idx]++; - perf_evlist__mmap_consume(evlist, 0); + perf_mmap__consume(md); } + perf_mmap__read_done(md); +out_init: err = 0; evlist__for_each_entry(evlist, evsel) { if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) { diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 868d82b501f4..b1af2499a3c9 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -188,9 +188,8 @@ static int mmap_events(synth_cb synth) pr_debug("looking for map %p\n", td->map); - thread__find_addr_map(thread, - PERF_RECORD_MISC_USER, MAP__FUNCTION, - (unsigned long) (td->map + 1), &al); + thread__find_map(thread, PERF_RECORD_MISC_USER, + (unsigned long) (td->map + 1), &al); thread__put(thread); @@ -218,7 +217,7 @@ static int mmap_events(synth_cb synth) * perf_event__synthesize_threads (global) * * We test we can find all memory maps via: - * thread__find_addr_map + * thread__find_map * * by using all thread objects. */ diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index 43519267b93b..344dc3ac2469 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -86,8 +86,13 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest for (i = 0; i < evlist->nr_mmaps; i++) { union perf_event *event; + struct perf_mmap *md; - while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + md = &evlist->mmap[i]; + if (perf_mmap__read_init(md) < 0) + continue; + + while ((event = perf_mmap__read_event(md)) != NULL) { const u32 type = event->header.type; int tp_flags; struct perf_sample sample; @@ -95,7 +100,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest ++nr_events; if (type != PERF_RECORD_SAMPLE) { - perf_evlist__mmap_consume(evlist, i); + perf_mmap__consume(md); continue; } @@ -115,6 +120,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest goto out_ok; } + perf_mmap__read_done(md); } if (nr_events == before) diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 18b06444f230..3b97ac018d5a 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -499,7 +499,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct perf_evlist *evlis * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", 0 == evsel->attr.sample_period); - TEST_ASSERT_VAL("wrong callgraph", !(PERF_SAMPLE_CALLCHAIN & evsel->attr.sample_type)); + TEST_ASSERT_VAL("wrong callgraph", !evsel__has_callchain(evsel)); TEST_ASSERT_VAL("wrong time", !(PERF_SAMPLE_TIME & evsel->attr.sample_type)); /* cpu/config=2,call-graph=no,time=0,period=2000/ */ @@ -512,7 +512,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct perf_evlist *evlis * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", 0 == evsel->attr.sample_period); - TEST_ASSERT_VAL("wrong callgraph", !(PERF_SAMPLE_CALLCHAIN & evsel->attr.sample_type)); + TEST_ASSERT_VAL("wrong callgraph", !evsel__has_callchain(evsel)); TEST_ASSERT_VAL("wrong time", !(PERF_SAMPLE_TIME & evsel->attr.sample_type)); return 0; @@ -1309,18 +1309,39 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist) return 0; } +static bool test__intel_pt_valid(void) +{ + return !!perf_pmu__find("intel_pt"); +} + +static int test__intel_pt(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "intel_pt//u") == 0); + return 0; +} + +static int test__checkevent_complex_name(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0); + return 0; +} + static int count_tracepoints(void) { struct dirent *events_ent; DIR *events_dir; int cnt = 0; - events_dir = opendir(tracing_events_path); + events_dir = tracing_events__opendir(); TEST_ASSERT_VAL("Can't open events dir", events_dir); while ((events_ent = readdir(events_dir))) { - char sys_path[PATH_MAX]; + char *sys_path; struct dirent *sys_ent; DIR *sys_dir; @@ -1331,8 +1352,8 @@ static int count_tracepoints(void) || !strcmp(events_ent->d_name, "header_page")) continue; - scnprintf(sys_path, PATH_MAX, "%s/%s", - tracing_events_path, events_ent->d_name); + sys_path = get_events_file(events_ent->d_name); + TEST_ASSERT_VAL("Can't get sys path", sys_path); sys_dir = opendir(sys_path); TEST_ASSERT_VAL("Can't open sys dir", sys_dir); @@ -1348,6 +1369,7 @@ static int count_tracepoints(void) } closedir(sys_dir); + put_events_file(sys_path); } closedir(events_dir); @@ -1366,6 +1388,7 @@ struct evlist_test { const char *name; __u32 type; const int id; + bool (*valid)(void); int (*check)(struct perf_evlist *evlist); }; @@ -1637,6 +1660,17 @@ static struct evlist_test test__events[] = { .check = test__checkevent_config_cache, .id = 51, }, + { + .name = "intel_pt//u", + .valid = test__intel_pt_valid, + .check = test__intel_pt, + .id = 52, + }, + { + .name = "cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk", + .check = test__checkevent_complex_name, + .id = 53 + } }; static struct evlist_test test__events_pmu[] = { @@ -1655,6 +1689,11 @@ static struct evlist_test test__events_pmu[] = { .check = test__checkevent_pmu_partial_time_callgraph, .id = 2, }, + { + .name = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp", + .check = test__checkevent_complex_name, + .id = 3, + } }; struct terms_test { @@ -1672,17 +1711,24 @@ static struct terms_test test__terms[] = { static int test_event(struct evlist_test *e) { + struct parse_events_error err = { .idx = 0, }; struct perf_evlist *evlist; int ret; + if (e->valid && !e->valid()) { + pr_debug("... SKIP"); + return 0; + } + evlist = perf_evlist__new(); if (evlist == NULL) return -ENOMEM; - ret = parse_events(evlist, e->name, NULL); + ret = parse_events(evlist, e->name, &err); if (ret) { - pr_debug("failed to parse event '%s', err %d\n", - e->name, 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); } else { ret = e->check(evlist); } @@ -1700,10 +1746,11 @@ static int test_events(struct evlist_test *events, unsigned cnt) for (i = 0; i < cnt; i++) { struct evlist_test *e = &events[i]; - pr_debug("running test %d '%s'\n", e->id, e->name); + pr_debug("running test %d '%s'", e->id, e->name); ret1 = test_event(e); if (ret1) ret2 = ret1; + pr_debug("\n"); } return ret2; @@ -1785,7 +1832,7 @@ static int test_pmu_events(void) } while (!ret && (ent = readdir(dir))) { - struct evlist_test e; + struct evlist_test e = { .id = 0, }; char name[2 * NAME_MAX + 1 + 12 + 3]; /* Names containing . are special and cannot be used directly */ diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 0afafab85238..34394cc05077 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -164,8 +164,13 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus for (i = 0; i < evlist->nr_mmaps; i++) { union perf_event *event; + struct perf_mmap *md; - while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + md = &evlist->mmap[i]; + if (perf_mmap__read_init(md) < 0) + continue; + + while ((event = perf_mmap__read_event(md)) != NULL) { const u32 type = event->header.type; const char *name = perf_event__name(type); @@ -266,8 +271,9 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus ++errs; } - perf_evlist__mmap_consume(evlist, i); + perf_mmap__consume(md); } + perf_mmap__read_done(md); } /* diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 9abca267afa9..7bedf8608fdd 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -98,7 +98,7 @@ static char *test_format_dir_get(void) struct test_format *format = &test_formats[i]; FILE *file; - snprintf(name, PATH_MAX, "%s/%s", dir, format->name); + scnprintf(name, PATH_MAX, "%s/%s", dir, format->name); file = fopen(name, "w"); if (!file) diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c index 5d2df65ada6a..40ab72149ce1 100644 --- a/tools/perf/tests/python-use.c +++ b/tools/perf/tests/python-use.c @@ -7,8 +7,7 @@ #include <stdlib.h> #include <linux/compiler.h> #include "tests.h" - -extern int verbose; +#include "util/debug.h" int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unused) { diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh index 30a950c9d407..1c16e56cd93e 100644 --- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh @@ -5,7 +5,7 @@ had_vfs_getname=$? cleanup_probe_vfs_getname() { if [ $had_vfs_getname -eq 1 ] ; then - perf probe -q -d probe:vfs_getname + perf probe -q -d probe:vfs_getname* fi } diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh new file mode 100755 index 000000000000..3013ac8f83d0 --- /dev/null +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -0,0 +1,94 @@ +# probe libc's inet_pton & backtrace it with ping + +# Installs a probe on libc's inet_pton function, that will use uprobes, +# then use 'perf trace' on a ping to localhost asking for just one packet +# with the a backtrace 3 levels deep, check that it is what we expect. +# This needs no debuginfo package, all is done using the libc ELF symtab +# and the CFI info in the binaries. + +# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 + +. $(dirname $0)/lib/probe.sh + +libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g') +nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254 + +event_pattern='probe_libc:inet_pton(\_[[:digit:]]+)?' + +add_libc_inet_pton_event() { + + event_name=$(perf probe -f -x $libc -a inet_pton 2>&1 | tail -n +2 | head -n -5 | \ + grep -P -o "$event_pattern(?=[[:space:]]\(on inet_pton in $libc\))") + + if [ $? -ne 0 -o -z "$event_name" ] ; then + printf "FAIL: could not add event\n" + return 1 + fi +} + +trace_libc_inet_pton_backtrace() { + + expected=`mktemp -u /tmp/expected.XXX` + + echo "ping[][0-9 \.:]+$event_name: \([[:xdigit:]]+\)" > $expected + echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected + case "$(uname -m)" in + s390x) + eventattr='call-graph=dwarf,max-stack=4' + echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected + echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected + echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected + ;; + ppc64|ppc64le) + eventattr='max-stack=4' + echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected + echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected + echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected + ;; + *) + eventattr='max-stack=3' + echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected + echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected + ;; + esac + + perf_data=`mktemp -u /tmp/perf.data.XXX` + perf_script=`mktemp -u /tmp/perf.script.XXX` + perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1 + perf script -i $perf_data > $perf_script + + exec 3<$perf_script + exec 4<$expected + while read line <&3 && read -r pattern <&4; do + [ -z "$pattern" ] && break + echo $line + echo "$line" | egrep -q "$pattern" + if [ $? -ne 0 ] ; then + printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line" + return 1 + fi + done + + # If any statements are executed from this point onwards, + # the exit code of the last among these will be reflected + # in err below. If the exit code is 0, the test will pass + # even if the perf script output does not match. +} + +delete_libc_inet_pton_event() { + + if [ -n "$event_name" ] ; then + perf probe -q -d $event_name + fi +} + +# Check for IPv6 interface existence +ip a sh lo | fgrep -q inet6 || exit 2 + +skip_if_no_perf_probe && \ +add_libc_inet_pton_event && \ +trace_libc_inet_pton_backtrace +err=$? +rm -f ${perf_data} ${perf_script} ${expected} +delete_libc_inet_pton_event +exit $err diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh deleted file mode 100755 index c446c894b297..000000000000 --- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh +++ /dev/null @@ -1,62 +0,0 @@ -# probe libc's inet_pton & backtrace it with ping - -# Installs a probe on libc's inet_pton function, that will use uprobes, -# then use 'perf trace' on a ping to localhost asking for just one packet -# with the a backtrace 3 levels deep, check that it is what we expect. -# This needs no debuginfo package, all is done using the libc ELF symtab -# and the CFI info in the binaries. - -# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 - -. $(dirname $0)/lib/probe.sh - -libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g') -nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254 - -trace_libc_inet_pton_backtrace() { - idx=0 - expected[0]="PING.*bytes" - expected[1]="64 bytes from ::1.*" - expected[2]=".*ping statistics.*" - expected[3]=".*packets transmitted.*" - expected[4]="rtt min.*" - expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)" - expected[6]=".*inet_pton[[:space:]]\($libc\)$" - case "$(uname -m)" in - s390x) - eventattr='call-graph=dwarf' - expected[7]="gaih_inet[[:space:]]\(inlined\)$" - expected[8]="__GI_getaddrinfo[[:space:]]\(inlined\)$" - expected[9]="main[[:space:]]\(.*/bin/ping.*\)$" - expected[10]="__libc_start_main[[:space:]]\($libc\)$" - expected[11]="_start[[:space:]]\(.*/bin/ping.*\)$" - ;; - *) - eventattr='max-stack=3' - expected[7]="getaddrinfo[[:space:]]\($libc\)$" - expected[8]=".*\(.*/bin/ping.*\)$" - ;; - esac - - perf trace --no-syscalls -e probe_libc:inet_pton/$eventattr/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do - echo $line - echo "$line" | egrep -q "${expected[$idx]}" - if [ $? -ne 0 ] ; then - printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line" - exit 1 - fi - let idx+=1 - [ -z "${expected[$idx]}" ] && break - done -} - -# Check for IPv6 interface existence -ip a sh lo | fgrep -q inet6 || exit 2 - -skip_if_no_perf_probe && \ -perf probe -q $libc inet_pton && \ -trace_libc_inet_pton_backtrace -err=$? -rm -f ${file} -perf probe -q -d probe_libc:inet_pton -exit $err diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh index 55ad9793d544..4ce276efe6b4 100755 --- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh +++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh @@ -17,7 +17,7 @@ skip_if_no_perf_probe || exit 2 file=$(mktemp /tmp/temporary_file.XXXXX) trace_open_vfs_getname() { - evts=$(echo $(perf list syscalls:sys_enter_open* |& egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/') + evts=$(echo $(perf list syscalls:sys_enter_open* 2>&1 | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/') perf trace -e $evts touch $file 2>&1 | \ egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$" } diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index f6c72f915d48..f9490b237893 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -39,6 +39,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) }; struct cpu_map *cpus; struct thread_map *threads; + struct perf_mmap *md; attr.sample_freq = 500; @@ -93,7 +94,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) perf_evlist__disable(evlist); - while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { + md = &evlist->mmap[0]; + if (perf_mmap__read_init(md) < 0) + goto out_init; + + while ((event = perf_mmap__read_event(md)) != NULL) { struct perf_sample sample; if (event->header.type != PERF_RECORD_SAMPLE) @@ -108,9 +113,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) total_periods += sample.period; nr_samples++; next_event: - perf_evlist__mmap_consume(evlist, 0); + perf_mmap__consume(md); } + perf_mmap__read_done(md); +out_init: if ((u64) nr_samples == total_periods) { pr_debug("All (%d) samples have period value of 1!\n", nr_samples); diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 33e00295a972..9b5be51e5e7b 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -258,16 +258,22 @@ static int process_events(struct perf_evlist *evlist, unsigned pos, cnt = 0; LIST_HEAD(events); struct event_node *events_array, *node; + struct perf_mmap *md; int i, ret; for (i = 0; i < evlist->nr_mmaps; i++) { - while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + md = &evlist->mmap[i]; + if (perf_mmap__read_init(md) < 0) + continue; + + while ((event = perf_mmap__read_event(md)) != NULL) { cnt += 1; ret = add_event(evlist, &events, event); - perf_evlist__mmap_consume(evlist, i); + perf_mmap__consume(md); if (ret < 0) goto out_free_nodes; } + perf_mmap__read_done(md); } events_array = calloc(cnt, sizeof(struct event_node)); diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 01b62b81751b..e92fa6029ac7 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -47,6 +47,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused char sbuf[STRERR_BUFSIZE]; struct cpu_map *cpus; struct thread_map *threads; + struct perf_mmap *md; signal(SIGCHLD, sig_handler); @@ -110,13 +111,19 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused perf_evlist__start_workload(evlist); retry: - while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { + md = &evlist->mmap[0]; + if (perf_mmap__read_init(md) < 0) + goto out_init; + + while ((event = perf_mmap__read_event(md)) != NULL) { if (event->header.type == PERF_RECORD_EXIT) nr_exit++; - perf_evlist__mmap_consume(evlist, 0); + perf_mmap__consume(md); } + perf_mmap__read_done(md); +out_init: if (!exited || !nr_exit) { perf_evlist__poll(evlist, -1); goto retry; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 2862b80bc288..a9760e790563 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -58,6 +58,7 @@ 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__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); @@ -102,6 +103,7 @@ 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); bool test__bp_signal_is_supported(void); diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index 17cb1bb3448c..9497d02f69e6 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -45,6 +45,7 @@ static int session_write_header(char *path) perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY); perf_header__set_feat(&session->header, HEADER_NRCPUS); + perf_header__set_feat(&session->header, HEADER_ARCH); session->header.data_size += DATA_SIZE; @@ -70,6 +71,27 @@ static int check_cpu_topology(char *path, struct cpu_map *map) session = perf_session__new(&data, false, NULL); TEST_ASSERT_VAL("can't get session", session); + /* On platforms with large numbers of CPUs process_cpu_topology() + * might issue an error while reading the perf.data file section + * HEADER_CPU_TOPOLOGY and the cpu_topology_map pointed to by member + * cpu is a NULL pointer. + * Example: On s390 + * CPU 0 is on core_id 0 and physical_package_id 6 + * CPU 1 is on core_id 1 and physical_package_id 3 + * + * Core_id and physical_package_id are platform and architecture + * dependend and might have higher numbers than the CPU id. + * This actually depends on the configuration. + * + * In this case process_cpu_topology() prints error message: + * "socket_id number is too big. You may need to upgrade the + * perf tool." + * + * This is the reason why this test might be skipped. + */ + if (!session->header.env.cpu) + return TEST_SKIP; + for (i = 0; i < session->header.env.nr_cpus_avail; i++) { if (!cpu_map__has(map, i)) continue; @@ -95,7 +117,7 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe { char path[PATH_MAX]; struct cpu_map *map; - int ret = -1; + int ret = TEST_FAIL; TEST_ASSERT_VAL("can't get templ file", !get_temp(path)); @@ -110,12 +132,9 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe goto free_path; } - if (check_cpu_topology(path, map)) - goto free_map; - ret = 0; - -free_map: + ret = check_cpu_topology(path, map); cpu_map__put(map); + free_path: unlink(path); return ret; diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index f6789fb029d6..7691980b7df1 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -19,8 +19,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest struct symbol *sym; struct map *kallsyms_map, *vmlinux_map, *map; struct machine kallsyms, vmlinux; - enum map_type type = MAP__FUNCTION; - struct maps *maps = &vmlinux.kmaps.maps[type]; + struct maps *maps = machine__kernel_maps(&vmlinux); u64 mem_start, mem_end; bool header_printed; @@ -56,7 +55,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest * be compacted against the list of modules found in the "vmlinux" * code and with the one got from /proc/modules from the "kallsyms" code. */ - if (__machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, true) <= 0) { + if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms") <= 0) { pr_debug("dso__load_kallsyms "); goto out; } @@ -94,7 +93,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest * maps__reloc_vmlinux will notice and set proper ->[un]map_ip routines * to fixup the symbols. */ - if (machine__load_vmlinux_path(&vmlinux, type) <= 0) { + if (machine__load_vmlinux_path(&vmlinux) <= 0) { pr_debug("Couldn't find a vmlinux that matches the kernel running on this machine, skipping test\n"); err = TEST_SKIP; goto out; @@ -108,7 +107,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest * in the kallsyms dso. For the ones that are in both, check its names and * end addresses too. */ - for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) { + map__for_each_symbol(vmlinux_map, sym, nd) { struct symbol *pair, *first_pair; sym = rb_entry(nd, struct symbol, rb_node); @@ -119,13 +118,12 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest mem_start = vmlinux_map->unmap_ip(vmlinux_map, sym->start); mem_end = vmlinux_map->unmap_ip(vmlinux_map, sym->end); - first_pair = machine__find_kernel_symbol(&kallsyms, type, - mem_start, NULL); + first_pair = machine__find_kernel_symbol(&kallsyms, mem_start, NULL); pair = first_pair; if (pair && UM(pair->start) == mem_start) { next_pair: - if (strcmp(sym->name, pair->name) == 0) { + if (arch__compare_symbol_names(sym->name, pair->name) == 0) { /* * kallsyms don't have the symbol end, so we * set that by using the next symbol start - 1, @@ -149,7 +147,7 @@ next_pair: */ continue; } else { - pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL); + pair = machine__find_kernel_symbol_by_name(&kallsyms, sym->name, NULL); if (pair) { if (UM(pair->start) == mem_start) goto next_pair; @@ -183,7 +181,7 @@ next_pair: * so use the short name, less descriptive but the same ("[kernel]" in * both cases. */ - pair = map_groups__find_by_name(&kallsyms.kmaps, type, + pair = map_groups__find_by_name(&kallsyms.kmaps, (map->dso->kernel ? map->dso->short_name : map->dso->name)); @@ -206,7 +204,7 @@ next_pair: mem_start = vmlinux_map->unmap_ip(vmlinux_map, map->start); mem_end = vmlinux_map->unmap_ip(vmlinux_map, map->end); - pair = map_groups__find(&kallsyms.kmaps, type, mem_start); + pair = map_groups__find(&kallsyms.kmaps, mem_start); if (pair == NULL || pair->priv) continue; @@ -228,7 +226,7 @@ next_pair: header_printed = false; - maps = &kallsyms.kmaps.maps[type]; + maps = machine__kernel_maps(&kallsyms); for (map = maps__first(maps); map; map = map__next(map)) { if (!map->priv) { diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build index 66330d4b739b..f528ba35e140 100644 --- a/tools/perf/trace/beauty/Build +++ b/tools/perf/trace/beauty/Build @@ -7,4 +7,5 @@ endif libperf-y += kcmp.o libperf-y += pkey_alloc.o libperf-y += prctl.o +libperf-y += socket.o libperf-y += statx.o diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 984a504d335c..9615af5d412b 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -106,6 +106,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg); #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3 +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_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/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh index 2149d3a98e42..9d3816815e60 100755 --- a/tools/perf/trace/beauty/drm_ioctl.sh +++ b/tools/perf/trace/beauty/drm_ioctl.sh @@ -1,13 +1,14 @@ #!/bin/sh -drm_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/ + printf "#ifndef DRM_COMMAND_BASE\n" -grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h +grep "#define DRM_COMMAND_BASE" $header_dir/drm.h printf "#endif\n" printf "static const char *drm_ioctl_cmds[] = {\n" -grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \ +grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \ sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[ ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/ [\2] = "\1",/g' -grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $drm_header_dir/i915_drm.h | \ +grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $header_dir/i915_drm.h | \ sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[ ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh index 40d063b8c082..a3c304caa336 100755 --- a/tools/perf/trace/beauty/kcmp_type.sh +++ b/tools/perf/trace/beauty/kcmp_type.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *kcmp_types[] = {\n" regex='^[[:space:]]+(KCMP_(\w+)),' diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh index bd28817afced..c4699fd46bb6 100755 --- a/tools/perf/trace/beauty/kvm_ioctl.sh +++ b/tools/perf/trace/beauty/kvm_ioctl.sh @@ -1,10 +1,10 @@ #!/bin/sh -kvm_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *kvm_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${kvm_header_dir}/kvm.h | \ +egrep $regex ${header_dir}/kvm.h | \ sed -r "s/$regex/\2 \1/g" | \ egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \ sort | xargs printf "\t[%s] = \"%s\",\n" diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh index 60ef8640ee70..431639eb4d29 100755 --- a/tools/perf/trace/beauty/madvise_behavior.sh +++ b/tools/perf/trace/beauty/madvise_behavior.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/ printf "static const char *madvise_advices[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*' diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c index 417e3ecfe9d7..9f68077b241b 100644 --- a/tools/perf/trace/beauty/mmap.c +++ b/tools/perf/trace/beauty/mmap.c @@ -54,6 +54,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, P_MMAP_FLAG(EXECUTABLE); P_MMAP_FLAG(FILE); P_MMAP_FLAG(FIXED); +#ifdef MAP_FIXED_NOREPLACE + P_MMAP_FLAG(FIXED_NOREPLACE); +#endif P_MMAP_FLAG(GROWSDOWN); P_MMAP_FLAG(HUGETLB); P_MMAP_FLAG(LOCKED); diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh index faea4237c793..6492c74df928 100755 --- a/tools/perf/trace/beauty/perf_ioctl.sh +++ b/tools/perf/trace/beauty/perf_ioctl.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *perf_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*' diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh index 62e51a02b839..e0a51aeb20b2 100755 --- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh +++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/ printf "static const char *pkey_alloc_access_rights[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*' diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh index 0be4138fbe71..f24722146ebe 100755 --- a/tools/perf/trace/beauty/prctl_option.sh +++ b/tools/perf/trace/beauty/prctl_option.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *prctl_options[] = {\n" regex='^#define[[:space:]]+PR_([GS]ET\w+)[[:space:]]*([[:xdigit:]]+).*' diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh index aad5ab130539..eb511bb5fbd3 100755 --- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh +++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh @@ -1,8 +1,8 @@ #!/bin/sh -sound_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/ printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n" -grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \ +grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \ sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh index b7e9ef6b2f55..6818392968b2 100755 --- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh +++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh @@ -1,8 +1,8 @@ #!/bin/sh -sound_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/ printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n" -grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \ +grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \ sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c new file mode 100644 index 000000000000..65227269384b --- /dev/null +++ b/tools/perf/trace/beauty/socket.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * trace/beauty/socket.c + * + * Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + */ + +#include "trace/beauty/beauty.h" +#include <sys/types.h> +#include <sys/socket.h> + +static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size) +{ +#include "trace/beauty/generated/socket_ipproto_array.c" + static DEFINE_STRARRAY(socket_ipproto); + + return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol); +} + +size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg) +{ + int domain = syscall_arg__val(arg, 0); + + if (domain == AF_INET || domain == AF_INET6) + return socket__scnprintf_ipproto(arg->val, bf, size); + + return syscall_arg__scnprintf_int(bf, size, arg); +} diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh new file mode 100755 index 000000000000..a3cc24633bec --- /dev/null +++ b/tools/perf/trace/beauty/socket_ipproto.sh @@ -0,0 +1,11 @@ +#!/bin/sh + +[ $# -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/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh index 76f1de697787..0f6a5197d0be 100755 --- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh +++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh @@ -1,17 +1,17 @@ #!/bin/sh -vhost_virtio_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *vhost_virtio_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${vhost_virtio_header_dir}/vhost.h | \ +egrep $regex ${header_dir}/vhost.h | \ sed -r "s/$regex/\2 \1/g" | \ sort | xargs printf "\t[%s] = \"%s\",\n" printf "};\n" printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${vhost_virtio_header_dir}/vhost.h | \ +egrep $regex ${header_dir}/vhost.h | \ sed -r "s/$regex/\2 \1/g" | \ sort | xargs printf "\t[%s] = \"%s\",\n" printf "};\n" diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 63399af3049f..4f75561424ed 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -45,23 +45,33 @@ void ui_browser__set_percent_color(struct ui_browser *browser, ui_browser__set_color(browser, color); } -void ui_browser__gotorc(struct ui_browser *browser, int y, int x) +void ui_browser__gotorc_title(struct ui_browser *browser, int y, int x) { SLsmg_gotorc(browser->y + y, browser->x + x); } +void ui_browser__gotorc(struct ui_browser *browser, int y, int x) +{ + SLsmg_gotorc(browser->y + y + browser->extra_title_lines, browser->x + x); +} + void ui_browser__write_nstring(struct ui_browser *browser __maybe_unused, const char *msg, unsigned int width) { slsmg_write_nstring(msg, width); } +void ui_browser__vprintf(struct ui_browser *browser __maybe_unused, const char *fmt, va_list args) +{ + slsmg_vprintf(fmt, args); +} + void ui_browser__printf(struct ui_browser *browser __maybe_unused, const char *fmt, ...) { va_list args; va_start(args, fmt); - slsmg_vprintf(fmt, args); + ui_browser__vprintf(browser, fmt, args); va_end(args); } @@ -186,6 +196,7 @@ void ui_browser__refresh_dimensions(struct ui_browser *browser) { browser->width = SLtt_Screen_Cols - 1; browser->height = browser->rows = SLtt_Screen_Rows - 2; + browser->rows -= browser->extra_title_lines; browser->y = 1; browser->x = 0; } @@ -332,8 +343,8 @@ static int __ui_browser__refresh(struct ui_browser *browser) else width += 1; - SLsmg_fill_region(browser->y + row, browser->x, - browser->height - row, width, ' '); + SLsmg_fill_region(browser->y + row + browser->extra_title_lines, browser->x, + browser->rows - row, width, ' '); return 0; } @@ -779,6 +790,4 @@ void ui_browser__init(void) struct ui_browser_colorset *c = &ui_browser__colorsets[i++]; sltt_set_color(c->colorset, c->name, c->fg, c->bg); } - - annotate_browser__init(); } diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 03e1734412b9..aa5932e1d62e 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -3,6 +3,7 @@ #define _PERF_UI_BROWSER_H_ 1 #include <linux/types.h> +#include <stdarg.h> #define HE_COLORSET_TOP 50 #define HE_COLORSET_MEDIUM 51 @@ -16,6 +17,7 @@ struct ui_browser { u64 index, top_idx; void *top, *entries; u16 y, x, width, height, rows, columns, horiz_scroll; + u8 extra_title_lines; int current_color; void *priv; const char *title; @@ -37,9 +39,11 @@ bool ui_browser__is_current_entry(struct ui_browser *browser, unsigned row); void ui_browser__refresh_dimensions(struct ui_browser *browser); void ui_browser__reset_index(struct ui_browser *browser); +void ui_browser__gotorc_title(struct ui_browser *browser, int y, int x); void ui_browser__gotorc(struct ui_browser *browser, int y, int x); void ui_browser__write_nstring(struct ui_browser *browser, const char *msg, unsigned int width); +void ui_browser__vprintf(struct ui_browser *browser, const char *fmt, va_list args); void ui_browser__printf(struct ui_browser *browser, const char *fmt, ...); void ui_browser__write_graph(struct ui_browser *browser, int graph); void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column, @@ -77,5 +81,4 @@ void ui_browser__list_head_seek(struct ui_browser *browser, off_t offset, int wh unsigned int ui_browser__list_head_refresh(struct ui_browser *browser); void ui_browser__init(void); -void annotate_browser__init(void); #endif /* _PERF_UI_BROWSER_H_ */ diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index fbf927cf775d..1d00e5ec7906 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -9,41 +9,19 @@ #include "../../util/sort.h" #include "../../util/symbol.h" #include "../../util/evsel.h" -#include "../../util/config.h" #include "../../util/evlist.h" #include <inttypes.h> #include <pthread.h> #include <linux/kernel.h> #include <linux/string.h> #include <sys/ttydefaults.h> +#include <asm/bug.h> struct disasm_line_samples { double percent; struct sym_hist_entry he; }; -#define IPC_WIDTH 6 -#define CYCLES_WIDTH 6 - -struct browser_line { - u32 idx; - int idx_asm; - int jump_sources; -}; - -static struct annotate_browser_opt { - bool hide_src_code, - use_offset, - jump_arrows, - show_linenr, - show_nr_jumps, - show_nr_samples, - show_total_period; -} annotate_browser__opts = { - .use_offset = true, - .jump_arrows = true, -}; - struct arch; struct annotate_browser { @@ -51,245 +29,99 @@ struct annotate_browser { struct rb_root entries; struct rb_node *curr_hot; struct annotation_line *selection; - struct annotation_line **offsets; struct arch *arch; - int nr_events; - u64 start; - int nr_asm_entries; - int nr_entries; - int max_jump_sources; - int nr_jumps; + struct annotation_options *opts; bool searching_backwards; - bool have_cycles; - u8 addr_width; - u8 jumps_width; - u8 target_width; - u8 min_addr_width; - u8 max_addr_width; char search_bf[128]; }; -static inline struct browser_line *browser_line(struct annotation_line *al) +static inline struct annotation *browser__annotation(struct ui_browser *browser) { - void *ptr = al; - - ptr = container_of(al, struct disasm_line, al); - return ptr - sizeof(struct browser_line); + struct map_symbol *ms = browser->priv; + return symbol__annotation(ms->sym); } -static bool disasm_line__filter(struct ui_browser *browser __maybe_unused, - void *entry) +static bool disasm_line__filter(struct ui_browser *browser, void *entry) { - if (annotate_browser__opts.hide_src_code) { - struct annotation_line *al = list_entry(entry, struct annotation_line, node); - - return al->offset == -1; - } - - return false; + struct annotation *notes = browser__annotation(browser); + struct annotation_line *al = list_entry(entry, struct annotation_line, node); + return annotation_line__filter(al, notes); } -static int annotate_browser__jumps_percent_color(struct annotate_browser *browser, - int nr, bool current) +static int ui_browser__jumps_percent_color(struct ui_browser *browser, int nr, bool current) { - if (current && (!browser->b.use_navkeypressed || browser->b.navkeypressed)) + struct annotation *notes = browser__annotation(browser); + + if (current && (!browser->use_navkeypressed || browser->navkeypressed)) return HE_COLORSET_SELECTED; - if (nr == browser->max_jump_sources) + if (nr == notes->max_jump_sources) return HE_COLORSET_TOP; if (nr > 1) return HE_COLORSET_MEDIUM; return HE_COLORSET_NORMAL; } -static int annotate_browser__set_jumps_percent_color(struct annotate_browser *browser, - int nr, bool current) +static int ui_browser__set_jumps_percent_color(void *browser, int nr, bool current) { - int color = annotate_browser__jumps_percent_color(browser, nr, current); - return ui_browser__set_color(&browser->b, color); + int color = ui_browser__jumps_percent_color(browser, nr, current); + return ui_browser__set_color(browser, color); } -static int annotate_browser__pcnt_width(struct annotate_browser *ab) +static int annotate_browser__set_color(void *browser, int color) { - return (annotate_browser__opts.show_total_period ? 12 : 7) * ab->nr_events; + return ui_browser__set_color(browser, color); } -static int annotate_browser__cycles_width(struct annotate_browser *ab) +static void annotate_browser__write_graph(void *browser, int graph) { - return ab->have_cycles ? IPC_WIDTH + CYCLES_WIDTH : 0; + ui_browser__write_graph(browser, graph); } -static void disasm_line__write(struct disasm_line *dl, struct ui_browser *browser, - char *bf, size_t size) +static void annotate_browser__set_percent_color(void *browser, double percent, bool current) { - if (dl->ins.ops && dl->ins.ops->scnprintf) { - if (ins__is_jump(&dl->ins)) { - bool fwd = dl->ops.target.offset > dl->al.offset; - - ui_browser__write_graph(browser, fwd ? SLSMG_DARROW_CHAR : - SLSMG_UARROW_CHAR); - SLsmg_write_char(' '); - } else if (ins__is_call(&dl->ins)) { - ui_browser__write_graph(browser, SLSMG_RARROW_CHAR); - SLsmg_write_char(' '); - } else if (ins__is_ret(&dl->ins)) { - ui_browser__write_graph(browser, SLSMG_LARROW_CHAR); - SLsmg_write_char(' '); - } else { - ui_browser__write_nstring(browser, " ", 2); - } - } else { - ui_browser__write_nstring(browser, " ", 2); - } + ui_browser__set_percent_color(browser, percent, current); +} + +static void annotate_browser__printf(void *browser, const char *fmt, ...) +{ + va_list args; - disasm_line__scnprintf(dl, bf, size, !annotate_browser__opts.use_offset); + va_start(args, fmt); + ui_browser__vprintf(browser, fmt, args); + va_end(args); } static void annotate_browser__write(struct ui_browser *browser, void *entry, int row) { struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); + struct annotation *notes = browser__annotation(browser); struct annotation_line *al = list_entry(entry, struct annotation_line, node); - struct browser_line *bl = browser_line(al); - bool current_entry = ui_browser__is_current_entry(browser, row); - bool change_color = (!annotate_browser__opts.hide_src_code && - (!current_entry || (browser->use_navkeypressed && - !browser->navkeypressed))); - int width = browser->width, printed; - int i, pcnt_width = annotate_browser__pcnt_width(ab), - cycles_width = annotate_browser__cycles_width(ab); - double percent_max = 0.0; - char bf[256]; - bool show_title = false; - - for (i = 0; i < ab->nr_events; i++) { - if (al->samples[i].percent > percent_max) - percent_max = al->samples[i].percent; - } - - if ((row == 0) && (al->offset == -1 || percent_max == 0.0)) { - if (ab->have_cycles) { - if (al->ipc == 0.0 && al->cycles == 0) - show_title = true; - } else - show_title = true; - } - - if (al->offset != -1 && percent_max != 0.0) { - for (i = 0; i < ab->nr_events; i++) { - ui_browser__set_percent_color(browser, - al->samples[i].percent, - current_entry); - if (annotate_browser__opts.show_total_period) { - ui_browser__printf(browser, "%11" PRIu64 " ", - al->samples[i].he.period); - } else if (annotate_browser__opts.show_nr_samples) { - ui_browser__printf(browser, "%6" PRIu64 " ", - al->samples[i].he.nr_samples); - } else { - ui_browser__printf(browser, "%6.2f ", - al->samples[i].percent); - } - } - } else { - ui_browser__set_percent_color(browser, 0, current_entry); - - if (!show_title) - ui_browser__write_nstring(browser, " ", pcnt_width); - else { - ui_browser__printf(browser, "%*s", pcnt_width, - annotate_browser__opts.show_total_period ? "Period" : - annotate_browser__opts.show_nr_samples ? "Samples" : "Percent"); - } - } - if (ab->have_cycles) { - if (al->ipc) - ui_browser__printf(browser, "%*.2f ", IPC_WIDTH - 1, al->ipc); - else if (!show_title) - ui_browser__write_nstring(browser, " ", IPC_WIDTH); - else - ui_browser__printf(browser, "%*s ", IPC_WIDTH - 1, "IPC"); - - if (al->cycles) - ui_browser__printf(browser, "%*" PRIu64 " ", - CYCLES_WIDTH - 1, al->cycles); - else if (!show_title) - ui_browser__write_nstring(browser, " ", CYCLES_WIDTH); - else - ui_browser__printf(browser, "%*s ", CYCLES_WIDTH - 1, "Cycle"); - } - - SLsmg_write_char(' '); + struct annotation_write_ops ops = { + .first_line = row == 0, + .current_entry = ui_browser__is_current_entry(browser, row), + .change_color = (!notes->options->hide_src_code && + (!ops.current_entry || + (browser->use_navkeypressed && + !browser->navkeypressed))), + .width = browser->width, + .obj = browser, + .set_color = annotate_browser__set_color, + .set_percent_color = annotate_browser__set_percent_color, + .set_jumps_percent_color = ui_browser__set_jumps_percent_color, + .printf = annotate_browser__printf, + .write_graph = annotate_browser__write_graph, + }; /* The scroll bar isn't being used */ if (!browser->navkeypressed) - width += 1; - - if (!*al->line) - ui_browser__write_nstring(browser, " ", width - pcnt_width - cycles_width); - else if (al->offset == -1) { - if (al->line_nr && annotate_browser__opts.show_linenr) - printed = scnprintf(bf, sizeof(bf), "%-*d ", - ab->addr_width + 1, al->line_nr); - else - printed = scnprintf(bf, sizeof(bf), "%*s ", - ab->addr_width, " "); - ui_browser__write_nstring(browser, bf, printed); - ui_browser__write_nstring(browser, al->line, width - printed - pcnt_width - cycles_width + 1); - } else { - u64 addr = al->offset; - int color = -1; - - if (!annotate_browser__opts.use_offset) - addr += ab->start; - - if (!annotate_browser__opts.use_offset) { - printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr); - } else { - if (bl->jump_sources) { - if (annotate_browser__opts.show_nr_jumps) { - int prev; - printed = scnprintf(bf, sizeof(bf), "%*d ", - ab->jumps_width, - bl->jump_sources); - prev = annotate_browser__set_jumps_percent_color(ab, bl->jump_sources, - current_entry); - ui_browser__write_nstring(browser, bf, printed); - ui_browser__set_color(browser, prev); - } - - printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ", - ab->target_width, addr); - } else { - printed = scnprintf(bf, sizeof(bf), "%*s ", - ab->addr_width, " "); - } - } - - if (change_color) - color = ui_browser__set_color(browser, HE_COLORSET_ADDR); - ui_browser__write_nstring(browser, bf, printed); - if (change_color) - ui_browser__set_color(browser, color); - - disasm_line__write(disasm_line(al), browser, bf, sizeof(bf)); + ops.width += 1; - ui_browser__write_nstring(browser, bf, width - pcnt_width - cycles_width - 3 - printed); - } + annotation_line__write(al, notes, &ops, ab->opts); - if (current_entry) + if (ops.current_entry) ab->selection = al; } -static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sym) -{ - if (!dl || !dl->ins.ops || !ins__is_jump(&dl->ins) - || !disasm_line__has_offset(dl) - || dl->ops.target.offset < 0 - || dl->ops.target.offset >= (s64)symbol__size(sym)) - return false; - - return true; -} - static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor) { struct disasm_line *pos = list_prev_entry(cursor, al.node); @@ -314,17 +146,18 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); struct disasm_line *cursor = disasm_line(ab->selection); struct annotation_line *target; - struct browser_line *btarget, *bcursor; unsigned int from, to; struct map_symbol *ms = ab->b.priv; struct symbol *sym = ms->sym; - u8 pcnt_width = annotate_browser__pcnt_width(ab); + struct annotation *notes = symbol__annotation(sym); + u8 pcnt_width = annotation__pcnt_width(notes); + int width; /* PLT symbols contain external offsets */ if (strstr(sym->name, "@plt")) return; - if (!disasm_line__is_valid_jump(cursor, sym)) + if (!disasm_line__is_valid_local_jump(cursor, sym)) return; /* @@ -347,31 +180,31 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) * name right after the '<' token and probably treating this like a * 'call' instruction. */ - target = ab->offsets[cursor->ops.target.offset]; + target = notes->offsets[cursor->ops.target.offset]; if (target == NULL) { - ui_helpline__printf("WARN: jump target inconsistency, press 'o', ab->offsets[%#x] = NULL\n", + ui_helpline__printf("WARN: jump target inconsistency, press 'o', notes->offsets[%#x] = NULL\n", cursor->ops.target.offset); return; } - bcursor = browser_line(&cursor->al); - btarget = browser_line(target); - - if (annotate_browser__opts.hide_src_code) { - from = bcursor->idx_asm; - to = btarget->idx_asm; + if (notes->options->hide_src_code) { + from = cursor->al.idx_asm; + to = target->idx_asm; } else { - from = (u64)bcursor->idx; - to = (u64)btarget->idx; + from = (u64)cursor->al.idx; + to = (u64)target->idx; } + width = annotation__cycles_width(notes); + ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS); - __ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width, + __ui_browser__line_arrow(browser, + pcnt_width + 2 + notes->widths.addr + width, from, to); if (is_fused(ab, cursor)) { ui_browser__mark_fused(browser, - pcnt_width + 3 + ab->addr_width, + pcnt_width + 3 + notes->widths.addr + width, from - 1, to > from ? true : false); } @@ -379,15 +212,15 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) static unsigned int annotate_browser__refresh(struct ui_browser *browser) { - struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); + struct annotation *notes = browser__annotation(browser); int ret = ui_browser__list_head_refresh(browser); - int pcnt_width = annotate_browser__pcnt_width(ab); + int pcnt_width = annotation__pcnt_width(notes); - if (annotate_browser__opts.jump_arrows) + if (notes->options->jump_arrows) annotate_browser__draw_current_jump(browser); ui_browser__set_color(browser, HE_COLORSET_NORMAL); - __ui_browser__vline(browser, pcnt_width, 0, browser->height - 1); + __ui_browser__vline(browser, pcnt_width, 0, browser->rows - 1); return ret; } @@ -395,10 +228,10 @@ static int disasm__cmp(struct annotation_line *a, struct annotation_line *b) { int i; - for (i = 0; i < a->samples_nr; i++) { - if (a->samples[i].percent == b->samples[i].percent) + for (i = 0; i < a->data_nr; i++) { + if (a->data[i].percent == b->data[i].percent) continue; - return a->samples[i].percent < b->samples[i].percent; + return a->data[i].percent < b->data[i].percent; } return 0; } @@ -425,6 +258,7 @@ static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line static void annotate_browser__set_top(struct annotate_browser *browser, struct annotation_line *pos, u32 idx) { + struct annotation *notes = browser__annotation(&browser->b); unsigned back; ui_browser__refresh_dimensions(&browser->b); @@ -434,7 +268,7 @@ static void annotate_browser__set_top(struct annotate_browser *browser, while (browser->b.top_idx != 0 && back != 0) { pos = list_entry(pos->node.prev, struct annotation_line, node); - if (disasm_line__filter(&browser->b, &pos->node)) + if (annotation_line__filter(pos, notes)) continue; --browser->b.top_idx; @@ -448,16 +282,12 @@ static void annotate_browser__set_top(struct annotate_browser *browser, static void annotate_browser__set_rb_top(struct annotate_browser *browser, struct rb_node *nd) { - struct browser_line *bpos; - struct annotation_line *pos; - u32 idx; + struct annotation *notes = browser__annotation(&browser->b); + struct annotation_line * pos = rb_entry(nd, struct annotation_line, rb_node); + u32 idx = pos->idx; - pos = rb_entry(nd, struct annotation_line, rb_node); - bpos = browser_line(pos); - - idx = bpos->idx; - if (annotate_browser__opts.hide_src_code) - idx = bpos->idx_asm; + if (notes->options->hide_src_code) + idx = pos->idx_asm; annotate_browser__set_top(browser, pos, idx); browser->curr_hot = nd; } @@ -485,11 +315,14 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser, continue; } - for (i = 0; i < pos->al.samples_nr; i++) { - struct annotation_data *sample = &pos->al.samples[i]; + for (i = 0; i < pos->al.data_nr; i++) { + double percent; + + percent = annotation_data__percent(&pos->al.data[i], + browser->opts->percent_type); - if (max_percent < sample->percent) - max_percent = sample->percent; + if (max_percent < percent) + max_percent = percent; } if (max_percent < 0.01 && pos->al.ipc == 0) { @@ -505,57 +338,67 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser, static bool annotate_browser__toggle_source(struct annotate_browser *browser) { + struct annotation *notes = browser__annotation(&browser->b); struct annotation_line *al; - struct browser_line *bl; off_t offset = browser->b.index - browser->b.top_idx; browser->b.seek(&browser->b, offset, SEEK_CUR); al = list_entry(browser->b.top, struct annotation_line, node); - bl = browser_line(al); - if (annotate_browser__opts.hide_src_code) { - if (bl->idx_asm < offset) - offset = bl->idx; + if (notes->options->hide_src_code) { + if (al->idx_asm < offset) + offset = al->idx; - browser->b.nr_entries = browser->nr_entries; - annotate_browser__opts.hide_src_code = false; + browser->b.nr_entries = notes->nr_entries; + notes->options->hide_src_code = false; browser->b.seek(&browser->b, -offset, SEEK_CUR); - browser->b.top_idx = bl->idx - offset; - browser->b.index = bl->idx; + browser->b.top_idx = al->idx - offset; + browser->b.index = al->idx; } else { - if (bl->idx_asm < 0) { + if (al->idx_asm < 0) { ui_helpline__puts("Only available for assembly lines."); browser->b.seek(&browser->b, -offset, SEEK_CUR); return false; } - if (bl->idx_asm < offset) - offset = bl->idx_asm; + if (al->idx_asm < offset) + offset = al->idx_asm; - browser->b.nr_entries = browser->nr_asm_entries; - annotate_browser__opts.hide_src_code = true; + browser->b.nr_entries = notes->nr_asm_entries; + notes->options->hide_src_code = true; browser->b.seek(&browser->b, -offset, SEEK_CUR); - browser->b.top_idx = bl->idx_asm - offset; - browser->b.index = bl->idx_asm; + browser->b.top_idx = al->idx_asm - offset; + browser->b.index = al->idx_asm; } return true; } -static void annotate_browser__init_asm_mode(struct annotate_browser *browser) +static void ui_browser__init_asm_mode(struct ui_browser *browser) { - ui_browser__reset_index(&browser->b); - browser->b.nr_entries = browser->nr_asm_entries; + struct annotation *notes = browser__annotation(browser); + ui_browser__reset_index(browser); + browser->nr_entries = notes->nr_asm_entries; } #define SYM_TITLE_MAX_SIZE (PATH_MAX + 64) static int sym_title(struct symbol *sym, struct map *map, char *title, - size_t sz) + size_t sz, int percent_type) { - return snprintf(title, sz, "%s %s", sym->name, map->dso->long_name); + return snprintf(title, sz, "%s %s [Percent: %s]", sym->name, map->dso->long_name, + percent_type_str(percent_type)); } +/* + * This can be called from external jumps, i.e. jumps from one functon + * to another, like from the kernel's entry_SYSCALL_64 function to the + * swapgs_restore_regs_and_return_to_usermode() function. + * + * So all we check here is that dl->ops.target.sym is set, if it is, just + * go to that function and when exiting from its disassembly, come back + * to the calling function. + */ static bool annotate_browser__callq(struct annotate_browser *browser, struct perf_evsel *evsel, struct hist_browser_timer *hbt) @@ -563,36 +406,26 @@ static bool annotate_browser__callq(struct annotate_browser *browser, struct map_symbol *ms = browser->b.priv; struct disasm_line *dl = disasm_line(browser->selection); struct annotation *notes; - struct addr_map_symbol target = { - .map = ms->map, - .addr = map__objdump_2mem(ms->map, dl->ops.target.addr), - }; char title[SYM_TITLE_MAX_SIZE]; - if (!ins__is_call(&dl->ins)) - return false; - - if (map_groups__find_ams(&target) || - map__rip_2objdump(target.map, target.map->map_ip(target.map, - target.addr)) != - dl->ops.target.addr) { + if (!dl->ops.target.sym) { ui_helpline__puts("The called function was not found."); return true; } - notes = symbol__annotation(target.sym); + notes = symbol__annotation(dl->ops.target.sym); pthread_mutex_lock(¬es->lock); - if (notes->src == NULL && symbol__alloc_hist(target.sym) < 0) { + if (!symbol__hists(dl->ops.target.sym, evsel->evlist->nr_entries)) { pthread_mutex_unlock(¬es->lock); ui__warning("Not enough memory for annotating '%s' symbol!\n", - target.sym->name); + dl->ops.target.sym->name); return true; } pthread_mutex_unlock(¬es->lock); - symbol__tui_annotate(target.sym, target.map, evsel, hbt); - sym_title(ms->sym, ms->map, title, sizeof(title)); + symbol__tui_annotate(dl->ops.target.sym, ms->map, evsel, hbt, browser->opts); + sym_title(ms->sym, ms->map, title, sizeof(title), browser->opts->percent_type); ui_browser__show_title(&browser->b, title); return true; } @@ -601,23 +434,23 @@ static struct disasm_line *annotate_browser__find_offset(struct annotate_browser *browser, s64 offset, s64 *idx) { - struct map_symbol *ms = browser->b.priv; - struct symbol *sym = ms->sym; - struct annotation *notes = symbol__annotation(sym); + struct annotation *notes = browser__annotation(&browser->b); struct disasm_line *pos; *idx = 0; list_for_each_entry(pos, ¬es->src->source, al.node) { if (pos->al.offset == offset) return pos; - if (!disasm_line__filter(&browser->b, &pos->al.node)) + if (!annotation_line__filter(&pos->al, notes)) ++*idx; } return NULL; } -static bool annotate_browser__jump(struct annotate_browser *browser) +static bool annotate_browser__jump(struct annotate_browser *browser, + struct perf_evsel *evsel, + struct hist_browser_timer *hbt) { struct disasm_line *dl = disasm_line(browser->selection); u64 offset; @@ -626,6 +459,11 @@ static bool annotate_browser__jump(struct annotate_browser *browser) if (!ins__is_jump(&dl->ins)) return false; + if (dl->ops.target.outside) { + annotate_browser__callq(browser, evsel, hbt); + return true; + } + offset = dl->ops.target.offset; dl = annotate_browser__find_offset(browser, offset, &idx); if (dl == NULL) { @@ -642,14 +480,12 @@ static struct annotation_line *annotate_browser__find_string(struct annotate_browser *browser, char *s, s64 *idx) { - struct map_symbol *ms = browser->b.priv; - struct symbol *sym = ms->sym; - struct annotation *notes = symbol__annotation(sym); + struct annotation *notes = browser__annotation(&browser->b); struct annotation_line *al = browser->selection; *idx = browser->b.index; list_for_each_entry_continue(al, ¬es->src->source, node) { - if (disasm_line__filter(&browser->b, &al->node)) + if (annotation_line__filter(al, notes)) continue; ++*idx; @@ -681,14 +517,12 @@ static struct annotation_line *annotate_browser__find_string_reverse(struct annotate_browser *browser, char *s, s64 *idx) { - struct map_symbol *ms = browser->b.priv; - struct symbol *sym = ms->sym; - struct annotation *notes = symbol__annotation(sym); + struct annotation *notes = browser__annotation(&browser->b); struct annotation_line *al = browser->selection; *idx = browser->b.index; list_for_each_entry_continue_reverse(al, ¬es->src->source, node) { - if (disasm_line__filter(&browser->b, &al->node)) + if (annotation_line__filter(al, notes)) continue; --*idx; @@ -764,17 +598,55 @@ bool annotate_browser__continue_search_reverse(struct annotate_browser *browser, return __annotate_browser__search_reverse(browser); } -static void annotate_browser__update_addr_width(struct annotate_browser *browser) +static int annotate_browser__show(struct ui_browser *browser, char *title, const char *help) { - if (annotate_browser__opts.use_offset) - browser->target_width = browser->min_addr_width; - else - browser->target_width = browser->max_addr_width; + struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); + struct map_symbol *ms = browser->priv; + struct symbol *sym = ms->sym; + char symbol_dso[SYM_TITLE_MAX_SIZE]; + + if (ui_browser__show(browser, title, help) < 0) + return -1; - browser->addr_width = browser->target_width; + sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso), ab->opts->percent_type); - if (annotate_browser__opts.show_nr_jumps) - browser->addr_width += browser->jumps_width + 1; + ui_browser__gotorc_title(browser, 0, 0); + ui_browser__set_color(browser, HE_COLORSET_ROOT); + ui_browser__write_nstring(browser, symbol_dso, browser->width + 1); + return 0; +} + +static void +switch_percent_type(struct annotation_options *opts, bool base) +{ + switch (opts->percent_type) { + case PERCENT_HITS_LOCAL: + if (base) + opts->percent_type = PERCENT_PERIOD_LOCAL; + else + opts->percent_type = PERCENT_HITS_GLOBAL; + break; + case PERCENT_HITS_GLOBAL: + if (base) + opts->percent_type = PERCENT_PERIOD_GLOBAL; + else + opts->percent_type = PERCENT_HITS_LOCAL; + break; + case PERCENT_PERIOD_LOCAL: + if (base) + opts->percent_type = PERCENT_HITS_LOCAL; + else + opts->percent_type = PERCENT_PERIOD_GLOBAL; + break; + case PERCENT_PERIOD_GLOBAL: + if (base) + opts->percent_type = PERCENT_HITS_GLOBAL; + else + opts->percent_type = PERCENT_PERIOD_LOCAL; + break; + default: + WARN_ON(1); + } } static int annotate_browser__run(struct annotate_browser *browser, @@ -782,15 +654,17 @@ static int annotate_browser__run(struct annotate_browser *browser, struct hist_browser_timer *hbt) { struct rb_node *nd = NULL; + struct hists *hists = evsel__hists(evsel); struct map_symbol *ms = browser->b.priv; struct symbol *sym = ms->sym; + struct annotation *notes = symbol__annotation(ms->sym); const char *help = "Press 'h' for help on key bindings"; int delay_secs = hbt ? hbt->refresh : 0; + char title[256]; int key; - char title[SYM_TITLE_MAX_SIZE]; - sym_title(sym, ms->map, title, sizeof(title)); - if (ui_browser__show(&browser->b, title, help) < 0) + hists__scnprintf_title(hists, title, sizeof(title)); + if (annotate_browser__show(&browser->b, title, help) < 0) return -1; annotate_browser__calc_percent(browser, evsel); @@ -821,8 +695,11 @@ static int annotate_browser__run(struct annotate_browser *browser, if (hbt) hbt->timer(hbt->arg); - if (delay_secs != 0) + if (delay_secs != 0) { symbol__annotate_decay_histogram(sym, evsel->idx); + hists__scnprintf_title(hists, title, sizeof(title)); + annotate_browser__show(&browser->b, title, help); + } continue; case K_TAB: if (nd != NULL) { @@ -854,11 +731,16 @@ static int annotate_browser__run(struct annotate_browser *browser, "J Toggle showing number of jump sources on targets\n" "n Search next string\n" "o Toggle disassembler output/simplified view\n" + "O Bump offset level (jump targets -> +call -> all -> cycle thru)\n" "s Toggle source code view\n" "t Circulate percent, total period, samples view\n" + "c Show min/max cycle\n" "/ Search string\n" "k Toggle line numbers\n" + "P Print to [symbol_name].annotation file.\n" "r Run available scripts\n" + "p Toggle percent type [local/global]\n" + "b Toggle percent base [period/hits]\n" "? Search string backwards\n"); continue; case 'r': @@ -867,8 +749,7 @@ static int annotate_browser__run(struct annotate_browser *browser, continue; } case 'k': - annotate_browser__opts.show_linenr = - !annotate_browser__opts.show_linenr; + notes->options->show_linenr = !notes->options->show_linenr; break; case 'H': nd = browser->curr_hot; @@ -878,15 +759,19 @@ static int annotate_browser__run(struct annotate_browser *browser, ui_helpline__puts(help); continue; case 'o': - annotate_browser__opts.use_offset = !annotate_browser__opts.use_offset; - annotate_browser__update_addr_width(browser); + notes->options->use_offset = !notes->options->use_offset; + annotation__update_column_widths(notes); + continue; + case 'O': + if (++notes->options->offset_level > ANNOTATION__MAX_OFFSET_LEVEL) + notes->options->offset_level = ANNOTATION__MIN_OFFSET_LEVEL; continue; case 'j': - annotate_browser__opts.jump_arrows = !annotate_browser__opts.jump_arrows; + notes->options->jump_arrows = !notes->options->jump_arrows; continue; case 'J': - annotate_browser__opts.show_nr_jumps = !annotate_browser__opts.show_nr_jumps; - annotate_browser__update_addr_width(browser); + notes->options->show_nr_jumps = !notes->options->show_nr_jumps; + annotation__update_column_widths(notes); continue; case '/': if (annotate_browser__search(browser, delay_secs)) { @@ -912,7 +797,7 @@ show_help: browser->b.height, browser->b.index, browser->b.top_idx, - browser->nr_asm_entries); + notes->nr_asm_entries); } continue; case K_ENTER: @@ -928,22 +813,38 @@ show_help: goto show_sup_ins; else if (ins__is_ret(&dl->ins)) goto out; - else if (!(annotate_browser__jump(browser) || + else if (!(annotate_browser__jump(browser, evsel, hbt) || annotate_browser__callq(browser, evsel, hbt))) { show_sup_ins: ui_helpline__puts("Actions are only available for function call/return & jump/branch instructions."); } continue; } + case 'P': + map_symbol__annotation_dump(ms, evsel, browser->opts); + continue; case 't': - if (annotate_browser__opts.show_total_period) { - annotate_browser__opts.show_total_period = false; - annotate_browser__opts.show_nr_samples = true; - } else if (annotate_browser__opts.show_nr_samples) - annotate_browser__opts.show_nr_samples = false; + if (notes->options->show_total_period) { + notes->options->show_total_period = false; + notes->options->show_nr_samples = true; + } else if (notes->options->show_nr_samples) + notes->options->show_nr_samples = false; else - annotate_browser__opts.show_total_period = true; - annotate_browser__update_addr_width(browser); + notes->options->show_total_period = true; + annotation__update_column_widths(notes); + continue; + case 'c': + if (notes->options->show_minmax_cycle) + notes->options->show_minmax_cycle = false; + else + notes->options->show_minmax_cycle = true; + annotation__update_column_widths(notes); + continue; + case 'p': + case 'b': + switch_percent_type(browser->opts, key == 'b'); + hists__scnprintf_title(hists, title, sizeof(title)); + annotate_browser__show(&browser->b, title, help); continue; case K_LEFT: case K_ESC: @@ -963,150 +864,29 @@ out: } int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel, - struct hist_browser_timer *hbt) + struct hist_browser_timer *hbt, + struct annotation_options *opts) { - /* Set default value for show_total_period and show_nr_samples */ - annotate_browser__opts.show_total_period = - symbol_conf.show_total_period; - annotate_browser__opts.show_nr_samples = - symbol_conf.show_nr_samples; - - return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt); + return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt, opts); } int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, - struct hist_browser_timer *hbt) + struct hist_browser_timer *hbt, + struct annotation_options *opts) { /* reset abort key so that it can get Ctrl-C as a key */ SLang_reset_tty(); SLang_init_tty(0, 0, 0); - return map_symbol__tui_annotate(&he->ms, evsel, hbt); -} - - -static unsigned count_insn(struct annotate_browser *browser, u64 start, u64 end) -{ - unsigned n_insn = 0; - u64 offset; - - for (offset = start; offset <= end; offset++) { - if (browser->offsets[offset]) - n_insn++; - } - return n_insn; -} - -static void count_and_fill(struct annotate_browser *browser, u64 start, u64 end, - struct cyc_hist *ch) -{ - unsigned n_insn; - u64 offset; - - n_insn = count_insn(browser, start, end); - if (n_insn && ch->num && ch->cycles) { - float ipc = n_insn / ((double)ch->cycles / (double)ch->num); - - /* Hide data when there are too many overlaps. */ - if (ch->reset >= 0x7fff || ch->reset >= ch->num / 2) - return; - - for (offset = start; offset <= end; offset++) { - struct annotation_line *al = browser->offsets[offset]; - - if (al) - al->ipc = ipc; - } - } -} - -/* - * This should probably be in util/annotate.c to share with the tty - * annotate, but right now we need the per byte offsets arrays, - * which are only here. - */ -static void annotate__compute_ipc(struct annotate_browser *browser, size_t size, - struct symbol *sym) -{ - u64 offset; - struct annotation *notes = symbol__annotation(sym); - - if (!notes->src || !notes->src->cycles_hist) - return; - - pthread_mutex_lock(¬es->lock); - for (offset = 0; offset < size; ++offset) { - struct cyc_hist *ch; - - ch = ¬es->src->cycles_hist[offset]; - if (ch && ch->cycles) { - struct annotation_line *al; - - if (ch->have_start) - count_and_fill(browser, ch->start, offset, ch); - al = browser->offsets[offset]; - if (al && ch->num_aggr) - al->cycles = ch->cycles_aggr / ch->num_aggr; - browser->have_cycles = true; - } - } - pthread_mutex_unlock(¬es->lock); -} - -static void annotate_browser__mark_jump_targets(struct annotate_browser *browser, - size_t size) -{ - u64 offset; - struct map_symbol *ms = browser->b.priv; - struct symbol *sym = ms->sym; - - /* PLT symbols contain external offsets */ - if (strstr(sym->name, "@plt")) - return; - - for (offset = 0; offset < size; ++offset) { - struct annotation_line *al = browser->offsets[offset]; - struct disasm_line *dl; - struct browser_line *blt; - - dl = disasm_line(al); - - if (!disasm_line__is_valid_jump(dl, sym)) - continue; - - al = browser->offsets[dl->ops.target.offset]; - - /* - * FIXME: Oops, no jump target? Buggy disassembler? Or do we - * have to adjust to the previous offset? - */ - if (al == NULL) - continue; - - blt = browser_line(al); - if (++blt->jump_sources > browser->max_jump_sources) - browser->max_jump_sources = blt->jump_sources; - - ++browser->nr_jumps; - } -} - -static inline int width_jumps(int n) -{ - if (n >= 100) - return 5; - if (n / 10) - return 2; - return 1; + return map_symbol__tui_annotate(&he->ms, evsel, hbt, opts); } int symbol__tui_annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, - struct hist_browser_timer *hbt) + struct hist_browser_timer *hbt, + struct annotation_options *opts) { - struct annotation_line *al; - struct annotation *notes; - size_t size; + struct annotation *notes = symbol__annotation(sym); struct map_symbol ms = { .map = map, .sym = sym, @@ -1117,31 +897,21 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, .seek = ui_browser__list_head_seek, .write = annotate_browser__write, .filter = disasm_line__filter, + .extra_title_lines = 1, /* for hists__scnprintf_title() */ .priv = &ms, .use_navkeypressed = true, }, + .opts = opts, }; int ret = -1, err; - int nr_pcnt = 1; if (sym == NULL) return -1; - size = symbol__size(sym); - if (map->dso->annotate_warned) return -1; - browser.offsets = zalloc(size * sizeof(struct annotation_line *)); - if (browser.offsets == NULL) { - ui__error("Not enough memory!"); - return -1; - } - - if (perf_evsel__is_group_event(evsel)) - nr_pcnt = evsel->nr_members; - - err = symbol__annotate(sym, map, evsel, sizeof(struct browser_line), &browser.arch); + err = symbol__annotate2(sym, map, evsel, opts, &browser.arch); if (err) { char msg[BUFSIZ]; symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); @@ -1149,110 +919,21 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, goto out_free_offsets; } - symbol__calc_percent(sym, evsel); - ui_helpline__push("Press ESC to exit"); - notes = symbol__annotation(sym); - browser.start = map__rip_2objdump(map, sym->start); - - list_for_each_entry(al, ¬es->src->source, node) { - struct browser_line *bpos; - size_t line_len = strlen(al->line); - - if (browser.b.width < line_len) - browser.b.width = line_len; - bpos = browser_line(al); - bpos->idx = browser.nr_entries++; - if (al->offset != -1) { - bpos->idx_asm = browser.nr_asm_entries++; - /* - * FIXME: short term bandaid to cope with assembly - * routines that comes with labels in the same column - * as the address in objdump, sigh. - * - * E.g. copy_user_generic_unrolled - */ - if (al->offset < (s64)size) - browser.offsets[al->offset] = al; - } else - bpos->idx_asm = -1; - } - - annotate_browser__mark_jump_targets(&browser, size); - annotate__compute_ipc(&browser, size, sym); - - browser.addr_width = browser.target_width = browser.min_addr_width = hex_width(size); - browser.max_addr_width = hex_width(sym->end); - browser.jumps_width = width_jumps(browser.max_jump_sources); - browser.nr_events = nr_pcnt; - browser.b.nr_entries = browser.nr_entries; + browser.b.width = notes->max_line_len; + browser.b.nr_entries = notes->nr_entries; browser.b.entries = ¬es->src->source, browser.b.width += 18; /* Percentage */ - if (annotate_browser__opts.hide_src_code) - annotate_browser__init_asm_mode(&browser); - - annotate_browser__update_addr_width(&browser); + if (notes->options->hide_src_code) + ui_browser__init_asm_mode(&browser.b); ret = annotate_browser__run(&browser, evsel, hbt); annotated_source__purge(notes->src); out_free_offsets: - free(browser.offsets); + zfree(¬es->offsets); return ret; } - -#define ANNOTATE_CFG(n) \ - { .name = #n, .value = &annotate_browser__opts.n, } - -/* - * Keep the entries sorted, they are bsearch'ed - */ -static struct annotate_config { - const char *name; - bool *value; -} annotate__configs[] = { - ANNOTATE_CFG(hide_src_code), - ANNOTATE_CFG(jump_arrows), - ANNOTATE_CFG(show_linenr), - ANNOTATE_CFG(show_nr_jumps), - ANNOTATE_CFG(show_nr_samples), - ANNOTATE_CFG(show_total_period), - ANNOTATE_CFG(use_offset), -}; - -#undef ANNOTATE_CFG - -static int annotate_config__cmp(const void *name, const void *cfgp) -{ - const struct annotate_config *cfg = cfgp; - - return strcmp(name, cfg->name); -} - -static int annotate__config(const char *var, const char *value, - void *data __maybe_unused) -{ - struct annotate_config *cfg; - const char *name; - - if (!strstarts(var, "annotate.")) - return 0; - - name = var + 9; - cfg = bsearch(name, annotate__configs, ARRAY_SIZE(annotate__configs), - sizeof(struct annotate_config), annotate_config__cmp); - - if (cfg == NULL) - ui__warning("%s variable unknown, ignoring...", var); - else - *cfg->value = perf_config_bool(name, value); - return 0; -} - -void annotate_browser__init(void) -{ - perf_config(annotate__config, NULL); -} diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 6495ee55d9c3..a96f62ca984a 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -32,8 +32,7 @@ extern void hist_browser__init_hpp(void); -static int perf_evsel_browser_title(struct hist_browser *browser, - char *bf, size_t size); +static int hists_browser__scnprintf_title(struct hist_browser *browser, char *bf, size_t size); static void hist_browser__update_nr_entries(struct hist_browser *hb); static struct rb_node *hists__filter_entries(struct rb_node *nd, @@ -62,6 +61,15 @@ static int hist_browser__get_folding(struct hist_browser *browser) return unfolded_rows; } +static void hist_browser__set_title_space(struct hist_browser *hb) +{ + struct ui_browser *browser = &hb->b; + struct hists *hists = hb->hists; + struct perf_hpp_list *hpp_list = hists->hpp_list; + + browser->extra_title_lines = hb->show_headers ? hpp_list->nr_header_lines : 0; +} + static u32 hist_browser__nr_entries(struct hist_browser *hb) { u32 nr_entries; @@ -82,10 +90,16 @@ static void hist_browser__update_rows(struct hist_browser *hb) struct ui_browser *browser = &hb->b; struct hists *hists = hb->hists; struct perf_hpp_list *hpp_list = hists->hpp_list; - u16 header_offset, index_row; + u16 index_row; - header_offset = hb->show_headers ? hpp_list->nr_header_lines : 0; - browser->rows = browser->height - header_offset; + if (!hb->show_headers) { + browser->rows += browser->extra_title_lines; + browser->extra_title_lines = 0; + return; + } + + browser->extra_title_lines = hpp_list->nr_header_lines; + browser->rows -= browser->extra_title_lines; /* * Verify if we were at the last line and that line isn't * visibe because we now show the header line(s). @@ -108,17 +122,6 @@ static void hist_browser__refresh_dimensions(struct ui_browser *browser) * changeset. */ ui_browser__refresh_dimensions(browser); - hist_browser__update_rows(hb); -} - -static void hist_browser__gotorc(struct hist_browser *browser, int row, int column) -{ - struct hists *hists = browser->hists; - struct perf_hpp_list *hpp_list = hists->hpp_list; - u16 header_offset; - - header_offset = browser->show_headers ? hpp_list->nr_header_lines : 0; - ui_browser__gotorc(&browser->b, row + header_offset, column); } static void hist_browser__reset(struct hist_browser *browser) @@ -656,9 +659,10 @@ int hist_browser__run(struct hist_browser *browser, const char *help, struct hist_entry *h = rb_entry(browser->b.top, struct hist_entry, rb_node); ui_helpline__pop(); - ui_helpline__fpush("%d: nr_ent=(%d,%d), rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", + ui_helpline__fpush("%d: nr_ent=(%d,%d), etl: %d, rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", seq++, browser->b.nr_entries, browser->hists->nr_entries, + browser->b.extra_title_lines, browser->b.rows, browser->b.index, browser->b.top_idx, @@ -733,7 +737,7 @@ static void hist_browser__show_callchain_entry(struct hist_browser *browser, } ui_browser__set_color(&browser->b, color); - hist_browser__gotorc(browser, row, 0); + ui_browser__gotorc(&browser->b, row, 0); ui_browser__write_nstring(&browser->b, " ", offset); ui_browser__printf(&browser->b, "%c", folded_sign); ui_browser__write_graph(&browser->b, show_annotated ? SLSMG_RARROW_CHAR : ' '); @@ -1227,6 +1231,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, int width = browser->b.width; char folded_sign = ' '; bool current_entry = ui_browser__is_current_entry(&browser->b, row); + bool use_callchain = hist_entry__has_callchains(entry) && symbol_conf.use_callchain; off_t row_offset = entry->row_offset; bool first = true; struct perf_hpp_fmt *fmt; @@ -1236,7 +1241,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, browser->selection = &entry->ms; } - if (symbol_conf.use_callchain) { + if (use_callchain) { hist_entry__init_have_children(entry); folded_sign = hist_entry__folded(entry); } @@ -1249,7 +1254,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, }; int column = 0; - hist_browser__gotorc(browser, row, 0); + ui_browser__gotorc(&browser->b, row, 0); hists__for_each_format(browser->hists, fmt) { char s[2048]; @@ -1272,7 +1277,7 @@ static int hist_browser__show_entry(struct hist_browser *browser, } if (first) { - if (symbol_conf.use_callchain) { + if (use_callchain) { ui_browser__printf(&browser->b, "%c ", folded_sign); width -= 2; } @@ -1358,7 +1363,7 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser, goto show_callchain; } - hist_browser__gotorc(browser, row, 0); + ui_browser__gotorc(&browser->b, row, 0); if (current_entry && browser->b.navkeypressed) ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED); @@ -1507,7 +1512,7 @@ static int hist_browser__show_no_entry(struct hist_browser *browser, browser->selection = NULL; } - hist_browser__gotorc(browser, row, 0); + ui_browser__gotorc(&browser->b, row, 0); if (current_entry && browser->b.navkeypressed) ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED); @@ -1579,7 +1584,7 @@ hists_browser__scnprintf_headers(struct hist_browser *browser, char *buf, int column = 0; int span = 0; - if (symbol_conf.use_callchain) { + if (hists__has_callchains(hists) && symbol_conf.use_callchain) { ret = scnprintf(buf, size, " "); if (advance_hpp_check(&dummy_hpp, ret)) return ret; @@ -1713,7 +1718,7 @@ static void hists_browser__headers(struct hist_browser *browser) hists_browser__scnprintf_headers(browser, headers, sizeof(headers), line); - ui_browser__gotorc(&browser->b, line, 0); + ui_browser__gotorc_title(&browser->b, line, 0); ui_browser__set_color(&browser->b, HE_COLORSET_ROOT); ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1); } @@ -1740,17 +1745,11 @@ static void ui_browser__hists_init_top(struct ui_browser *browser) static unsigned int hist_browser__refresh(struct ui_browser *browser) { unsigned row = 0; - u16 header_offset = 0; struct rb_node *nd; struct hist_browser *hb = container_of(browser, struct hist_browser, b); - struct hists *hists = hb->hists; - - if (hb->show_headers) { - struct perf_hpp_list *hpp_list = hists->hpp_list; + if (hb->show_headers) hist_browser__show_headers(hb); - header_offset = hpp_list->nr_header_lines; - } ui_browser__hists_init_top(browser); hb->he_selection = NULL; @@ -1788,7 +1787,7 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser) break; } - return row + header_offset; + return row; } static struct rb_node *hists__filter_entries(struct rb_node *nd, @@ -1989,7 +1988,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, bool first = true; int ret; - if (symbol_conf.use_callchain) { + if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) { folded_sign = hist_entry__folded(he); printed += fprintf(fp, "%c ", folded_sign); } @@ -2143,6 +2142,7 @@ void hist_browser__init(struct hist_browser *browser, browser->b.seek = ui_browser__hists_seek; browser->b.use_navkeypressed = true; browser->show_headers = symbol_conf.show_hist_headers; + hist_browser__set_title_space(browser); if (symbol_conf.report_hierarchy) { struct perf_hpp_list_node *fmt_node; @@ -2176,14 +2176,16 @@ struct hist_browser *hist_browser__new(struct hists *hists) static struct hist_browser * perf_evsel_browser__new(struct perf_evsel *evsel, struct hist_browser_timer *hbt, - struct perf_env *env) + struct perf_env *env, + struct annotation_options *annotation_opts) { struct hist_browser *browser = hist_browser__new(evsel__hists(evsel)); if (browser) { browser->hbt = hbt; browser->env = env; - browser->title = perf_evsel_browser_title; + browser->title = hists_browser__scnprintf_title; + browser->annotation_opts = annotation_opts; } return browser; } @@ -2209,79 +2211,11 @@ static inline bool is_report_browser(void *timer) return timer == NULL; } -static int perf_evsel_browser_title(struct hist_browser *browser, - char *bf, size_t size) +static int hists_browser__scnprintf_title(struct hist_browser *browser, char *bf, size_t size) { struct hist_browser_timer *hbt = browser->hbt; - struct hists *hists = browser->hists; - char unit; - int printed; - const struct dso *dso = hists->dso_filter; - const struct thread *thread = hists->thread_filter; - int socket_id = hists->socket_filter; - unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; - u64 nr_events = hists->stats.total_period; - struct perf_evsel *evsel = hists_to_evsel(hists); - const char *ev_name = perf_evsel__name(evsel); - char buf[512]; - size_t buflen = sizeof(buf); - char ref[30] = " show reference callgraph, "; - bool enable_ref = false; - - if (symbol_conf.filter_relative) { - nr_samples = hists->stats.nr_non_filtered_samples; - nr_events = hists->stats.total_non_filtered_period; - } - - if (perf_evsel__is_group_event(evsel)) { - struct perf_evsel *pos; + int printed = __hists__scnprintf_title(browser->hists, bf, size, !is_report_browser(hbt)); - perf_evsel__group_desc(evsel, buf, buflen); - ev_name = buf; - - for_each_group_member(pos, evsel) { - struct hists *pos_hists = evsel__hists(pos); - - if (symbol_conf.filter_relative) { - nr_samples += pos_hists->stats.nr_non_filtered_samples; - nr_events += pos_hists->stats.total_non_filtered_period; - } else { - nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE]; - nr_events += pos_hists->stats.total_period; - } - } - } - - if (symbol_conf.show_ref_callgraph && - strstr(ev_name, "call-graph=no")) - enable_ref = true; - nr_samples = convert_unit(nr_samples, &unit); - printed = scnprintf(bf, size, - "Samples: %lu%c of event '%s',%sEvent count (approx.): %" PRIu64, - nr_samples, unit, ev_name, enable_ref ? ref : " ", nr_events); - - - if (hists->uid_filter_str) - printed += snprintf(bf + printed, size - printed, - ", UID: %s", hists->uid_filter_str); - if (thread) { - if (hists__has(hists, thread)) { - printed += scnprintf(bf + printed, size - printed, - ", Thread: %s(%d)", - (thread->comm_set ? thread__comm_str(thread) : ""), - thread->tid); - } else { - printed += scnprintf(bf + printed, size - printed, - ", Thread: %s", - (thread->comm_set ? thread__comm_str(thread) : "")); - } - } - if (dso) - printed += scnprintf(bf + printed, size - printed, - ", DSO: %s", dso->short_name); - if (socket_id > -1) - printed += scnprintf(bf + printed, size - printed, - ", Processor Socket: %d", socket_id); if (!is_report_browser(hbt)) { struct perf_top *top = hbt->arg; @@ -2405,7 +2339,8 @@ do_annotate(struct hist_browser *browser, struct popup_action *act) struct hist_entry *he; int err; - if (!objdump_path && perf_env__lookup_objdump(browser->env)) + if (!browser->annotation_opts->objdump_path && + perf_env__lookup_objdump(browser->env, &browser->annotation_opts->objdump_path)) return 0; notes = symbol__annotation(act->ms.sym); @@ -2413,7 +2348,8 @@ do_annotate(struct hist_browser *browser, struct popup_action *act) return 0; evsel = hists_to_evsel(browser->hists); - err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt); + err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt, + browser->annotation_opts); he = hist_browser__selected_entry(browser); /* * offer option to annotate the other branch source or target @@ -2736,7 +2672,7 @@ static void hist_browser__update_percent_limit(struct hist_browser *hb, he->nr_rows = 0; } - if (!he->leaf || !symbol_conf.use_callchain) + if (!he->leaf || !hist_entry__has_callchains(he) || !symbol_conf.use_callchain) goto next; if (callchain_param.mode == CHAIN_GRAPH_REL) { @@ -2766,10 +2702,11 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, - bool warn_lost_event) + bool warn_lost_event, + struct annotation_options *annotation_opts) { struct hists *hists = evsel__hists(evsel); - struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env); + struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env, annotation_opts); struct branch_info *bi; #define MAX_OPTIONS 16 char *options[MAX_OPTIONS]; @@ -2783,7 +2720,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "h/?/F1 Show this window\n" \ "UP/DOWN/PGUP\n" \ "PGDN/SPACE Navigate\n" \ - "q/ESC/CTRL+C Exit browser\n\n" \ + "q/ESC/CTRL+C Exit browser or go back to previous screen\n\n" \ "For multiple event sessions:\n\n" \ "TAB/UNTAB Switch events\n\n" \ "For symbolic views (--sort has sym):\n\n" \ @@ -3131,6 +3068,7 @@ out: struct perf_evsel_menu { struct ui_browser b; struct perf_evsel *selection; + struct annotation_options *annotation_opts; bool lost_events, lost_events_warned; float min_pcnt; struct perf_env *env; @@ -3232,7 +3170,8 @@ browse_hists: true, hbt, menu->min_pcnt, menu->env, - warn_lost_event); + warn_lost_event, + menu->annotation_opts); ui_browser__show_title(&menu->b, title); switch (key) { case K_TAB: @@ -3291,7 +3230,8 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, - bool warn_lost_event) + bool warn_lost_event, + struct annotation_options *annotation_opts) { struct perf_evsel *pos; struct perf_evsel_menu menu = { @@ -3306,6 +3246,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, }, .min_pcnt = min_pcnt, .env = env, + .annotation_opts = annotation_opts, }; ui_helpline__push("Press ESC to exit"); @@ -3326,7 +3267,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, - bool warn_lost_event) + bool warn_lost_event, + struct annotation_options *annotation_opts) { int nr_entries = evlist->nr_entries; @@ -3336,7 +3278,8 @@ single_entry: return perf_evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt, - env, warn_lost_event); + env, warn_lost_event, + annotation_opts); } if (symbol_conf.event_group) { @@ -3354,5 +3297,6 @@ single_entry: return __perf_evlist__tui_browse_hists(evlist, nr_entries, help, hbt, min_pcnt, env, - warn_lost_event); + warn_lost_event, + annotation_opts); } diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h index 9428bee076f2..91d3e18b50aa 100644 --- a/tools/perf/ui/browsers/hists.h +++ b/tools/perf/ui/browsers/hists.h @@ -4,6 +4,8 @@ #include "ui/browser.h" +struct annotation_options; + struct hist_browser { struct ui_browser b; struct hists *hists; @@ -12,6 +14,7 @@ struct hist_browser { struct hist_browser_timer *hbt; struct pstack *pstack; struct perf_env *env; + struct annotation_options *annotation_opts; int print_seq; bool show_dso; bool show_headers; diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c index e03fa75f108a..5b8b8c637686 100644 --- a/tools/perf/ui/browsers/map.c +++ b/tools/perf/ui/browsers/map.c @@ -104,7 +104,7 @@ int map__browse(struct map *map) { struct map_browser mb = { .b = { - .entries = &map->dso->symbols[map->type], + .entries = &map->dso->symbols, .refresh = ui_browser__rb_tree_refresh, .seek = ui_browser__rb_tree_seek, .write = map_browser__write, diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index aeeaf15029f0..48428c9acd89 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -169,7 +169,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map, if (map->dso->annotate_warned) return -1; - err = symbol__annotate(sym, map, evsel, 0, NULL); + err = symbol__annotate(sym, map, evsel, 0, &annotation__default_options, NULL); if (err) { char msg[BUFSIZ]; symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 24e1ec201ffd..4ab663ec3e5e 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -382,7 +382,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, gtk_tree_store_set(store, &iter, col_idx++, s, -1); } - if (symbol_conf.use_callchain && hists__has(hists, sym)) { + if (hist_entry__has_callchains(h) && + symbol_conf.use_callchain && hists__has(hists, sym)) { if (callchain_param.mode == CHAIN_GRAPH_REL) total = symbol_conf.cumulate_callchain ? h->stat_acc->period : h->stat.period; @@ -479,7 +480,7 @@ static void perf_gtk__add_hierarchy_entries(struct hists *hists, } } - if (symbol_conf.use_callchain && he->leaf) { + if (he->leaf && hist_entry__has_callchains(he) && symbol_conf.use_callchain) { if (callchain_param.mode == CHAIN_GRAPH_REL) total = symbol_conf.cumulate_callchain ? he->stat_acc->period : he->stat.period; diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 706f6f1e9c7d..fe3dfaa64a91 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -207,7 +207,7 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b, if (ret) return ret; - if (a->thread != b->thread || !symbol_conf.use_callchain) + if (a->thread != b->thread || !hist_entry__has_callchains(a) || !symbol_conf.use_callchain) return 0; ret = b->callchain->max_depth - a->callchain->max_depth; diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 25dd1e0ecc58..74c4ae1f0a05 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -516,7 +516,7 @@ static int hist_entry__hierarchy_fprintf(struct hist_entry *he, } printed += putc('\n', fp); - if (symbol_conf.use_callchain && he->leaf) { + if (he->leaf && hist_entry__has_callchains(he) && symbol_conf.use_callchain) { u64 total = hists__total_period(hists); printed += hist_entry_callchain__fprintf(he, total, 0, fp); @@ -529,7 +529,7 @@ out: static int hist_entry__fprintf(struct hist_entry *he, size_t size, char *bf, size_t bfsz, FILE *fp, - bool use_callchain) + bool ignore_callchains) { int ret; int callchain_ret = 0; @@ -550,7 +550,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, ret = fprintf(fp, "%s\n", bf); - if (use_callchain) + if (hist_entry__has_callchains(he) && !ignore_callchains) callchain_ret = hist_entry_callchain__fprintf(he, total_period, 0, fp); @@ -755,7 +755,7 @@ int hists__fprintf_headers(struct hists *hists, FILE *fp) size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, - bool use_callchain) + bool ignore_callchains) { struct rb_node *nd; size_t ret = 0; @@ -799,7 +799,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, if (percent < min_pcnt) continue; - ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain); + ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, ignore_callchains); if (max_rows && ++nr_rows >= max_rows) break; @@ -819,8 +819,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, } if (h->ms.map == NULL && verbose > 1) { - __map_groups__fprintf_maps(h->thread->mg, - MAP__FUNCTION, fp); + map_groups__fprintf(h->thread->mg, fp); fprintf(fp, "%.10s end\n", graph_dotted_line); } } @@ -840,15 +839,11 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp) for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) { const char *name; - if (stats->nr_events[i] == 0) - continue; - name = perf_event__name(i); if (!strcmp(name, "UNKNOWN")) continue; - ret += fprintf(fp, "%16s events: %10d\n", name, - stats->nr_events[i]); + ret += fprintf(fp, "%16s events: %10d\n", name, stats->nr_events[i]); } return ret; diff --git a/tools/perf/util/Build b/tools/perf/util/Build index ea0a452550b0..7efe15b9618d 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -24,7 +24,6 @@ libperf-y += libstring.o libperf-y += bitmap.o libperf-y += hweight.o libperf-y += smt.o -libperf-y += quote.o libperf-y += strbuf.o libperf-y += string.o libperf-y += strlist.o @@ -88,6 +87,7 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt.o libperf-$(CONFIG_AUXTRACE) += intel-bts.o libperf-$(CONFIG_AUXTRACE) += arm-spe.o libperf-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o +libperf-$(CONFIG_AUXTRACE) += s390-cpumsf.o ifdef CONFIG_LIBOPENCSD libperf-$(CONFIG_AUXTRACE) += cs-etm.o @@ -106,6 +106,7 @@ libperf-y += units.o libperf-y += time-utils.o libperf-y += expr-bison.o libperf-y += branch.o +libperf-y += mem2node.o libperf-$(CONFIG_LIBBPF) += bpf-loader.o libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o @@ -151,6 +152,8 @@ libperf-y += perf-hooks.o libperf-$(CONFIG_CXX) += c++/ CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))" + # avoid compiler warnings in 32-bit mode CFLAGS_genelf_debug.o += -Wno-packed diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 28b233c3dcbe..28cd6a17491b 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -14,11 +14,14 @@ #include "sort.h" #include "build-id.h" #include "color.h" +#include "config.h" #include "cache.h" #include "symbol.h" +#include "units.h" #include "debug.h" #include "annotate.h" #include "evsel.h" +#include "evlist.h" #include "block-range.h" #include "string2.h" #include "arch/common.h" @@ -27,10 +30,28 @@ #include <linux/bitops.h> #include <linux/kernel.h> +/* FIXME: For the HE_COLORSET */ +#include "ui/browser.h" + +/* + * FIXME: Using the same values as slang.h, + * but that header may not be available everywhere + */ +#define LARROW_CHAR ((unsigned char)',') +#define RARROW_CHAR ((unsigned char)'+') +#define DARROW_CHAR ((unsigned char)'.') +#define UARROW_CHAR ((unsigned char)'-') + #include "sane_ctype.h" -const char *disassembler_style; -const char *objdump_path; +struct annotation_options annotation__default_options = { + .use_offset = true, + .jump_arrows = true, + .annotate_src = true, + .offset_level = ANNOTATION__OFFSET_JUMP_TARGETS, + .percent_type = PERCENT_PERIOD_LOCAL, +}; + static regex_t file_lineno; static struct ins_ops *ins__find(struct arch *arch, const char *name); @@ -184,9 +205,13 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2) return arch->ins_is_fused(arch, ins1, ins2); } -static int call__parse(struct arch *arch, struct ins_operands *ops, struct map *map) +static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) { char *endptr, *tok, *name; + struct map *map = ms->map; + struct addr_map_symbol target = { + .map = map, + }; ops->target.addr = strtoull(ops->raw, &endptr, 16); @@ -208,32 +233,42 @@ static int call__parse(struct arch *arch, struct ins_operands *ops, struct map * ops->target.name = strdup(name); *tok = '>'; - return ops->target.name == NULL ? -1 : 0; + if (ops->target.name == NULL) + return -1; +find_target: + target.addr = map__objdump_2mem(map, ops->target.addr); + + if (map_groups__find_ams(&target) == 0 && + map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr) + ops->target.sym = target.sym; + + return 0; indirect_call: tok = strchr(endptr, '*'); - if (tok == NULL) { - struct symbol *sym = map__find_symbol(map, map->map_ip(map, ops->target.addr)); - if (sym != NULL) - ops->target.name = strdup(sym->name); - else - ops->target.addr = 0; - return 0; - } + if (tok != NULL) { + endptr++; - ops->target.addr = strtoull(tok + 1, NULL, 16); - return 0; + /* Indirect call can use a non-rip register and offset: callq *0x8(%rbx). + * Do not parse such instruction. */ + if (strstr(endptr, "(%r") == NULL) + ops->target.addr = strtoull(endptr, NULL, 16); + } + goto find_target; } static int call__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops) { - if (ops->target.name) - return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name); + if (ops->target.sym) + return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name); if (ops->target.addr == 0) return ins__raw_scnprintf(ins, bf, size, ops); + if (ops->target.name) + return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name); + return scnprintf(bf, size, "%-6s *%" PRIx64, ins->name, ops->target.addr); } @@ -244,14 +279,45 @@ static struct ins_ops call_ops = { bool ins__is_call(const struct ins *ins) { - return ins->ops == &call_ops; + return ins->ops == &call_ops || ins->ops == &s390_call_ops; +} + +/* + * Prevents from matching commas in the comment section, e.g.: + * ffff200008446e70: b.cs ffff2000084470f4 <generic_exec_single+0x314> // b.hs, b.nlast + */ +static inline const char *validate_comma(const char *c, struct ins_operands *ops) +{ + if (ops->raw_comment && c > ops->raw_comment) + return NULL; + + return c; } -static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map *map __maybe_unused) +static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) { - const char *s = strchr(ops->raw, '+'); + struct map *map = ms->map; + struct symbol *sym = ms->sym; + struct addr_map_symbol target = { + .map = map, + }; const char *c = strchr(ops->raw, ','); + u64 start, end; + ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char); + c = validate_comma(c, ops); + + /* + * Examples of lines to parse for the _cpp_lex_token@@Base + * function: + * + * 1159e6c: jne 115aa32 <_cpp_lex_token@@Base+0xf92> + * 1159e8b: jne c469be <cpp_named_operator2name@@Base+0xa72> + * + * The first is a jump to an offset inside the same function, + * the second is to another function, i.e. that 0xa72 is an + * offset in the cpp_named_operator2name@@base function. + */ /* * skip over possible up to 2 operands to get to address, e.g.: * tbnz w0, #26, ffff0000083cd190 <security_file_permission+0xd0> @@ -260,6 +326,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op ops->target.addr = strtoull(c, NULL, 16); if (!ops->target.addr) { c = strchr(c, ','); + c = validate_comma(c, ops); if (c++ != NULL) ops->target.addr = strtoull(c, NULL, 16); } @@ -267,8 +334,36 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op ops->target.addr = strtoull(ops->raw, NULL, 16); } - if (s++ != NULL) { - ops->target.offset = strtoull(s, NULL, 16); + target.addr = map__objdump_2mem(map, ops->target.addr); + start = map->unmap_ip(map, sym->start), + end = map->unmap_ip(map, sym->end); + + ops->target.outside = target.addr < start || target.addr > end; + + /* + * FIXME: things like this in _cpp_lex_token (gcc's cc1 program): + + cpp_named_operator2name@@Base+0xa72 + + * Point to a place that is after the cpp_named_operator2name + * boundaries, i.e. in the ELF symbol table for cc1 + * cpp_named_operator2name is marked as being 32-bytes long, but it in + * fact is much larger than that, so we seem to need a symbols__find() + * routine that looks for >= current->start and < next_symbol->start, + * possibly just for C++ objects? + * + * For now lets just make some progress by marking jumps to outside the + * current function as call like. + * + * Actual navigation will come next, with further understanding of how + * the symbol searching and disassembly should be done. + */ + if (map_groups__find_ams(&target) == 0 && + map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr) + ops->target.sym = target.sym; + + if (!ops->target.outside) { + ops->target.offset = target.addr - start; ops->target.offset_avail = true; } else { ops->target.offset_avail = false; @@ -280,14 +375,21 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op static int jump__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops) { - const char *c = strchr(ops->raw, ','); + const char *c; if (!ops->target.addr || ops->target.offset < 0) return ins__raw_scnprintf(ins, bf, size, ops); + if (ops->target.outside && ops->target.sym != NULL) + return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name); + + c = strchr(ops->raw, ','); + c = validate_comma(c, ops); + if (c != NULL) { const char *c2 = strchr(c + 1, ','); + c2 = validate_comma(c2, ops); /* check for 3-op insn */ if (c2 != NULL) c = c2; @@ -340,7 +442,7 @@ static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep) return 0; } -static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map *map) +static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) { ops->locked.ops = zalloc(sizeof(*ops->locked.ops)); if (ops->locked.ops == NULL) @@ -355,7 +457,7 @@ static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map * goto out_free_ops; if (ops->locked.ins.ops->parse && - ops->locked.ins.ops->parse(arch, ops->locked.ops, map) < 0) + ops->locked.ins.ops->parse(arch, ops->locked.ops, ms) < 0) goto out_free_ops; return 0; @@ -398,7 +500,7 @@ static struct ins_ops lock_ops = { .scnprintf = lock__scnprintf, }; -static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *map __maybe_unused) +static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused) { char *s = strchr(ops->raw, ','), *target, *comment, prev; @@ -459,7 +561,7 @@ static struct ins_ops mov_ops = { .scnprintf = mov__scnprintf, }; -static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map *map __maybe_unused) +static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused) { char *target, *comment, *s, prev; @@ -603,10 +705,28 @@ static struct arch *arch__find(const char *name) return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp); } -int symbol__alloc_hist(struct symbol *sym) +static struct annotated_source *annotated_source__new(void) +{ + struct annotated_source *src = zalloc(sizeof(*src)); + + if (src != NULL) + INIT_LIST_HEAD(&src->source); + + return src; +} + +static __maybe_unused void annotated_source__delete(struct annotated_source *src) +{ + if (src == NULL) + return; + zfree(&src->histograms); + zfree(&src->cycles_hist); + free(src); +} + +static int annotated_source__alloc_histograms(struct annotated_source *src, + size_t size, int nr_hists) { - struct annotation *notes = symbol__annotation(sym); - size_t size = symbol__size(sym); size_t sizeof_sym_hist; /* @@ -626,17 +746,13 @@ int symbol__alloc_hist(struct symbol *sym) sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(struct sym_hist_entry)); /* Check for overflow in zalloc argument */ - if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src)) - / symbol_conf.nr_events) + if (sizeof_sym_hist > SIZE_MAX / nr_hists) return -1; - notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist); - if (notes->src == NULL) - return -1; - notes->src->sizeof_sym_hist = sizeof_sym_hist; - notes->src->nr_histograms = symbol_conf.nr_events; - INIT_LIST_HEAD(¬es->src->source); - return 0; + src->sizeof_sym_hist = sizeof_sym_hist; + src->nr_histograms = nr_hists; + src->histograms = calloc(nr_hists, sizeof_sym_hist) ; + return src->histograms ? 0 : -1; } /* The cycles histogram is lazily allocated. */ @@ -666,14 +782,11 @@ void symbol__annotate_zero_histograms(struct symbol *sym) pthread_mutex_unlock(¬es->lock); } -static int __symbol__account_cycles(struct annotation *notes, +static int __symbol__account_cycles(struct cyc_hist *ch, u64 start, unsigned offset, unsigned cycles, unsigned have_start) { - struct cyc_hist *ch; - - ch = notes->src->cycles_hist; /* * For now we can only account one basic block per * final jump. But multiple could be overlapping. @@ -685,6 +798,15 @@ static int __symbol__account_cycles(struct annotation *notes, ch[offset].num_aggr++; ch[offset].cycles_aggr += cycles; + if (cycles > ch[offset].cycles_max) + ch[offset].cycles_max = cycles; + + if (ch[offset].cycles_min) { + if (cycles && cycles < ch[offset].cycles_min) + ch[offset].cycles_min = cycles; + } else + ch[offset].cycles_min = cycles; + if (!have_start && ch[offset].have_start) return 0; if (ch[offset].num) { @@ -707,7 +829,7 @@ static int __symbol__account_cycles(struct annotation *notes, } static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, - struct annotation *notes, int evidx, u64 addr, + struct annotated_source *src, int evidx, u64 addr, struct perf_sample *sample) { unsigned offset; @@ -723,7 +845,12 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, } offset = addr - sym->start; - h = annotation__histogram(notes, evidx); + h = annotated_source__histogram(src, evidx); + if (h == NULL) { + pr_debug("%s(%d): ENOMEM! sym->name=%s, start=%#" PRIx64 ", addr=%#" PRIx64 ", end=%#" PRIx64 ", func: %d\n", + __func__, __LINE__, sym->name, sym->start, addr, sym->end, sym->type == STT_FUNC); + return -ENOMEM; + } h->nr_samples++; h->addr[offset].nr_samples++; h->period += sample->period; @@ -736,45 +863,69 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map, return 0; } -static struct annotation *symbol__get_annotation(struct symbol *sym, bool cycles) +static struct cyc_hist *symbol__cycles_hist(struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); if (notes->src == NULL) { - if (symbol__alloc_hist(sym) < 0) + notes->src = annotated_source__new(); + if (notes->src == NULL) return NULL; + goto alloc_cycles_hist; } - if (!notes->src->cycles_hist && cycles) { - if (symbol__alloc_hist_cycles(sym) < 0) + + if (!notes->src->cycles_hist) { +alloc_cycles_hist: + symbol__alloc_hist_cycles(sym); + } + + return notes->src->cycles_hist; +} + +struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists) +{ + struct annotation *notes = symbol__annotation(sym); + + if (notes->src == NULL) { + notes->src = annotated_source__new(); + if (notes->src == NULL) return NULL; + goto alloc_histograms; } - return notes; + + if (notes->src->histograms == NULL) { +alloc_histograms: + annotated_source__alloc_histograms(notes->src, symbol__size(sym), + nr_hists); + } + + return notes->src; } static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, - int evidx, u64 addr, + struct perf_evsel *evsel, u64 addr, struct perf_sample *sample) { - struct annotation *notes; + struct annotated_source *src; if (sym == NULL) return 0; - notes = symbol__get_annotation(sym, false); - if (notes == NULL) + src = symbol__hists(sym, evsel->evlist->nr_entries); + if (src == NULL) return -ENOMEM; - return __symbol__inc_addr_samples(sym, map, notes, evidx, addr, sample); + return __symbol__inc_addr_samples(sym, map, src, evsel->idx, addr, sample); } static int symbol__account_cycles(u64 addr, u64 start, struct symbol *sym, unsigned cycles) { - struct annotation *notes; + struct cyc_hist *cycles_hist; unsigned offset; if (sym == NULL) return 0; - notes = symbol__get_annotation(sym, true); - if (notes == NULL) + cycles_hist = symbol__cycles_hist(sym); + if (cycles_hist == NULL) return -ENOMEM; if (addr < sym->start || addr >= sym->end) return -ERANGE; @@ -786,7 +937,7 @@ static int symbol__account_cycles(u64 addr, u64 start, start = 0; } offset = addr - sym->start; - return __symbol__account_cycles(notes, + return __symbol__account_cycles(cycles_hist, start ? start - sym->start : 0, offset, cycles, !!start); @@ -826,26 +977,89 @@ int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, return err; } +static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64 end) +{ + unsigned n_insn = 0; + u64 offset; + + for (offset = start; offset <= end; offset++) { + if (notes->offsets[offset]) + n_insn++; + } + return n_insn; +} + +static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 end, struct cyc_hist *ch) +{ + unsigned n_insn; + u64 offset; + + n_insn = annotation__count_insn(notes, start, end); + if (n_insn && ch->num && ch->cycles) { + float ipc = n_insn / ((double)ch->cycles / (double)ch->num); + + /* Hide data when there are too many overlaps. */ + if (ch->reset >= 0x7fff || ch->reset >= ch->num / 2) + return; + + for (offset = start; offset <= end; offset++) { + struct annotation_line *al = notes->offsets[offset]; + + if (al) + al->ipc = ipc; + } + } +} + +void annotation__compute_ipc(struct annotation *notes, size_t size) +{ + u64 offset; + + if (!notes->src || !notes->src->cycles_hist) + return; + + pthread_mutex_lock(¬es->lock); + for (offset = 0; offset < size; ++offset) { + struct cyc_hist *ch; + + ch = ¬es->src->cycles_hist[offset]; + if (ch && ch->cycles) { + struct annotation_line *al; + + if (ch->have_start) + annotation__count_and_fill(notes, ch->start, offset, ch); + al = notes->offsets[offset]; + if (al && ch->num_aggr) { + al->cycles = ch->cycles_aggr / ch->num_aggr; + al->cycles_max = ch->cycles_max; + al->cycles_min = ch->cycles_min; + } + notes->have_cycles = true; + } + } + pthread_mutex_unlock(¬es->lock); +} + int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, - int evidx) + struct perf_evsel *evsel) { - return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr, sample); + return symbol__inc_addr_samples(ams->sym, ams->map, evsel, ams->al_addr, sample); } int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample, - int evidx, u64 ip) + struct perf_evsel *evsel, u64 ip) { - return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip, sample); + return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evsel, ip, sample); } -static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map *map) +static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms) { dl->ins.ops = ins__find(arch, dl->ins.name); if (!dl->ins.ops) return; - if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, map) < 0) + if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, ms) < 0) dl->ins.ops = NULL; } @@ -882,8 +1096,9 @@ out_free_name: struct annotate_args { size_t privsize; struct arch *arch; - struct map *map; + struct map_symbol ms; struct perf_evsel *evsel; + struct annotation_options *options; s64 offset; char *line; int line_nr; @@ -920,7 +1135,7 @@ annotation_line__new(struct annotate_args *args, size_t privsize) if (perf_evsel__is_group_event(evsel)) nr = evsel->nr_members; - size += sizeof(al->samples[0]) * nr; + size += sizeof(al->data[0]) * nr; al = zalloc(size); if (al) { @@ -929,7 +1144,7 @@ annotation_line__new(struct annotate_args *args, size_t privsize) al->offset = args->offset; al->line = strdup(args->line); al->line_nr = args->line_nr; - al->samples_nr = nr; + al->data_nr = nr; } return al; @@ -964,7 +1179,7 @@ static struct disasm_line *disasm_line__new(struct annotate_args *args) if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0) goto out_free_line; - disasm_line__init_ins(dl, args->arch, args->map); + disasm_line__init_ins(dl, args->arch, &args->ms); } } @@ -1109,7 +1324,8 @@ static int disasm_line__print(struct disasm_line *dl, u64 start, int addr_fmt_wi static int annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start, struct perf_evsel *evsel, u64 len, int min_pcnt, int printed, - int max_lines, struct annotation_line *queue, int addr_fmt_width) + int max_lines, struct annotation_line *queue, int addr_fmt_width, + int percent_type) { struct disasm_line *dl = container_of(al, struct disasm_line, al); static const char *prev_line; @@ -1121,13 +1337,19 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start const char *color; struct annotation *notes = symbol__annotation(sym); - for (i = 0; i < al->samples_nr; i++) { - struct annotation_data *sample = &al->samples[i]; + for (i = 0; i < al->data_nr; i++) { + double percent; + + percent = annotation_data__percent(&al->data[i], + percent_type); - if (sample->percent > max_percent) - max_percent = sample->percent; + if (percent > max_percent) + max_percent = percent; } + if (al->data_nr > nr_percent) + nr_percent = al->data_nr; + if (max_percent < min_pcnt) return -1; @@ -1139,7 +1361,8 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start if (queue == al) break; annotation_line__print(queue, sym, start, evsel, len, - 0, 0, 1, NULL, addr_fmt_width); + 0, 0, 1, NULL, addr_fmt_width, + percent_type); } } @@ -1160,18 +1383,20 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start } for (i = 0; i < nr_percent; i++) { - struct annotation_data *sample = &al->samples[i]; + struct annotation_data *data = &al->data[i]; + double percent; - color = get_percent_color(sample->percent); + percent = annotation_data__percent(data, percent_type); + color = get_percent_color(percent); if (symbol_conf.show_total_period) color_fprintf(stdout, color, " %11" PRIu64, - sample->he.period); + data->he.period); else if (symbol_conf.show_nr_samples) color_fprintf(stdout, color, " %7" PRIu64, - sample->he.nr_samples); + data->he.nr_samples); else - color_fprintf(stdout, color, " %7.2f", sample->percent); + color_fprintf(stdout, color, " %7.2f", percent); } printf(" : "); @@ -1222,7 +1447,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file, struct annotate_args *args, int *line_nr) { - struct map *map = args->map; + struct map *map = args->ms.map; struct annotation *notes = symbol__annotation(sym); struct disasm_line *dl; char *line = NULL, *parsed_line, *tmp, *tmp2; @@ -1269,6 +1494,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file, args->offset = offset; args->line = parsed_line; args->line_nr = *line_nr; + args->ms.sym = sym; dl = disasm_line__new(args); free(line); @@ -1277,14 +1503,14 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file, if (dl == NULL) return -1; - if (!disasm_line__has_offset(dl)) { + if (!disasm_line__has_local_offset(dl)) { dl->ops.target.offset = dl->ops.target.addr - map__rip_2objdump(map, sym->start); dl->ops.target.offset_avail = true; } - /* kcore has no symbols, so add the call target name */ - if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.name) { + /* kcore has no symbols, so add the call target symbol */ + if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.sym) { struct addr_map_symbol target = { .map = map, .addr = dl->ops.target.addr, @@ -1292,7 +1518,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file, if (!map_groups__find_ams(&target) && target.sym->start == target.al_addr) - dl->ops.target.name = strdup(target.sym->name); + dl->ops.target.sym = target.sym; } annotation_line__add(&dl->al, ¬es->src->source); @@ -1421,13 +1647,15 @@ fallback: static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) { - struct map *map = args->map; + struct annotation_options *opts = args->options; + struct map *map = args->ms.map; struct dso *dso = map->dso; - char command[PATH_MAX * 2]; + char *command; FILE *file; char symfs_filename[PATH_MAX]; struct kcore_extract kce; bool delete_extract = false; + bool decomp = false; int stdout_fd[2]; int lineno = 0; int nline; @@ -1461,28 +1689,34 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) tmp, sizeof(tmp)) < 0) goto out; + decomp = true; strcpy(symfs_filename, tmp); } - snprintf(command, sizeof(command), + err = asprintf(&command, "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand", - objdump_path ? objdump_path : "objdump", - disassembler_style ? "-M " : "", - disassembler_style ? disassembler_style : "", + opts->objdump_path ?: "objdump", + opts->disassembler_style ? "-M " : "", + opts->disassembler_style ?: "", map__rip_2objdump(map, sym->start), map__rip_2objdump(map, sym->end), - symbol_conf.annotate_asm_raw ? "" : "--no-show-raw", - symbol_conf.annotate_src ? "-S" : "", + opts->show_asm_raw ? "" : "--no-show-raw", + opts->annotate_src ? "-S" : "", symfs_filename, symfs_filename); + if (err < 0) { + pr_err("Failure allocating memory for the command to run\n"); + goto out_remove_tmp; + } + pr_debug("Executing: %s\n", command); err = -1; if (pipe(stdout_fd) < 0) { pr_err("Failure creating the pipe to run %s\n", command); - goto out_remove_tmp; + goto out_free_command; } pid = fork(); @@ -1509,7 +1743,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) * If we were using debug info should retry with * original binary. */ - goto out_remove_tmp; + goto out_free_command; } nline = 0; @@ -1537,10 +1771,12 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) fclose(file); err = 0; +out_free_command: + free(command); out_remove_tmp: close(stdout_fd[0]); - if (dso__needs_decompress(dso)) + if (decomp) unlink(symfs_filename); if (delete_extract) @@ -1550,37 +1786,48 @@ out: out_close_stdout: close(stdout_fd[1]); - goto out_remove_tmp; + goto out_free_command; } -static void calc_percent(struct sym_hist *hist, - struct annotation_data *sample, +static void calc_percent(struct sym_hist *sym_hist, + struct hists *hists, + struct annotation_data *data, s64 offset, s64 end) { unsigned int hits = 0; u64 period = 0; while (offset < end) { - hits += hist->addr[offset].nr_samples; - period += hist->addr[offset].period; + hits += sym_hist->addr[offset].nr_samples; + period += sym_hist->addr[offset].period; ++offset; } - if (hist->nr_samples) { - sample->he.period = period; - sample->he.nr_samples = hits; - sample->percent = 100.0 * hits / hist->nr_samples; + if (sym_hist->nr_samples) { + data->he.period = period; + data->he.nr_samples = hits; + data->percent[PERCENT_HITS_LOCAL] = 100.0 * hits / sym_hist->nr_samples; } + + if (hists->stats.nr_non_filtered_samples) + data->percent[PERCENT_HITS_GLOBAL] = 100.0 * hits / hists->stats.nr_non_filtered_samples; + + if (sym_hist->period) + data->percent[PERCENT_PERIOD_LOCAL] = 100.0 * period / sym_hist->period; + + if (hists->stats.total_period) + data->percent[PERCENT_PERIOD_GLOBAL] = 100.0 * period / hists->stats.total_period; } static void annotation__calc_percent(struct annotation *notes, - struct perf_evsel *evsel, s64 len) + struct perf_evsel *leader, s64 len) { struct annotation_line *al, *next; + struct perf_evsel *evsel; list_for_each_entry(al, ¬es->src->source, node) { s64 end; - int i; + int i = 0; if (al->offset == -1) continue; @@ -1588,14 +1835,17 @@ static void annotation__calc_percent(struct annotation *notes, next = annotation_line__next(al, ¬es->src->source); end = next ? next->offset : len; - for (i = 0; i < al->samples_nr; i++) { - struct annotation_data *sample; - struct sym_hist *hist; + for_each_group_evsel(evsel, leader) { + struct hists *hists = evsel__hists(evsel); + struct annotation_data *data; + struct sym_hist *sym_hist; - hist = annotation__histogram(notes, evsel->idx + i); - sample = &al->samples[i]; + BUG_ON(i >= al->data_nr); - calc_percent(hist, sample, al->offset, end); + sym_hist = annotation__histogram(notes, evsel->idx); + data = &al->data[i++]; + + calc_percent(sym_hist, hists, data, al->offset, end); } } } @@ -1609,12 +1859,13 @@ void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel) int symbol__annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, size_t privsize, + struct annotation_options *options, struct arch **parch) { struct annotate_args args = { .privsize = privsize, - .map = map, .evsel = evsel, + .options = options, }; struct perf_env *env = perf_evsel__env(evsel); const char *arch_name = perf_env__arch(env); @@ -1639,10 +1890,14 @@ int symbol__annotate(struct symbol *sym, struct map *map, } } + args.ms.map = map; + args.ms.sym = sym; + return symbol__disassemble(sym, &args); } -static void insert_source_line(struct rb_root *root, struct annotation_line *al) +static void insert_source_line(struct rb_root *root, struct annotation_line *al, + struct annotation_options *opts) { struct annotation_line *iter; struct rb_node **p = &root->rb_node; @@ -1655,8 +1910,10 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al) ret = strcmp(iter->path, al->path); if (ret == 0) { - for (i = 0; i < al->samples_nr; i++) - iter->samples[i].percent_sum += al->samples[i].percent; + for (i = 0; i < al->data_nr; i++) { + iter->data[i].percent_sum += annotation_data__percent(&al->data[i], + opts->percent_type); + } return; } @@ -1666,8 +1923,10 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al) p = &(*p)->rb_right; } - for (i = 0; i < al->samples_nr; i++) - al->samples[i].percent_sum = al->samples[i].percent; + for (i = 0; i < al->data_nr; i++) { + al->data[i].percent_sum = annotation_data__percent(&al->data[i], + opts->percent_type); + } rb_link_node(&al->rb_node, parent, p); rb_insert_color(&al->rb_node, root); @@ -1677,10 +1936,10 @@ static int cmp_source_line(struct annotation_line *a, struct annotation_line *b) { int i; - for (i = 0; i < a->samples_nr; i++) { - if (a->samples[i].percent_sum == b->samples[i].percent_sum) + for (i = 0; i < a->data_nr; i++) { + if (a->data[i].percent_sum == b->data[i].percent_sum) continue; - return a->samples[i].percent_sum > b->samples[i].percent_sum; + return a->data[i].percent_sum > b->data[i].percent_sum; } return 0; @@ -1745,8 +2004,8 @@ static void print_summary(struct rb_root *root, const char *filename) int i; al = rb_entry(node, struct annotation_line, rb_node); - for (i = 0; i < al->samples_nr; i++) { - percent = al->samples[i].percent_sum; + for (i = 0; i < al->data_nr; i++) { + percent = al->data[i].percent_sum; color = get_percent_color(percent); color_fprintf(stdout, color, " %7.2f", percent); @@ -1789,8 +2048,8 @@ static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start) } int symbol__annotate_printf(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, bool full_paths, - int min_pcnt, int max_lines, int context) + struct perf_evsel *evsel, + struct annotation_options *opts) { struct dso *dso = map->dso; char *filename; @@ -1802,28 +2061,35 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, u64 start = map__rip_2objdump(map, sym->start); int printed = 2, queue_len = 0, addr_fmt_width; int more = 0; + bool context = opts->context; u64 len; int width = symbol_conf.show_total_period ? 12 : 8; int graph_dotted_len; + char buf[512]; filename = strdup(dso->long_name); if (!filename) return -ENOMEM; - if (full_paths) + if (opts->full_path) d_filename = filename; else d_filename = basename(filename); len = symbol__size(sym); - if (perf_evsel__is_group_event(evsel)) + if (perf_evsel__is_group_event(evsel)) { width *= evsel->nr_members; + perf_evsel__group_desc(evsel, buf, sizeof(buf)); + evsel_name = buf; + } - graph_dotted_len = printf(" %-*.*s| Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n", + graph_dotted_len = printf(" %-*.*s| Source code & Disassembly of %s for %s (%" PRIu64 " samples, " + "percent: %s)\n", width, width, symbol_conf.show_total_period ? "Period" : symbol_conf.show_nr_samples ? "Samples" : "Percent", - d_filename, evsel_name, h->nr_samples); + d_filename, evsel_name, h->nr_samples, + percent_type_str(opts->percent_type)); printf("%-*.*s----\n", graph_dotted_len, graph_dotted_len, graph_dotted_line); @@ -1842,8 +2108,8 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, } err = annotation_line__print(pos, sym, start, evsel, len, - min_pcnt, printed, max_lines, - queue, addr_fmt_width); + opts->min_pcnt, printed, opts->max_lines, + queue, addr_fmt_width, opts->percent_type); switch (err) { case 0: @@ -1879,6 +2145,105 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, return more; } +static void FILE__set_percent_color(void *fp __maybe_unused, + double percent __maybe_unused, + bool current __maybe_unused) +{ +} + +static int FILE__set_jumps_percent_color(void *fp __maybe_unused, + int nr __maybe_unused, bool current __maybe_unused) +{ + return 0; +} + +static int FILE__set_color(void *fp __maybe_unused, int color __maybe_unused) +{ + return 0; +} + +static void FILE__printf(void *fp, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vfprintf(fp, fmt, args); + va_end(args); +} + +static void FILE__write_graph(void *fp, int graph) +{ + const char *s; + switch (graph) { + + case DARROW_CHAR: s = "↓"; break; + case UARROW_CHAR: s = "↑"; break; + case LARROW_CHAR: s = "←"; break; + case RARROW_CHAR: s = "→"; break; + default: s = "?"; break; + } + + fputs(s, fp); +} + +static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp, + struct annotation_options *opts) +{ + struct annotation *notes = symbol__annotation(sym); + struct annotation_write_ops wops = { + .first_line = true, + .obj = fp, + .set_color = FILE__set_color, + .set_percent_color = FILE__set_percent_color, + .set_jumps_percent_color = FILE__set_jumps_percent_color, + .printf = FILE__printf, + .write_graph = FILE__write_graph, + }; + struct annotation_line *al; + + list_for_each_entry(al, ¬es->src->source, node) { + if (annotation_line__filter(al, notes)) + continue; + annotation_line__write(al, notes, &wops, opts); + fputc('\n', fp); + wops.first_line = false; + } + + return 0; +} + +int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel, + struct annotation_options *opts) +{ + const char *ev_name = perf_evsel__name(evsel); + char buf[1024]; + char *filename; + int err = -1; + FILE *fp; + + if (asprintf(&filename, "%s.annotation", ms->sym->name) < 0) + return -1; + + fp = fopen(filename, "w"); + if (fp == NULL) + goto out_free_filename; + + if (perf_evsel__is_group_event(evsel)) { + perf_evsel__group_desc(evsel, buf, sizeof(buf)); + ev_name = buf; + } + + fprintf(fp, "%s() %s\nEvent: %s\n\n", + ms->sym->name, ms->map->dso->long_name, ev_name); + symbol__annotate_fprintf2(ms->sym, fp, opts); + + fclose(fp); + err = 0; +out_free_filename: + free(filename); + return err; +} + void symbol__annotate_zero_histogram(struct symbol *sym, int evidx) { struct annotation *notes = symbol__annotation(sym); @@ -1938,8 +2303,110 @@ size_t disasm__fprintf(struct list_head *head, FILE *fp) return printed; } +bool disasm_line__is_valid_local_jump(struct disasm_line *dl, struct symbol *sym) +{ + if (!dl || !dl->ins.ops || !ins__is_jump(&dl->ins) || + !disasm_line__has_local_offset(dl) || dl->ops.target.offset < 0 || + dl->ops.target.offset >= (s64)symbol__size(sym)) + return false; + + return true; +} + +void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym) +{ + u64 offset, size = symbol__size(sym); + + /* PLT symbols contain external offsets */ + if (strstr(sym->name, "@plt")) + return; + + for (offset = 0; offset < size; ++offset) { + struct annotation_line *al = notes->offsets[offset]; + struct disasm_line *dl; + + dl = disasm_line(al); + + if (!disasm_line__is_valid_local_jump(dl, sym)) + continue; + + al = notes->offsets[dl->ops.target.offset]; + + /* + * FIXME: Oops, no jump target? Buggy disassembler? Or do we + * have to adjust to the previous offset? + */ + if (al == NULL) + continue; + + if (++al->jump_sources > notes->max_jump_sources) + notes->max_jump_sources = al->jump_sources; + + ++notes->nr_jumps; + } +} + +void annotation__set_offsets(struct annotation *notes, s64 size) +{ + struct annotation_line *al; + + notes->max_line_len = 0; + + list_for_each_entry(al, ¬es->src->source, node) { + size_t line_len = strlen(al->line); + + if (notes->max_line_len < line_len) + notes->max_line_len = line_len; + al->idx = notes->nr_entries++; + if (al->offset != -1) { + al->idx_asm = notes->nr_asm_entries++; + /* + * FIXME: short term bandaid to cope with assembly + * routines that comes with labels in the same column + * as the address in objdump, sigh. + * + * E.g. copy_user_generic_unrolled + */ + if (al->offset < size) + notes->offsets[al->offset] = al; + } else + al->idx_asm = -1; + } +} + +static inline int width_jumps(int n) +{ + if (n >= 100) + return 5; + if (n / 10) + return 2; + return 1; +} + +void annotation__init_column_widths(struct annotation *notes, struct symbol *sym) +{ + notes->widths.addr = notes->widths.target = + notes->widths.min_addr = hex_width(symbol__size(sym)); + notes->widths.max_addr = hex_width(sym->end); + notes->widths.jumps = width_jumps(notes->max_jump_sources); +} + +void annotation__update_column_widths(struct annotation *notes) +{ + if (notes->options->use_offset) + notes->widths.target = notes->widths.min_addr; + else + notes->widths.target = notes->widths.max_addr; + + notes->widths.addr = notes->widths.target; + + if (notes->options->show_nr_jumps) + notes->widths.addr += notes->widths.jumps + 1; +} + static void annotation__calc_lines(struct annotation *notes, struct map *map, - struct rb_root *root, u64 start) + struct rb_root *root, + struct annotation_options *opts) { struct annotation_line *al; struct rb_root tmp_root = RB_ROOT; @@ -1948,55 +2415,83 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map, double percent_max = 0.0; int i; - for (i = 0; i < al->samples_nr; i++) { - struct annotation_data *sample; + for (i = 0; i < al->data_nr; i++) { + double percent; - sample = &al->samples[i]; + percent = annotation_data__percent(&al->data[i], + opts->percent_type); - if (sample->percent > percent_max) - percent_max = sample->percent; + if (percent > percent_max) + percent_max = percent; } if (percent_max <= 0.5) continue; - al->path = get_srcline(map->dso, start + al->offset, NULL, - false, true, start + al->offset); - insert_source_line(&tmp_root, al); + al->path = get_srcline(map->dso, notes->start + al->offset, NULL, + false, true, notes->start + al->offset); + insert_source_line(&tmp_root, al, opts); } resort_source_line(root, &tmp_root); } static void symbol__calc_lines(struct symbol *sym, struct map *map, - struct rb_root *root) + struct rb_root *root, + struct annotation_options *opts) { struct annotation *notes = symbol__annotation(sym); - u64 start = map__rip_2objdump(map, sym->start); - annotation__calc_lines(notes, map, root, start); + annotation__calc_lines(notes, map, root, opts); +} + +int symbol__tty_annotate2(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, + struct annotation_options *opts) +{ + struct dso *dso = map->dso; + struct rb_root source_line = RB_ROOT; + struct hists *hists = evsel__hists(evsel); + char buf[1024]; + + if (symbol__annotate2(sym, map, evsel, opts, NULL) < 0) + return -1; + + if (opts->print_lines) { + srcline_full_filename = opts->full_path; + symbol__calc_lines(sym, map, &source_line, opts); + print_summary(&source_line, dso->long_name); + } + + hists__scnprintf_title(hists, buf, sizeof(buf)); + fprintf(stdout, "%s, [percent: %s]\n%s() %s\n", + buf, percent_type_str(opts->percent_type), sym->name, dso->long_name); + symbol__annotate_fprintf2(sym, stdout, opts); + + annotated_source__purge(symbol__annotation(sym)->src); + + return 0; } int symbol__tty_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, bool print_lines, - bool full_paths, int min_pcnt, int max_lines) + struct perf_evsel *evsel, + struct annotation_options *opts) { struct dso *dso = map->dso; struct rb_root source_line = RB_ROOT; - if (symbol__annotate(sym, map, evsel, 0, NULL) < 0) + if (symbol__annotate(sym, map, evsel, 0, opts, NULL) < 0) return -1; symbol__calc_percent(sym, evsel); - if (print_lines) { - srcline_full_filename = full_paths; - symbol__calc_lines(sym, map, &source_line); + if (opts->print_lines) { + srcline_full_filename = opts->full_path; + symbol__calc_lines(sym, map, &source_line, opts); print_summary(&source_line, dso->long_name); } - symbol__annotate_printf(sym, map, evsel, full_paths, - min_pcnt, max_lines, 0); + symbol__annotate_printf(sym, map, evsel, opts); annotated_source__purge(symbol__annotation(sym)->src); @@ -2007,3 +2502,380 @@ bool ui__has_annotation(void) { return use_browser == 1 && perf_hpp_list.sym; } + + +static double annotation_line__max_percent(struct annotation_line *al, + struct annotation *notes, + unsigned int percent_type) +{ + double percent_max = 0.0; + int i; + + for (i = 0; i < notes->nr_events; i++) { + double percent; + + percent = annotation_data__percent(&al->data[i], + percent_type); + + if (percent > percent_max) + percent_max = percent; + } + + return percent_max; +} + +static void disasm_line__write(struct disasm_line *dl, struct annotation *notes, + void *obj, char *bf, size_t size, + void (*obj__printf)(void *obj, const char *fmt, ...), + void (*obj__write_graph)(void *obj, int graph)) +{ + if (dl->ins.ops && dl->ins.ops->scnprintf) { + if (ins__is_jump(&dl->ins)) { + bool fwd; + + if (dl->ops.target.outside) + goto call_like; + fwd = dl->ops.target.offset > dl->al.offset; + obj__write_graph(obj, fwd ? DARROW_CHAR : UARROW_CHAR); + obj__printf(obj, " "); + } else if (ins__is_call(&dl->ins)) { +call_like: + obj__write_graph(obj, RARROW_CHAR); + obj__printf(obj, " "); + } else if (ins__is_ret(&dl->ins)) { + obj__write_graph(obj, LARROW_CHAR); + obj__printf(obj, " "); + } else { + obj__printf(obj, " "); + } + } else { + obj__printf(obj, " "); + } + + disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset); +} + +static void __annotation_line__write(struct annotation_line *al, struct annotation *notes, + bool first_line, bool current_entry, bool change_color, int width, + void *obj, unsigned int percent_type, + int (*obj__set_color)(void *obj, int color), + void (*obj__set_percent_color)(void *obj, double percent, bool current), + int (*obj__set_jumps_percent_color)(void *obj, int nr, bool current), + void (*obj__printf)(void *obj, const char *fmt, ...), + void (*obj__write_graph)(void *obj, int graph)) + +{ + double percent_max = annotation_line__max_percent(al, notes, percent_type); + int pcnt_width = annotation__pcnt_width(notes), + cycles_width = annotation__cycles_width(notes); + bool show_title = false; + char bf[256]; + int printed; + + if (first_line && (al->offset == -1 || percent_max == 0.0)) { + if (notes->have_cycles) { + if (al->ipc == 0.0 && al->cycles == 0) + show_title = true; + } else + show_title = true; + } + + if (al->offset != -1 && percent_max != 0.0) { + int i; + + for (i = 0; i < notes->nr_events; i++) { + double percent; + + percent = annotation_data__percent(&al->data[i], percent_type); + + obj__set_percent_color(obj, percent, current_entry); + if (notes->options->show_total_period) { + obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period); + } else if (notes->options->show_nr_samples) { + obj__printf(obj, "%6" PRIu64 " ", + al->data[i].he.nr_samples); + } else { + obj__printf(obj, "%6.2f ", percent); + } + } + } else { + obj__set_percent_color(obj, 0, current_entry); + + if (!show_title) + obj__printf(obj, "%-*s", pcnt_width, " "); + else { + obj__printf(obj, "%-*s", pcnt_width, + notes->options->show_total_period ? "Period" : + notes->options->show_nr_samples ? "Samples" : "Percent"); + } + } + + if (notes->have_cycles) { + if (al->ipc) + obj__printf(obj, "%*.2f ", ANNOTATION__IPC_WIDTH - 1, al->ipc); + else if (!show_title) + obj__printf(obj, "%*s", ANNOTATION__IPC_WIDTH, " "); + else + obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC"); + + if (!notes->options->show_minmax_cycle) { + if (al->cycles) + obj__printf(obj, "%*" PRIu64 " ", + ANNOTATION__CYCLES_WIDTH - 1, al->cycles); + else if (!show_title) + obj__printf(obj, "%*s", + ANNOTATION__CYCLES_WIDTH, " "); + else + obj__printf(obj, "%*s ", + ANNOTATION__CYCLES_WIDTH - 1, + "Cycle"); + } else { + if (al->cycles) { + char str[32]; + + scnprintf(str, sizeof(str), + "%" PRIu64 "(%" PRIu64 "/%" PRIu64 ")", + al->cycles, al->cycles_min, + al->cycles_max); + + obj__printf(obj, "%*s ", + ANNOTATION__MINMAX_CYCLES_WIDTH - 1, + str); + } else if (!show_title) + obj__printf(obj, "%*s", + ANNOTATION__MINMAX_CYCLES_WIDTH, + " "); + else + obj__printf(obj, "%*s ", + ANNOTATION__MINMAX_CYCLES_WIDTH - 1, + "Cycle(min/max)"); + } + } + + obj__printf(obj, " "); + + if (!*al->line) + obj__printf(obj, "%-*s", width - pcnt_width - cycles_width, " "); + else if (al->offset == -1) { + if (al->line_nr && notes->options->show_linenr) + printed = scnprintf(bf, sizeof(bf), "%-*d ", notes->widths.addr + 1, al->line_nr); + else + printed = scnprintf(bf, sizeof(bf), "%-*s ", notes->widths.addr, " "); + obj__printf(obj, bf); + obj__printf(obj, "%-*s", width - printed - pcnt_width - cycles_width + 1, al->line); + } else { + u64 addr = al->offset; + int color = -1; + + if (!notes->options->use_offset) + addr += notes->start; + + if (!notes->options->use_offset) { + printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr); + } else { + if (al->jump_sources && + notes->options->offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) { + if (notes->options->show_nr_jumps) { + int prev; + printed = scnprintf(bf, sizeof(bf), "%*d ", + notes->widths.jumps, + al->jump_sources); + prev = obj__set_jumps_percent_color(obj, al->jump_sources, + current_entry); + obj__printf(obj, bf); + obj__set_color(obj, prev); + } +print_addr: + printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ", + notes->widths.target, addr); + } else if (ins__is_call(&disasm_line(al)->ins) && + notes->options->offset_level >= ANNOTATION__OFFSET_CALL) { + goto print_addr; + } else if (notes->options->offset_level == ANNOTATION__MAX_OFFSET_LEVEL) { + goto print_addr; + } else { + printed = scnprintf(bf, sizeof(bf), "%-*s ", + notes->widths.addr, " "); + } + } + + if (change_color) + color = obj__set_color(obj, HE_COLORSET_ADDR); + obj__printf(obj, bf); + if (change_color) + obj__set_color(obj, color); + + disasm_line__write(disasm_line(al), notes, obj, bf, sizeof(bf), obj__printf, obj__write_graph); + + obj__printf(obj, "%-*s", width - pcnt_width - cycles_width - 3 - printed, bf); + } + +} + +void annotation_line__write(struct annotation_line *al, struct annotation *notes, + struct annotation_write_ops *wops, + struct annotation_options *opts) +{ + __annotation_line__write(al, notes, wops->first_line, wops->current_entry, + wops->change_color, wops->width, wops->obj, + opts->percent_type, + wops->set_color, wops->set_percent_color, + wops->set_jumps_percent_color, wops->printf, + wops->write_graph); +} + +int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *evsel, + struct annotation_options *options, struct arch **parch) +{ + struct annotation *notes = symbol__annotation(sym); + size_t size = symbol__size(sym); + int nr_pcnt = 1, err; + + notes->offsets = zalloc(size * sizeof(struct annotation_line *)); + if (notes->offsets == NULL) + return -1; + + if (perf_evsel__is_group_event(evsel)) + nr_pcnt = evsel->nr_members; + + err = symbol__annotate(sym, map, evsel, 0, options, parch); + if (err) + goto out_free_offsets; + + notes->options = options; + + symbol__calc_percent(sym, evsel); + + notes->start = map__rip_2objdump(map, sym->start); + + annotation__set_offsets(notes, size); + annotation__mark_jump_targets(notes, sym); + annotation__compute_ipc(notes, size); + annotation__init_column_widths(notes, sym); + notes->nr_events = nr_pcnt; + + annotation__update_column_widths(notes); + + return 0; + +out_free_offsets: + zfree(¬es->offsets); + return -1; +} + +#define ANNOTATION__CFG(n) \ + { .name = #n, .value = &annotation__default_options.n, } + +/* + * Keep the entries sorted, they are bsearch'ed + */ +static struct annotation_config { + const char *name; + void *value; +} annotation__configs[] = { + ANNOTATION__CFG(hide_src_code), + ANNOTATION__CFG(jump_arrows), + ANNOTATION__CFG(offset_level), + ANNOTATION__CFG(show_linenr), + ANNOTATION__CFG(show_nr_jumps), + ANNOTATION__CFG(show_nr_samples), + ANNOTATION__CFG(show_total_period), + ANNOTATION__CFG(use_offset), +}; + +#undef ANNOTATION__CFG + +static int annotation_config__cmp(const void *name, const void *cfgp) +{ + const struct annotation_config *cfg = cfgp; + + return strcmp(name, cfg->name); +} + +static int annotation__config(const char *var, const char *value, + void *data __maybe_unused) +{ + struct annotation_config *cfg; + const char *name; + + if (!strstarts(var, "annotate.")) + return 0; + + name = var + 9; + cfg = bsearch(name, annotation__configs, ARRAY_SIZE(annotation__configs), + sizeof(struct annotation_config), annotation_config__cmp); + + if (cfg == NULL) + pr_debug("%s variable unknown, ignoring...", var); + else if (strcmp(var, "annotate.offset_level") == 0) { + perf_config_int(cfg->value, name, value); + + if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL) + *(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL; + else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL) + *(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL; + } else { + *(bool *)cfg->value = perf_config_bool(name, value); + } + return 0; +} + +void annotation_config__init(void) +{ + perf_config(annotation__config, NULL); + + annotation__default_options.show_total_period = symbol_conf.show_total_period; + annotation__default_options.show_nr_samples = symbol_conf.show_nr_samples; +} + +static unsigned int parse_percent_type(char *str1, char *str2) +{ + unsigned int type = (unsigned int) -1; + + if (!strcmp("period", str1)) { + if (!strcmp("local", str2)) + type = PERCENT_PERIOD_LOCAL; + else if (!strcmp("global", str2)) + type = PERCENT_PERIOD_GLOBAL; + } + + if (!strcmp("hits", str1)) { + if (!strcmp("local", str2)) + type = PERCENT_HITS_LOCAL; + else if (!strcmp("global", str2)) + type = PERCENT_HITS_GLOBAL; + } + + return type; +} + +int annotate_parse_percent_type(const struct option *opt, const char *_str, + int unset __maybe_unused) +{ + struct annotation_options *opts = opt->value; + unsigned int type; + char *str1, *str2; + int err = -1; + + str1 = strdup(_str); + if (!str1) + return -ENOMEM; + + str2 = strchr(str1, '-'); + if (!str2) + goto out; + + *str2++ = 0; + + type = parse_percent_type(str1, str2); + if (type == (unsigned int) -1) + type = parse_percent_type(str2, str1); + if (type != (unsigned int) -1) { + opts->percent_type = type; + err = 0; + } + +out: + free(str1); + return err; +} diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index ce427445671f..5399ba2321bb 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -11,6 +11,7 @@ #include <linux/list.h> #include <linux/rbtree.h> #include <pthread.h> +#include <asm/bug.h> struct ins_ops; @@ -21,12 +22,15 @@ struct ins { struct ins_operands { char *raw; + char *raw_comment; struct { char *raw; char *name; + struct symbol *sym; u64 addr; s64 offset; bool offset_avail; + bool outside; } target; union { struct { @@ -45,7 +49,7 @@ struct arch; struct ins_ops { void (*free)(struct ins_operands *ops); - int (*parse)(struct arch *arch, struct ins_operands *ops, struct map *map); + int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms); int (*scnprintf)(struct ins *ins, char *bf, size_t size, struct ins_operands *ops); }; @@ -57,6 +61,42 @@ bool ins__is_lock(const struct ins *ins); int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops); bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2); +#define ANNOTATION__IPC_WIDTH 6 +#define ANNOTATION__CYCLES_WIDTH 6 +#define ANNOTATION__MINMAX_CYCLES_WIDTH 19 + +struct annotation_options { + bool hide_src_code, + use_offset, + jump_arrows, + print_lines, + full_path, + show_linenr, + show_nr_jumps, + show_nr_samples, + show_total_period, + show_minmax_cycle, + show_asm_raw, + annotate_src; + u8 offset_level; + int min_pcnt; + int max_lines; + int context; + const char *objdump_path; + const char *disassembler_style; + unsigned int percent_type; +}; + +enum { + ANNOTATION__OFFSET_JUMP_TARGETS = 1, + ANNOTATION__OFFSET_CALL, + ANNOTATION__MAX_OFFSET_LEVEL, +}; + +#define ANNOTATION__MIN_OFFSET_LEVEL ANNOTATION__OFFSET_JUMP_TARGETS + +extern struct annotation_options annotation__default_options; + struct annotation; struct sym_hist_entry { @@ -64,8 +104,16 @@ struct sym_hist_entry { u64 period; }; +enum { + PERCENT_HITS_LOCAL, + PERCENT_HITS_GLOBAL, + PERCENT_PERIOD_LOCAL, + PERCENT_PERIOD_GLOBAL, + PERCENT_MAX, +}; + struct annotation_data { - double percent; + double percent[PERCENT_MAX]; double percent_sum; struct sym_hist_entry he; }; @@ -76,12 +124,17 @@ struct annotation_line { s64 offset; char *line; int line_nr; + int jump_sources; float ipc; u64 cycles; + u64 cycles_max; + u64 cycles_min; size_t privsize; char *path; - int samples_nr; - struct annotation_data samples[0]; + u32 idx; + int idx_asm; + int data_nr; + struct annotation_data data[0]; }; struct disasm_line { @@ -92,19 +145,71 @@ struct disasm_line { struct annotation_line al; }; +static inline double annotation_data__percent(struct annotation_data *data, + unsigned int which) +{ + return which < PERCENT_MAX ? data->percent[which] : -1; +} + +static inline const char *percent_type_str(unsigned int type) +{ + static const char *str[PERCENT_MAX] = { + "local hits", + "global hits", + "local period", + "global period", + }; + + if (WARN_ON(type >= PERCENT_MAX)) + return "N/A"; + + return str[type]; +} + static inline struct disasm_line *disasm_line(struct annotation_line *al) { return al ? container_of(al, struct disasm_line, al) : NULL; } -static inline bool disasm_line__has_offset(const struct disasm_line *dl) +/* + * Is this offset in the same function as the line it is used? + * asm functions jump to other functions, for instance. + */ +static inline bool disasm_line__has_local_offset(const struct disasm_line *dl) { - return dl->ops.target.offset_avail; + return dl->ops.target.offset_avail && !dl->ops.target.outside; } +/* + * Can we draw an arrow from the jump to its target, for instance? I.e. + * is the jump and its target in the same function? + */ +bool disasm_line__is_valid_local_jump(struct disasm_line *dl, struct symbol *sym); + void disasm_line__free(struct disasm_line *dl); struct annotation_line * annotation_line__next(struct annotation_line *pos, struct list_head *head); + +struct annotation_write_ops { + bool first_line, current_entry, change_color; + int width; + void *obj; + int (*set_color)(void *obj, int color); + void (*set_percent_color)(void *obj, double percent, bool current); + int (*set_jumps_percent_color)(void *obj, int nr, bool current); + void (*printf)(void *obj, const char *fmt, ...); + void (*write_graph)(void *obj, int graph); +}; + +void annotation_line__write(struct annotation_line *al, struct annotation *notes, + struct annotation_write_ops *ops, + struct annotation_options *opts); + +int __annotation__scnprintf_samples_period(struct annotation *notes, + char *bf, size_t size, + struct perf_evsel *evsel, + bool show_freq); + int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw); size_t disasm__fprintf(struct list_head *head, FILE *fp); void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel); @@ -119,6 +224,8 @@ struct cyc_hist { u64 start; u64 cycles; u64 cycles_aggr; + u64 cycles_max; + u64 cycles_min; u32 num; u32 num_aggr; u8 have_start; @@ -128,7 +235,11 @@ struct cyc_hist { /** struct annotated_source - symbols with hits have this attached as in sannotation * - * @histogram: Array of addr hit histograms per event being monitored + * @histograms: Array of addr hit histograms per event being monitored + * nr_histograms: This may not be the same as evsel->evlist->nr_entries if + * we have more than a group in a evlist, where we will want + * to see each group separately, that is why symbol__annotate2() + * sets src->nr_histograms to evsel->nr_members. * @lines: If 'print_lines' is specified, per source code line percentages * @source: source parsed from a disassembler like objdump -dS * @cyc_hist: Average cycles per basic block @@ -144,19 +255,64 @@ struct annotated_source { int nr_histograms; size_t sizeof_sym_hist; struct cyc_hist *cycles_hist; - struct sym_hist histograms[0]; + struct sym_hist *histograms; }; struct annotation { pthread_mutex_t lock; u64 max_coverage; + u64 start; + struct annotation_options *options; + struct annotation_line **offsets; + int nr_events; + int nr_jumps; + int max_jump_sources; + int nr_entries; + int nr_asm_entries; + u16 max_line_len; + struct { + u8 addr; + u8 jumps; + u8 target; + u8 min_addr; + u8 max_addr; + } widths; + bool have_cycles; struct annotated_source *src; }; +static inline int annotation__cycles_width(struct annotation *notes) +{ + if (notes->have_cycles && notes->options->show_minmax_cycle) + return ANNOTATION__IPC_WIDTH + ANNOTATION__MINMAX_CYCLES_WIDTH; + + return notes->have_cycles ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0; +} + +static inline int annotation__pcnt_width(struct annotation *notes) +{ + return (notes->options->show_total_period ? 12 : 7) * notes->nr_events; +} + +static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes) +{ + return notes->options->hide_src_code && al->offset == -1; +} + +void annotation__set_offsets(struct annotation *notes, s64 size); +void annotation__compute_ipc(struct annotation *notes, size_t size); +void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym); +void annotation__update_column_widths(struct annotation *notes); +void annotation__init_column_widths(struct annotation *notes, struct symbol *sym); + +static inline struct sym_hist *annotated_source__histogram(struct annotated_source *src, int idx) +{ + return ((void *)src->histograms) + (src->sizeof_sym_hist * idx); +} + static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx) { - return (((void *)¬es->src->histograms) + - (notes->src->sizeof_sym_hist * idx)); + return annotated_source__histogram(notes->src, idx); } static inline struct annotation *symbol__annotation(struct symbol *sym) @@ -165,21 +321,26 @@ static inline struct annotation *symbol__annotation(struct symbol *sym) } int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, - int evidx); + struct perf_evsel *evsel); int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, struct addr_map_symbol *start, unsigned cycles); int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample, - int evidx, u64 addr); + struct perf_evsel *evsel, u64 addr); -int symbol__alloc_hist(struct symbol *sym); +struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists); void symbol__annotate_zero_histograms(struct symbol *sym); int symbol__annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, size_t privsize, + struct annotation_options *options, struct arch **parch); +int symbol__annotate2(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, + struct annotation_options *options, + struct arch **parch); enum symbol_disassemble_errno { SYMBOL_ANNOTATE_ERRNO__SUCCESS = 0, @@ -202,33 +363,41 @@ int symbol__strerror_disassemble(struct symbol *sym, struct map *map, int errnum, char *buf, size_t buflen); int symbol__annotate_printf(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, bool full_paths, - int min_pcnt, int max_lines, int context); + struct perf_evsel *evsel, + struct annotation_options *options); void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); void annotated_source__purge(struct annotated_source *as); +int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel, + struct annotation_options *opts); + bool ui__has_annotation(void); int symbol__tty_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, bool print_lines, - bool full_paths, int min_pcnt, int max_lines); + struct perf_evsel *evsel, struct annotation_options *opts); + +int symbol__tty_annotate2(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, struct annotation_options *opts); #ifdef HAVE_SLANG_SUPPORT int symbol__tui_annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, - struct hist_browser_timer *hbt); + struct hist_browser_timer *hbt, + struct annotation_options *opts); #else static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, struct map *map __maybe_unused, struct perf_evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt - __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused, + struct annotation_options *opts __maybe_unused) { return 0; } #endif -extern const char *disassembler_style; +void annotation_config__init(void); +int annotate_parse_percent_type(const struct option *opt, const char *_str, + int unset); #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 6470ea2aa25e..db1511359c5e 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -56,6 +56,7 @@ #include "intel-pt.h" #include "intel-bts.h" #include "arm-spe.h" +#include "s390-cpumsf.h" #include "sane_ctype.h" #include "symbol/kallsyms.h" @@ -202,6 +203,9 @@ static int auxtrace_queues__grow(struct auxtrace_queues *queues, for (i = 0; i < queues->nr_queues; i++) { list_splice_tail(&queues->queue_array[i].head, &queue_array[i].head); + queue_array[i].tid = queues->queue_array[i].tid; + queue_array[i].cpu = queues->queue_array[i].cpu; + queue_array[i].set = queues->queue_array[i].set; queue_array[i].priv = queues->queue_array[i].priv; } @@ -233,9 +237,9 @@ static void *auxtrace_copy_data(u64 size, struct perf_session *session) return p; } -static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues, - unsigned int idx, - struct auxtrace_buffer *buffer) +static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues, + unsigned int idx, + struct auxtrace_buffer *buffer) { struct auxtrace_queue *queue; int err; @@ -286,7 +290,7 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues, return -ENOMEM; b->size = BUFFER_LIMIT_FOR_32_BIT; b->consecutive = consecutive; - err = auxtrace_queues__add_buffer(queues, idx, b); + err = auxtrace_queues__queue_buffer(queues, idx, b); if (err) { auxtrace_buffer__free(b); return err; @@ -302,31 +306,6 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues, return 0; } -static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues, - struct perf_session *session, - unsigned int idx, - struct auxtrace_buffer *buffer) -{ - if (session->one_mmap) { - buffer->data = buffer->data_offset - session->one_mmap_offset + - session->one_mmap_addr; - } else if (perf_data__is_pipe(session->data)) { - buffer->data = auxtrace_copy_data(buffer->size, session); - if (!buffer->data) - return -ENOMEM; - buffer->data_needs_freeing = true; - } else if (BITS_PER_LONG == 32 && - buffer->size > BUFFER_LIMIT_FOR_32_BIT) { - int err; - - err = auxtrace_queues__split_buffer(queues, idx, buffer); - if (err) - return err; - } - - return auxtrace_queues__add_buffer(queues, idx, buffer); -} - static bool filter_cpu(struct perf_session *session, int cpu) { unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap; @@ -334,45 +313,71 @@ static bool filter_cpu(struct perf_session *session, int cpu) return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap); } -int auxtrace_queues__add_event(struct auxtrace_queues *queues, - struct perf_session *session, - union perf_event *event, off_t data_offset, - struct auxtrace_buffer **buffer_ptr) +static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues, + struct perf_session *session, + unsigned int idx, + struct auxtrace_buffer *buffer, + struct auxtrace_buffer **buffer_ptr) { - struct auxtrace_buffer *buffer; - unsigned int idx; - int err; + int err = -ENOMEM; - if (filter_cpu(session, event->auxtrace.cpu)) + if (filter_cpu(session, buffer->cpu)) return 0; - buffer = zalloc(sizeof(struct auxtrace_buffer)); + buffer = memdup(buffer, sizeof(*buffer)); if (!buffer) return -ENOMEM; - buffer->pid = -1; - buffer->tid = event->auxtrace.tid; - buffer->cpu = event->auxtrace.cpu; - buffer->data_offset = data_offset; - buffer->offset = event->auxtrace.offset; - buffer->reference = event->auxtrace.reference; - buffer->size = event->auxtrace.size; - idx = event->auxtrace.idx; + if (session->one_mmap) { + buffer->data = buffer->data_offset - session->one_mmap_offset + + session->one_mmap_addr; + } else if (perf_data__is_pipe(session->data)) { + buffer->data = auxtrace_copy_data(buffer->size, session); + if (!buffer->data) + goto out_free; + buffer->data_needs_freeing = true; + } else if (BITS_PER_LONG == 32 && + buffer->size > BUFFER_LIMIT_FOR_32_BIT) { + err = auxtrace_queues__split_buffer(queues, idx, buffer); + if (err) + goto out_free; + } - err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer); + err = auxtrace_queues__queue_buffer(queues, idx, buffer); if (err) - goto out_err; + goto out_free; + /* FIXME: Doesn't work for split buffer */ if (buffer_ptr) *buffer_ptr = buffer; return 0; -out_err: +out_free: auxtrace_buffer__free(buffer); return err; } +int auxtrace_queues__add_event(struct auxtrace_queues *queues, + struct perf_session *session, + union perf_event *event, off_t data_offset, + struct auxtrace_buffer **buffer_ptr) +{ + struct auxtrace_buffer buffer = { + .pid = -1, + .tid = event->auxtrace.tid, + .cpu = event->auxtrace.cpu, + .data_offset = data_offset, + .offset = event->auxtrace.offset, + .reference = event->auxtrace.reference, + .size = event->auxtrace.size, + }; + unsigned int idx = event->auxtrace.idx; + + return auxtrace_queues__add_buffer(queues, session, idx, &buffer, + buffer_ptr); +} + static int auxtrace_queues__add_indexed_event(struct auxtrace_queues *queues, struct perf_session *session, off_t file_offset, size_t sz) @@ -919,6 +924,8 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused, return arm_spe_process_auxtrace_info(event, session); case PERF_AUXTRACE_CS_ETM: return cs_etm__process_auxtrace_info(event, session); + case PERF_AUXTRACE_S390_CPUMSF: + return s390_cpumsf_process_auxtrace_info(event, session); case PERF_AUXTRACE_UNKNOWN: default: return -EINVAL; @@ -1678,7 +1685,7 @@ struct sym_args { static bool kern_sym_match(struct sym_args *args, const char *name, char type) { /* A function with the same name, and global or the n'th found or any */ - return symbol_type__is_a(type, MAP__FUNCTION) && + return kallsyms__is_function(type) && !strcmp(name, args->name) && ((args->global && isupper(type)) || (args->selected && ++(args->cnt) == args->idx) || @@ -1783,7 +1790,7 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused, { struct sym_args *args = arg; - if (!symbol_type__is_a(type, MAP__FUNCTION)) + if (!kallsyms__is_function(type)) return 0; if (!args->started) { @@ -1914,7 +1921,7 @@ static void print_duplicate_syms(struct dso *dso, const char *sym_name) pr_err("Multiple symbols with name '%s'\n", sym_name); - sym = dso__first_symbol(dso, MAP__FUNCTION); + sym = dso__first_symbol(dso); while (sym) { if (dso_sym_match(sym, sym_name, &cnt, -1)) { pr_err("#%d\t0x%"PRIx64"\t%c\t%s\n", @@ -1944,7 +1951,7 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start, *start = 0; *size = 0; - sym = dso__first_symbol(dso, MAP__FUNCTION); + sym = dso__first_symbol(dso); while (sym) { if (*start) { if (!*size) @@ -1971,8 +1978,8 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start, static int addr_filter__entire_dso(struct addr_filter *filt, struct dso *dso) { - struct symbol *first_sym = dso__first_symbol(dso, MAP__FUNCTION); - struct symbol *last_sym = dso__last_symbol(dso, MAP__FUNCTION); + struct symbol *first_sym = dso__first_symbol(dso); + struct symbol *last_sym = dso__last_symbol(dso); if (!first_sym || !last_sym) { pr_err("Failed to determine filter for %s\nNo symbols found.\n", diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 453c148d2158..71fc3bd74299 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -44,6 +44,7 @@ enum auxtrace_type { PERF_AUXTRACE_INTEL_BTS, PERF_AUXTRACE_CS_ETM, PERF_AUXTRACE_ARM_SPE, + PERF_AUXTRACE_S390_CPUMSF, }; enum itrace_period_type { @@ -130,6 +131,7 @@ struct auxtrace_index { /** * struct auxtrace - session callbacks to allow AUX area data decoding. * @process_event: lets the decoder see all session events + * @process_auxtrace_event: process a PERF_RECORD_AUXTRACE event * @flush_events: process any remaining data * @free_events: free resources associated with event processing * @free: free resources associated with the session @@ -301,6 +303,7 @@ struct auxtrace_mmap_params { * @parse_snapshot_options: parse snapshot options * @reference: provide a 64-bit reference number for auxtrace_event * @read_finish: called after reading from an auxtrace mmap + * @alignment: alignment (if any) for AUX area data */ struct auxtrace_record { int (*recording_options)(struct auxtrace_record *itr, diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index af7ad814b2c3..47aac41349a2 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -66,7 +66,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name) } obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name); - if (IS_ERR(obj)) { + if (IS_ERR_OR_NULL(obj)) { pr_debug("bpf: failed to load buffer\n"); return ERR_PTR(-EINVAL); } @@ -102,14 +102,14 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source) pr_debug("bpf: successfull builtin compilation\n"); obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename); - if (!IS_ERR(obj) && llvm_param.dump_obj) + if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj) llvm__dump_obj(filename, obj_buf, obj_buf_sz); free(obj_buf); } else obj = bpf_object__open(filename); - if (IS_ERR(obj)) { + if (IS_ERR_OR_NULL(obj)) { pr_debug("bpf: failed to load %s\n", filename); return obj; } @@ -747,7 +747,9 @@ int bpf__load(struct bpf_object *obj) err = bpf_object__load(obj); if (err) { - pr_debug("bpf: load objects failed\n"); + char bf[128]; + libbpf_strerror(err, bf, sizeof(bf)); + pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf); return err; } return 0; @@ -1527,13 +1529,13 @@ int bpf__apply_obj_config(void) bpf_object__for_each_safe(obj, objtmp) \ bpf_map__for_each(pos, obj) -#define bpf__for_each_stdout_map(pos, obj, objtmp) \ +#define bpf__for_each_map_named(pos, obj, objtmp, name) \ bpf__for_each_map(pos, obj, objtmp) \ if (bpf_map__name(pos) && \ - (strcmp("__bpf_stdout__", \ + (strcmp(name, \ bpf_map__name(pos)) == 0)) -int bpf__setup_stdout(struct perf_evlist *evlist) +struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const char *name) { struct bpf_map_priv *tmpl_priv = NULL; struct bpf_object *obj, *tmp; @@ -1542,11 +1544,11 @@ int bpf__setup_stdout(struct perf_evlist *evlist) int err; bool need_init = false; - bpf__for_each_stdout_map(map, obj, tmp) { + bpf__for_each_map_named(map, obj, tmp, name) { struct bpf_map_priv *priv = bpf_map__priv(map); if (IS_ERR(priv)) - return -BPF_LOADER_ERRNO__INTERNAL; + return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL); /* * No need to check map type: type should have been @@ -1559,49 +1561,61 @@ int bpf__setup_stdout(struct perf_evlist *evlist) } if (!need_init) - return 0; + return NULL; if (!tmpl_priv) { - err = parse_events(evlist, "bpf-output/no-inherit=1,name=__bpf_stdout__/", - NULL); + char *event_definition = NULL; + + if (asprintf(&event_definition, "bpf-output/no-inherit=1,name=%s/", name) < 0) + return ERR_PTR(-ENOMEM); + + err = parse_events(evlist, event_definition, NULL); + free(event_definition); + if (err) { - pr_debug("ERROR: failed to create bpf-output event\n"); - return -err; + pr_debug("ERROR: failed to create the \"%s\" bpf-output event\n", name); + return ERR_PTR(-err); } evsel = perf_evlist__last(evlist); } - bpf__for_each_stdout_map(map, obj, tmp) { + bpf__for_each_map_named(map, obj, tmp, name) { struct bpf_map_priv *priv = bpf_map__priv(map); if (IS_ERR(priv)) - return -BPF_LOADER_ERRNO__INTERNAL; + return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL); if (priv) continue; if (tmpl_priv) { priv = bpf_map_priv__clone(tmpl_priv); if (!priv) - return -ENOMEM; + return ERR_PTR(-ENOMEM); err = bpf_map__set_priv(map, priv, bpf_map_priv__clear); if (err) { bpf_map_priv__clear(map, priv); - return err; + return ERR_PTR(err); } } else if (evsel) { struct bpf_map_op *op; op = bpf_map__add_newop(map, NULL); if (IS_ERR(op)) - return PTR_ERR(op); + return ERR_PTR(PTR_ERR(op)); op->op_type = BPF_MAP_OP_SET_EVSEL; op->v.evsel = evsel; } } - return 0; + return evsel; +} + +int bpf__setup_stdout(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__"); + return IS_ERR(evsel) ? PTR_ERR(evsel) : 0; } #define ERRNO_OFFSET(e) ((e) - __BPF_LOADER_ERRNO__START) @@ -1778,8 +1792,8 @@ int bpf__strerror_apply_obj_config(int err, char *buf, size_t size) return 0; } -int bpf__strerror_setup_stdout(struct perf_evlist *evlist __maybe_unused, - int err, char *buf, size_t size) +int bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused, + int err, char *buf, size_t size) { bpf__strerror_head(err, buf, size); bpf__strerror_end(buf, size); diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index 5d3aefd6fae7..62d245a90e1d 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -43,6 +43,7 @@ enum bpf_loader_errno { __BPF_LOADER_ERRNO__END, }; +struct perf_evsel; struct bpf_object; struct parse_events_term; #define PERF_BPF_PROBE_GROUP "perf_bpf_probe" @@ -82,9 +83,8 @@ int bpf__apply_obj_config(void); int bpf__strerror_apply_obj_config(int err, char *buf, size_t size); int bpf__setup_stdout(struct perf_evlist *evlist); -int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err, - char *buf, size_t size); - +struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const char *name); +int bpf__strerror_setup_output_event(struct perf_evlist *evlist, int err, char *buf, size_t size); #else #include <errno.h> @@ -138,6 +138,12 @@ bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused) return 0; } +static inline struct perf_evsel * +bpf__setup_output_event(struct perf_evlist *evlist __maybe_unused, const char *name __maybe_unused) +{ + return NULL; +} + static inline int __bpf_strerror(char *buf, size_t size) { @@ -193,11 +199,16 @@ bpf__strerror_apply_obj_config(int err __maybe_unused, } static inline int -bpf__strerror_setup_stdout(struct perf_evlist *evlist __maybe_unused, - int err __maybe_unused, char *buf, - size_t size) +bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused, + int err __maybe_unused, char *buf, size_t size) { return __bpf_strerror(buf, size); } + #endif + +static inline int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err, char *buf, size_t size) +{ + return bpf__strerror_setup_output_event(evlist, err, buf, size); +} #endif diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c index 29347756b0af..77e4891e17b0 100644 --- a/tools/perf/util/bpf-prologue.c +++ b/tools/perf/util/bpf-prologue.c @@ -61,7 +61,7 @@ check_pos(struct bpf_insn_pos *pos) /* * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see - * Documentation/trace/kprobetrace.txt) to size field of BPF_LDX_MEM + * Documentation/trace/kprobetrace.rst) to size field of BPF_LDX_MEM * instruction (BPF_{B,H,W,DW}). */ static int diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 7f8553630c4d..04b1d53e4bf9 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -47,9 +47,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, return -1; } - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al); - - if (al.map != NULL) + if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) al.map->dso->hit = 1; thread__put(thread); @@ -316,7 +314,6 @@ static int machine__write_buildid_table(struct machine *machine, struct feat_fd *fd) { int err = 0; - char nm[PATH_MAX]; struct dso *pos; u16 kmisc = PERF_RECORD_MISC_KERNEL, umisc = PERF_RECORD_MISC_USER; @@ -338,9 +335,8 @@ static int machine__write_buildid_table(struct machine *machine, name = pos->short_name; name_len = pos->short_name_len; } else if (dso__is_kcore(pos)) { - machine__mmap_name(machine, nm, sizeof(nm)); - name = nm; - name_len = strlen(nm); + name = machine->mmap_name; + name_len = strlen(name); } else { name = pos->long_name; name_len = pos->long_name_len; @@ -813,12 +809,10 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine) bool is_kallsyms = dso__is_kallsyms(dso); bool is_vdso = dso__is_vdso(dso); const char *name = dso->long_name; - char nm[PATH_MAX]; if (dso__is_kcore(dso)) { is_kallsyms = true; - machine__mmap_name(machine, nm, sizeof(nm)); - name = nm; + name = machine->mmap_name; } return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, dso->nsinfo, is_kallsyms, is_vdso); diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp index a4014d786676..7b042a5ebc68 100644 --- a/tools/perf/util/c++/clang-test.cpp +++ b/tools/perf/util/c++/clang-test.cpp @@ -41,7 +41,7 @@ int test__clang_to_IR(void) if (!M) return -1; for (llvm::Function& F : *M) - if (F.getName() == "bpf_func__SyS_epoll_wait") + if (F.getName() == "bpf_func__SyS_epoll_pwait") return 0; return -1; } diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index 1bfc946e37dc..89512504551b 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -9,6 +9,7 @@ * Copyright (C) 2016 Huawei Inc. */ +#include "clang/Basic/Version.h" #include "clang/CodeGen/CodeGenAction.h" #include "clang/Frontend/CompilerInvocation.h" #include "clang/Frontend/CompilerInstance.h" @@ -58,7 +59,8 @@ createCompilerInvocation(llvm::opt::ArgStringList CFlags, StringRef& Path, FrontendOptions& Opts = CI->getFrontendOpts(); Opts.Inputs.clear(); - Opts.Inputs.emplace_back(Path, IK_C); + Opts.Inputs.emplace_back(Path, + FrontendOptions::getInputKindForExtension("c")); return CI; } @@ -71,10 +73,17 @@ getModuleFromSource(llvm::opt::ArgStringList CFlags, Clang.setVirtualFileSystem(&*VFS); +#if CLANG_VERSION_MAJOR < 4 IntrusiveRefCntPtr<CompilerInvocation> CI = createCompilerInvocation(std::move(CFlags), Path, Clang.getDiagnostics()); Clang.setInvocation(&*CI); +#else + std::shared_ptr<CompilerInvocation> CI( + createCompilerInvocation(std::move(CFlags), Path, + Clang.getDiagnostics())); + Clang.setInvocation(CI); +#endif std::unique_ptr<CodeGenAction> Act(new EmitLLVMOnlyAction(&*LLVMCtx)); if (!Clang.ExecuteAction(*Act)) @@ -137,8 +146,15 @@ getBPFObjectFromModule(llvm::Module *Module) raw_svector_ostream ostream(*Buffer); legacy::PassManager PM; - if (TargetMachine->addPassesToEmitFile(PM, ostream, - TargetMachine::CGFT_ObjectFile)) { + bool NotAdded; +#if CLANG_VERSION_MAJOR < 7 + NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, + TargetMachine::CGFT_ObjectFile); +#else + NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, nullptr, + TargetMachine::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/cgroup.c b/tools/perf/util/cgroup.c index 984f69144f87..ccd02634a616 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -71,7 +71,7 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen) return -1; } -static int open_cgroup(char *name) +static int open_cgroup(const char *name) { char path[PATH_MAX + 1]; char mnt[PATH_MAX + 1]; @@ -81,7 +81,7 @@ static int open_cgroup(char *name) if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1)) return -1; - snprintf(path, PATH_MAX, "%s/%s", mnt, name); + scnprintf(path, PATH_MAX, "%s/%s", mnt, name); fd = open(path, O_RDONLY); if (fd == -1) @@ -90,41 +90,61 @@ static int open_cgroup(char *name) return fd; } -static int add_cgroup(struct perf_evlist *evlist, char *str) +static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, const char *str) { struct perf_evsel *counter; - struct cgroup_sel *cgrp = NULL; - int n; /* * check if cgrp is already defined, if so we reuse it */ evlist__for_each_entry(evlist, counter) { - cgrp = counter->cgrp; - if (!cgrp) + if (!counter->cgrp) continue; - if (!strcmp(cgrp->name, str)) { - refcount_inc(&cgrp->refcnt); - break; - } - - cgrp = NULL; + if (!strcmp(counter->cgrp->name, str)) + return cgroup__get(counter->cgrp); } - if (!cgrp) { - cgrp = zalloc(sizeof(*cgrp)); - if (!cgrp) - return -1; + return NULL; +} + +static struct cgroup *cgroup__new(const char *name) +{ + struct cgroup *cgroup = zalloc(sizeof(*cgroup)); - cgrp->name = str; - refcount_set(&cgrp->refcnt, 1); + if (cgroup != NULL) { + refcount_set(&cgroup->refcnt, 1); - cgrp->fd = open_cgroup(str); - if (cgrp->fd == -1) { - free(cgrp); - return -1; - } + cgroup->name = strdup(name); + if (!cgroup->name) + goto out_err; + cgroup->fd = open_cgroup(name); + if (cgroup->fd == -1) + goto out_free_name; } + return cgroup; + +out_free_name: + free(cgroup->name); +out_err: + free(cgroup); + return NULL; +} + +struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name) +{ + struct cgroup *cgroup = evlist__find_cgroup(evlist, name); + + return cgroup ?: cgroup__new(name); +} + +static int add_cgroup(struct perf_evlist *evlist, const char *str) +{ + struct perf_evsel *counter; + struct cgroup *cgrp = evlist__findnew_cgroup(evlist, str); + int n; + + if (!cgrp) + return -1; /* * find corresponding event * if add cgroup N, then need to find event N @@ -135,31 +155,58 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) goto found; n++; } - if (refcount_dec_and_test(&cgrp->refcnt)) - free(cgrp); + cgroup__put(cgrp); return -1; found: counter->cgrp = cgrp; return 0; } -void close_cgroup(struct cgroup_sel *cgrp) +static void cgroup__delete(struct cgroup *cgroup) +{ + close(cgroup->fd); + zfree(&cgroup->name); + free(cgroup); +} + +void cgroup__put(struct cgroup *cgrp) { if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) { - close(cgrp->fd); - zfree(&cgrp->name); - free(cgrp); + cgroup__delete(cgrp); } } -int parse_cgroups(const struct option *opt __maybe_unused, const char *str, +struct cgroup *cgroup__get(struct cgroup *cgroup) +{ + if (cgroup) + refcount_inc(&cgroup->refcnt); + return cgroup; +} + +static void evsel__set_default_cgroup(struct perf_evsel *evsel, struct cgroup *cgroup) +{ + if (evsel->cgrp == NULL) + evsel->cgrp = cgroup__get(cgroup); +} + +void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup) +{ + struct perf_evsel *evsel; + + evlist__for_each_entry(evlist, evsel) + evsel__set_default_cgroup(evsel, cgroup); +} + +int parse_cgroups(const struct option *opt, const char *str, int unset __maybe_unused) { struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; + struct perf_evsel *counter; + struct cgroup *cgrp = NULL; const char *p, *e, *eos = str + strlen(str); char *s; - int ret; + int ret, i; if (list_empty(&evlist->entries)) { fprintf(stderr, "must define events before cgroups\n"); @@ -177,10 +224,9 @@ int parse_cgroups(const struct option *opt __maybe_unused, const char *str, if (!s) return -1; ret = add_cgroup(evlist, s); - if (ret) { - free(s); + free(s); + if (ret) return -1; - } } /* nr_cgroups is increased een for empty cgroups */ nr_cgroups++; @@ -188,5 +234,18 @@ int parse_cgroups(const struct option *opt __maybe_unused, const char *str, break; str = p+1; } + /* for the case one cgroup combine to multiple events */ + i = 0; + if (nr_cgroups == 1) { + evlist__for_each_entry(evlist, counter) { + if (i == 0) + cgrp = counter->cgrp; + else { + counter->cgrp = cgrp; + refcount_inc(&cgrp->refcnt); + } + i++; + } + } return 0; } diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h index afafc87e9201..f033a80c1b14 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -6,7 +6,7 @@ struct option; -struct cgroup_sel { +struct cgroup { char *name; int fd; refcount_t refcnt; @@ -14,7 +14,16 @@ struct cgroup_sel { extern int nr_cgroups; /* number of explicit cgroups defined */ -void close_cgroup(struct cgroup_sel *cgrp); + +struct cgroup *cgroup__get(struct cgroup *cgroup); +void cgroup__put(struct cgroup *cgroup); + +struct perf_evlist; + +struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name); + +void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup); + int parse_cgroups(const struct option *opt, const char *str, int unset); #endif /* __CGROUP_H__ */ diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 7798a2cc8a86..31279a7bd919 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -20,9 +20,10 @@ static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,} static struct comm_str *comm_str__get(struct comm_str *cs) { - if (cs) - refcount_inc(&cs->refcnt); - return cs; + if (cs && refcount_inc_not_zero(&cs->refcnt)) + return cs; + + return NULL; } static void comm_str__put(struct comm_str *cs) @@ -67,9 +68,14 @@ struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root) parent = *p; iter = rb_entry(parent, struct comm_str, rb_node); + /* + * If we race with comm_str__put, iter->refcnt is 0 + * and it will be removed within comm_str__put call + * shortly, ignore it in this search. + */ cmp = strcmp(str, iter->str); - if (!cmp) - return comm_str__get(iter); + if (!cmp && comm_str__get(iter)) + return iter; if (cmp < 0) p = &(*p)->rb_left; diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h index ecca688a25fb..892e92e7e7fc 100644 --- a/tools/perf/util/compress.h +++ b/tools/perf/util/compress.h @@ -4,10 +4,12 @@ #ifdef HAVE_ZLIB_SUPPORT int gzip_decompress_to_file(const char *input, int output_fd); +bool gzip_is_compressed(const char *input); #endif #ifdef HAVE_LZMA_SUPPORT int lzma_decompress_to_file(const char *input, int output_fd); +bool lzma_is_compressed(const char *input); #endif #endif /* PERF_COMPRESS_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 84eb9393c7db..5ac157056cdf 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -707,6 +707,14 @@ struct perf_config_set *perf_config_set__new(void) return set; } +static int perf_config__init(void) +{ + if (config_set == NULL) + config_set = perf_config_set__new(); + + return config_set == NULL; +} + int perf_config(config_fn_t fn, void *data) { int ret = 0; @@ -714,7 +722,7 @@ int perf_config(config_fn_t fn, void *data) struct perf_config_section *section; struct perf_config_item *item; - if (config_set == NULL) + if (config_set == NULL && perf_config__init()) return -1; perf_config_set__for_each_entry(config_set, section, item) { @@ -735,12 +743,6 @@ int perf_config(config_fn_t fn, void *data) return ret; } -void perf_config__init(void) -{ - if (config_set == NULL) - config_set = perf_config_set__new(); -} - void perf_config__exit(void) { perf_config_set__delete(config_set); diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index baf82bf227ac..bd0a5897c76a 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -38,7 +38,6 @@ struct perf_config_set *perf_config_set__new(void); void perf_config_set__delete(struct perf_config_set *set); int perf_config_set__collect(struct perf_config_set *set, const char *file_name, const char *var, const char *value); -void perf_config__init(void); void perf_config__exit(void); void perf_config__refresh(void); diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 1fb01849f1c7..938def6d0bb9 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * SPDX-License-Identifier: GPL-2.0 - * * Copyright(C) 2015-2018 Linaro Limited. * * Author: Tor Jeremiassen <tor@ti.com> @@ -32,6 +31,8 @@ #endif #endif +#define CS_ETM_INVAL_ADDR 0xdeadbeefdeadbeefUL + struct cs_etm_decoder { void *data; void (*packet_printer)(const char *msg); @@ -78,6 +79,8 @@ int cs_etm_decoder__reset(struct cs_etm_decoder *decoder) { ocsd_datapath_resp_t dp_ret; + decoder->prev_return = OCSD_RESP_CONT; + dp_ret = ocsd_dt_process_data(decoder->dcd_tree, OCSD_OP_RESET, 0, 0, NULL, NULL); if (OCSD_DATA_RESP_IS_FATAL(dp_ret)) @@ -95,11 +98,19 @@ int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder, /* Nothing to do, might as well just return */ if (decoder->packet_count == 0) return 0; + /* + * The queueing process in function cs_etm_decoder__buffer_packet() + * increments the tail *before* using it. This is somewhat counter + * intuitive but it has the advantage of centralizing tail management + * at a single location. Because of that we need to follow the same + * heuristic with the head, i.e we increment it before using its + * value. Otherwise the first element of the packet queue is not + * used. + */ + decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1); *packet = decoder->packet_buffer[decoder->head]; - decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1); - decoder->packet_count--; return 1; @@ -252,17 +263,17 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder) decoder->tail = 0; decoder->packet_count = 0; for (i = 0; i < MAX_BUFFER; i++) { - decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL; - decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL; - decoder->packet_buffer[i].exc = false; - decoder->packet_buffer[i].exc_ret = false; - decoder->packet_buffer[i].cpu = INT_MIN; + decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[i].last_instr_taken_branch = false; + decoder->packet_buffer[i].exc = false; + decoder->packet_buffer[i].exc_ret = false; + decoder->packet_buffer[i].cpu = INT_MIN; } } static ocsd_datapath_resp_t cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder, - const ocsd_generic_trace_elem *elem, const u8 trace_chan_id, enum cs_etm_sample_type sample_type) { @@ -278,18 +289,16 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder, return OCSD_RESP_FATAL_SYS_ERR; et = decoder->tail; + et = (et + 1) & (MAX_BUFFER - 1); + decoder->tail = et; + decoder->packet_count++; + decoder->packet_buffer[et].sample_type = sample_type; - decoder->packet_buffer[et].start_addr = elem->st_addr; - decoder->packet_buffer[et].end_addr = elem->en_addr; decoder->packet_buffer[et].exc = false; decoder->packet_buffer[et].exc_ret = false; decoder->packet_buffer[et].cpu = *((int *)inode->priv); - - /* Wrap around if need be */ - et = (et + 1) & (MAX_BUFFER - 1); - - decoder->tail = et; - decoder->packet_count++; + decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR; + decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR; if (decoder->packet_count == MAX_BUFFER - 1) return OCSD_RESP_WAIT; @@ -297,6 +306,47 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder, return OCSD_RESP_CONT; } +static ocsd_datapath_resp_t +cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder, + const ocsd_generic_trace_elem *elem, + const uint8_t trace_chan_id) +{ + int ret = 0; + struct cs_etm_packet *packet; + + ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id, + CS_ETM_RANGE); + if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT) + return ret; + + packet = &decoder->packet_buffer[decoder->tail]; + + packet->start_addr = elem->st_addr; + packet->end_addr = elem->en_addr; + switch (elem->last_i_type) { + case OCSD_INSTR_BR: + case OCSD_INSTR_BR_INDIRECT: + packet->last_instr_taken_branch = elem->last_instr_exec; + break; + case OCSD_INSTR_ISB: + case OCSD_INSTR_DSB_DMB: + case OCSD_INSTR_OTHER: + default: + packet->last_instr_taken_branch = false; + break; + } + + return ret; +} + +static ocsd_datapath_resp_t +cs_etm_decoder__buffer_trace_on(struct cs_etm_decoder *decoder, + const uint8_t trace_chan_id) +{ + return cs_etm_decoder__buffer_packet(decoder, trace_chan_id, + CS_ETM_TRACE_ON); +} + static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer( const void *context, const ocsd_trc_index_t indx __maybe_unused, @@ -313,12 +363,13 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer( decoder->trace_on = false; break; case OCSD_GEN_TRC_ELEM_TRACE_ON: + resp = cs_etm_decoder__buffer_trace_on(decoder, + trace_chan_id); decoder->trace_on = true; break; case OCSD_GEN_TRC_ELEM_INSTR_RANGE: - resp = cs_etm_decoder__buffer_packet(decoder, elem, - trace_chan_id, - CS_ETM_RANGE); + resp = cs_etm_decoder__buffer_range(decoder, elem, + trace_chan_id); break; case OCSD_GEN_TRC_ELEM_EXCEPTION: decoder->packet_buffer[decoder->tail].exc = true; diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h index 3d2e6205d186..612b5755f742 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h @@ -23,13 +23,16 @@ struct cs_etm_buffer { }; enum cs_etm_sample_type { + CS_ETM_EMPTY = 0, CS_ETM_RANGE = 1 << 0, + CS_ETM_TRACE_ON = 1 << 1, }; struct cs_etm_packet { enum cs_etm_sample_type sample_type; u64 start_addr; u64 end_addr; + u8 last_instr_taken_branch; u8 exc; u8 exc_ret; int cpu; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index b9f0a53dfa65..2ae640257fdb 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * SPDX-License-Identifier: GPL-2.0 - * * Copyright(C) 2015-2018 Linaro Limited. * * Author: Tor Jeremiassen <tor@ti.com> @@ -32,6 +31,14 @@ #define MAX_TIMESTAMP (~0ULL) +/* + * A64 instructions are always 4 bytes + * + * Only A64 is supported, so can use this constant for converting between + * addresses and instruction counts, calculting offsets etc + */ +#define A64_INSTR_SIZE 4 + struct cs_etm_auxtrace { struct auxtrace auxtrace; struct auxtrace_queues queues; @@ -45,11 +52,15 @@ struct cs_etm_auxtrace { u8 snapshot_mode; u8 data_queued; u8 sample_branches; + u8 sample_instructions; int num_cpu; u32 auxtrace_type; u64 branches_sample_type; u64 branches_id; + u64 instructions_sample_type; + u64 instructions_sample_period; + u64 instructions_id; u64 **metadata; u64 kernel_start; unsigned int pmu_type; @@ -68,6 +79,12 @@ struct cs_etm_queue { u64 time; u64 timestamp; u64 offset; + u64 period_instructions; + struct branch_stack *last_branch; + struct branch_stack *last_branch_rb; + size_t last_branch_pos; + struct cs_etm_packet *prev_packet; + struct cs_etm_packet *packet; }; static int cs_etm__update_queues(struct cs_etm_auxtrace *etm); @@ -174,6 +191,16 @@ static void cs_etm__free_queue(void *priv) { struct cs_etm_queue *etmq = priv; + if (!etmq) + return; + + thread__zput(etmq->thread); + cs_etm_decoder__free(etmq->decoder); + zfree(&etmq->event_buf); + zfree(&etmq->last_branch); + zfree(&etmq->last_branch_rb); + zfree(&etmq->prev_packet); + zfree(&etmq->packet); free(etmq); } @@ -212,6 +239,7 @@ static void cs_etm__free(struct perf_session *session) for (i = 0; i < aux->num_cpu; i++) zfree(&aux->metadata[i]); + thread__zput(aux->unknown_thread); zfree(&aux->metadata); zfree(&aux); } @@ -242,9 +270,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address, thread = etmq->etm->unknown_thread; } - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, address, &al); - - if (!al.map || !al.map->dso) + if (!thread__find_map(thread, cpumode, address, &al) || !al.map->dso) return 0; if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR && @@ -270,11 +296,35 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm, struct cs_etm_decoder_params d_params; struct cs_etm_trace_params *t_params; struct cs_etm_queue *etmq; + size_t szp = sizeof(struct cs_etm_packet); etmq = zalloc(sizeof(*etmq)); if (!etmq) return NULL; + etmq->packet = zalloc(szp); + if (!etmq->packet) + goto out_free; + + if (etm->synth_opts.last_branch || etm->sample_branches) { + etmq->prev_packet = zalloc(szp); + if (!etmq->prev_packet) + goto out_free; + } + + if (etm->synth_opts.last_branch) { + size_t sz = sizeof(struct branch_stack); + + sz += etm->synth_opts.last_branch_sz * + sizeof(struct branch_entry); + etmq->last_branch = zalloc(sz); + if (!etmq->last_branch) + goto out_free; + etmq->last_branch_rb = zalloc(sz); + if (!etmq->last_branch_rb) + goto out_free; + } + etmq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE); if (!etmq->event_buf) goto out_free; @@ -329,6 +379,7 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm, goto out_free_decoder; etmq->offset = 0; + etmq->period_instructions = 0; return etmq; @@ -336,6 +387,10 @@ out_free_decoder: cs_etm_decoder__free(etmq->decoder); out_free: zfree(&etmq->event_buf); + zfree(&etmq->last_branch); + zfree(&etmq->last_branch_rb); + zfree(&etmq->prev_packet); + zfree(&etmq->packet); free(etmq); return NULL; @@ -389,6 +444,142 @@ static int cs_etm__update_queues(struct cs_etm_auxtrace *etm) return 0; } +static inline void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq) +{ + struct branch_stack *bs_src = etmq->last_branch_rb; + struct branch_stack *bs_dst = etmq->last_branch; + size_t nr = 0; + + /* + * Set the number of records before early exit: ->nr is used to + * determine how many branches to copy from ->entries. + */ + bs_dst->nr = bs_src->nr; + + /* + * Early exit when there is nothing to copy. + */ + if (!bs_src->nr) + return; + + /* + * As bs_src->entries is a circular buffer, we need to copy from it in + * two steps. First, copy the branches from the most recently inserted + * branch ->last_branch_pos until the end of bs_src->entries buffer. + */ + nr = etmq->etm->synth_opts.last_branch_sz - etmq->last_branch_pos; + memcpy(&bs_dst->entries[0], + &bs_src->entries[etmq->last_branch_pos], + sizeof(struct branch_entry) * nr); + + /* + * If we wrapped around at least once, the branches from the beginning + * of the bs_src->entries buffer and until the ->last_branch_pos element + * are older valid branches: copy them over. The total number of + * branches copied over will be equal to the number of branches asked by + * the user in last_branch_sz. + */ + if (bs_src->nr >= etmq->etm->synth_opts.last_branch_sz) { + memcpy(&bs_dst->entries[nr], + &bs_src->entries[0], + sizeof(struct branch_entry) * etmq->last_branch_pos); + } +} + +static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq) +{ + etmq->last_branch_pos = 0; + etmq->last_branch_rb->nr = 0; +} + +static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet) +{ + /* Returns 0 for the CS_ETM_TRACE_ON packet */ + if (packet->sample_type == CS_ETM_TRACE_ON) + return 0; + + /* + * The packet records the execution range with an exclusive end address + * + * A64 instructions are constant size, so the last executed + * instruction is A64_INSTR_SIZE before the end address + * Will need to do instruction level decode for T32 instructions as + * they can be variable size (not yet supported). + */ + return packet->end_addr - A64_INSTR_SIZE; +} + +static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet) +{ + /* Returns 0 for the CS_ETM_TRACE_ON packet */ + if (packet->sample_type == CS_ETM_TRACE_ON) + return 0; + + return packet->start_addr; +} + +static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet) +{ + /* + * Only A64 instructions are currently supported, so can get + * instruction count by dividing. + * Will need to do instruction level decode for T32 instructions as + * they can be variable size (not yet supported). + */ + return (packet->end_addr - packet->start_addr) / A64_INSTR_SIZE; +} + +static inline u64 cs_etm__instr_addr(const struct cs_etm_packet *packet, + u64 offset) +{ + /* + * Only A64 instructions are currently supported, so can get + * instruction address by muliplying. + * Will need to do instruction level decode for T32 instructions as + * they can be variable size (not yet supported). + */ + return packet->start_addr + offset * A64_INSTR_SIZE; +} + +static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq) +{ + struct branch_stack *bs = etmq->last_branch_rb; + struct branch_entry *be; + + /* + * The branches are recorded in a circular buffer in reverse + * chronological order: we start recording from the last element of the + * buffer down. After writing the first element of the stack, move the + * insert position back to the end of the buffer. + */ + if (!etmq->last_branch_pos) + etmq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz; + + etmq->last_branch_pos -= 1; + + be = &bs->entries[etmq->last_branch_pos]; + be->from = cs_etm__last_executed_instr(etmq->prev_packet); + be->to = cs_etm__first_executed_instr(etmq->packet); + /* No support for mispredict */ + be->flags.mispred = 0; + be->flags.predicted = 1; + + /* + * Increment bs->nr until reaching the number of last branches asked by + * the user on the command line. + */ + if (bs->nr < etmq->etm->synth_opts.last_branch_sz) + bs->nr += 1; +} + +static int cs_etm__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 int cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq) { @@ -433,8 +624,8 @@ cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq) return buff->len; } -static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm, - struct auxtrace_queue *queue) +static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm, + struct auxtrace_queue *queue) { struct cs_etm_queue *etmq = queue->priv; @@ -453,35 +644,105 @@ static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm, } } +static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq, + u64 addr, u64 period) +{ + int ret = 0; + struct cs_etm_auxtrace *etm = etmq->etm; + union perf_event *event = etmq->event_buf; + struct perf_sample sample = {.ip = 0,}; + + event->sample.header.type = PERF_RECORD_SAMPLE; + event->sample.header.misc = PERF_RECORD_MISC_USER; + event->sample.header.size = sizeof(struct perf_event_header); + + sample.ip = addr; + sample.pid = etmq->pid; + sample.tid = etmq->tid; + sample.id = etmq->etm->instructions_id; + sample.stream_id = etmq->etm->instructions_id; + sample.period = period; + sample.cpu = etmq->packet->cpu; + sample.flags = 0; + sample.insn_len = 1; + sample.cpumode = event->header.misc; + + if (etm->synth_opts.last_branch) { + cs_etm__copy_last_branch_rb(etmq); + sample.branch_stack = etmq->last_branch; + } + + if (etm->synth_opts.inject) { + ret = cs_etm__inject_event(event, &sample, + etm->instructions_sample_type); + if (ret) + return ret; + } + + ret = perf_session__deliver_synth_event(etm->session, event, &sample); + + if (ret) + pr_err( + "CS ETM Trace: failed to deliver instruction event, error %d\n", + ret); + + if (etm->synth_opts.last_branch) + cs_etm__reset_last_branch_rb(etmq); + + return ret; +} + /* * The cs etm packet encodes an instruction range between a branch target * and the next taken branch. Generate sample accordingly. */ -static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq, - struct cs_etm_packet *packet) +static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq) { int ret = 0; struct cs_etm_auxtrace *etm = etmq->etm; struct perf_sample sample = {.ip = 0,}; union perf_event *event = etmq->event_buf; - u64 start_addr = packet->start_addr; - u64 end_addr = packet->end_addr; + struct dummy_branch_stack { + u64 nr; + struct branch_entry entries; + } dummy_bs; event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = PERF_RECORD_MISC_USER; event->sample.header.size = sizeof(struct perf_event_header); - sample.ip = start_addr; + sample.ip = cs_etm__last_executed_instr(etmq->prev_packet); sample.pid = etmq->pid; sample.tid = etmq->tid; - sample.addr = end_addr; + sample.addr = cs_etm__first_executed_instr(etmq->packet); sample.id = etmq->etm->branches_id; sample.stream_id = etmq->etm->branches_id; sample.period = 1; - sample.cpu = packet->cpu; + sample.cpu = etmq->packet->cpu; sample.flags = 0; sample.cpumode = PERF_RECORD_MISC_USER; + /* + * perf report cannot handle events without a branch stack + */ + if (etm->synth_opts.last_branch) { + dummy_bs = (struct dummy_branch_stack){ + .nr = 1, + .entries = { + .from = sample.ip, + .to = sample.addr, + }, + }; + sample.branch_stack = (struct branch_stack *)&dummy_bs; + } + + if (etm->synth_opts.inject) { + ret = cs_etm__inject_event(event, &sample, + etm->branches_sample_type); + if (ret) + return ret; + } + ret = perf_session__deliver_synth_event(etm->session, event, &sample); if (ret) @@ -578,6 +839,24 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, etm->sample_branches = true; etm->branches_sample_type = attr.sample_type; etm->branches_id = id; + id += 1; + attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR; + } + + if (etm->synth_opts.last_branch) + attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + + if (etm->synth_opts.instructions) { + attr.config = PERF_COUNT_HW_INSTRUCTIONS; + attr.sample_period = etm->synth_opts.period; + etm->instructions_sample_period = attr.sample_period; + err = cs_etm__synth_event(session, &attr, id); + if (err) + return err; + etm->sample_instructions = true; + etm->instructions_sample_type = attr.sample_type; + etm->instructions_id = id; + id += 1; } return 0; @@ -585,25 +864,139 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, static int cs_etm__sample(struct cs_etm_queue *etmq) { + struct cs_etm_auxtrace *etm = etmq->etm; + struct cs_etm_packet *tmp; int ret; - struct cs_etm_packet packet; + u64 instrs_executed; - while (1) { - ret = cs_etm_decoder__get_packet(etmq->decoder, &packet); - if (ret <= 0) + instrs_executed = cs_etm__instr_count(etmq->packet); + etmq->period_instructions += instrs_executed; + + /* + * Record a branch when the last instruction in + * PREV_PACKET is a branch. + */ + if (etm->synth_opts.last_branch && + etmq->prev_packet && + etmq->prev_packet->sample_type == CS_ETM_RANGE && + etmq->prev_packet->last_instr_taken_branch) + cs_etm__update_last_branch_rb(etmq); + + if (etm->sample_instructions && + etmq->period_instructions >= etm->instructions_sample_period) { + /* + * Emit instruction sample periodically + * TODO: allow period to be defined in cycles and clock time + */ + + /* Get number of instructions executed after the sample point */ + u64 instrs_over = etmq->period_instructions - + etm->instructions_sample_period; + + /* + * Calculate the address of the sampled instruction (-1 as + * sample is reported as though instruction has just been + * executed, but PC has not advanced to next instruction) + */ + u64 offset = (instrs_executed - instrs_over - 1); + u64 addr = cs_etm__instr_addr(etmq->packet, offset); + + ret = cs_etm__synth_instruction_sample( + etmq, addr, etm->instructions_sample_period); + if (ret) return ret; + /* Carry remaining instructions into next sample period */ + etmq->period_instructions = instrs_over; + } + + if (etm->sample_branches && etmq->prev_packet) { + bool generate_sample = false; + + /* Generate sample for tracing on packet */ + if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON) + generate_sample = true; + + /* Generate sample for branch taken packet */ + if (etmq->prev_packet->sample_type == CS_ETM_RANGE && + etmq->prev_packet->last_instr_taken_branch) + generate_sample = true; + + if (generate_sample) { + ret = cs_etm__synth_branch_sample(etmq); + if (ret) + return ret; + } + } + + if (etm->sample_branches || etm->synth_opts.last_branch) { /* - * If the packet contains an instruction range, generate an - * instruction sequence event. + * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for + * the next incoming packet. */ - if (packet.sample_type & CS_ETM_RANGE) - cs_etm__synth_branch_sample(etmq, &packet); + tmp = etmq->packet; + etmq->packet = etmq->prev_packet; + etmq->prev_packet = tmp; } return 0; } +static int cs_etm__flush(struct cs_etm_queue *etmq) +{ + int err = 0; + struct cs_etm_auxtrace *etm = etmq->etm; + struct cs_etm_packet *tmp; + + if (!etmq->prev_packet) + return 0; + + /* Handle start tracing packet */ + if (etmq->prev_packet->sample_type == CS_ETM_EMPTY) + goto swap_packet; + + if (etmq->etm->synth_opts.last_branch && + etmq->prev_packet->sample_type == CS_ETM_RANGE) { + /* + * Generate a last branch event for the branches left in the + * circular buffer at the end of the trace. + * + * Use the address of the end of the last reported execution + * range + */ + u64 addr = cs_etm__last_executed_instr(etmq->prev_packet); + + err = cs_etm__synth_instruction_sample( + etmq, addr, + etmq->period_instructions); + if (err) + return err; + + etmq->period_instructions = 0; + + } + + if (etm->sample_branches && + etmq->prev_packet->sample_type == CS_ETM_RANGE) { + err = cs_etm__synth_branch_sample(etmq); + if (err) + return err; + } + +swap_packet: + if (etmq->etm->synth_opts.last_branch) { + /* + * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for + * the next incoming packet. + */ + tmp = etmq->packet; + etmq->packet = etmq->prev_packet; + etmq->prev_packet = tmp; + } + + return err; +} + static int cs_etm__run_decoder(struct cs_etm_queue *etmq) { struct cs_etm_auxtrace *etm = etmq->etm; @@ -615,45 +1008,79 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq) etm->kernel_start = machine__kernel_start(etm->machine); /* Go through each buffer in the queue and decode them one by one */ -more: - buffer_used = 0; - memset(&buffer, 0, sizeof(buffer)); - err = cs_etm__get_trace(&buffer, etmq); - if (err <= 0) - return err; - /* - * We cannot assume consecutive blocks in the data file are contiguous, - * reset the decoder to force re-sync. - */ - err = cs_etm_decoder__reset(etmq->decoder); - if (err != 0) - return err; - - /* Run trace decoder until buffer consumed or end of trace */ - do { - processed = 0; - - err = cs_etm_decoder__process_data_block( - etmq->decoder, - etmq->offset, - &buffer.buf[buffer_used], - buffer.len - buffer_used, - &processed); - - if (err) + while (1) { + buffer_used = 0; + memset(&buffer, 0, sizeof(buffer)); + err = cs_etm__get_trace(&buffer, etmq); + if (err <= 0) return err; - - etmq->offset += processed; - buffer_used += processed; - /* - * Nothing to do with an error condition, let's hope the next - * chunk will be better. + * We cannot assume consecutive blocks in the data file are + * contiguous, reset the decoder to force re-sync. */ - err = cs_etm__sample(etmq); - } while (buffer.len > buffer_used); + err = cs_etm_decoder__reset(etmq->decoder); + if (err != 0) + return err; -goto more; + /* Run trace decoder until buffer consumed or end of trace */ + do { + processed = 0; + err = cs_etm_decoder__process_data_block( + etmq->decoder, + etmq->offset, + &buffer.buf[buffer_used], + buffer.len - buffer_used, + &processed); + if (err) + return err; + + etmq->offset += processed; + buffer_used += processed; + + /* Process each packet in this chunk */ + while (1) { + err = cs_etm_decoder__get_packet(etmq->decoder, + etmq->packet); + if (err <= 0) + /* + * Stop processing this chunk on + * end of data or error + */ + break; + + switch (etmq->packet->sample_type) { + case CS_ETM_RANGE: + /* + * If the packet contains an instruction + * range, generate instruction sequence + * events. + */ + cs_etm__sample(etmq); + break; + case CS_ETM_TRACE_ON: + /* + * Discontinuity in trace, flush + * previous branch stack + */ + cs_etm__flush(etmq); + break; + case CS_ETM_EMPTY: + /* + * Should not receive empty packet, + * report error. + */ + pr_err("CS ETM Trace: empty packet\n"); + return -EINVAL; + default: + break; + } + } + } while (buffer.len > buffer_used); + + if (err == 0) + /* Flush any remaining branch stack entries */ + err = cs_etm__flush(etmq); + } return err; } @@ -980,6 +1407,23 @@ int cs_etm__process_auxtrace_info(union perf_event *event, etm->auxtrace.free = cs_etm__free; session->auxtrace = &etm->auxtrace; + etm->unknown_thread = thread__new(999999999, 999999999); + if (!etm->unknown_thread) + goto err_free_queues; + + /* + * Initialize list node so that at thread__zput() we can avoid + * segmentation fault at list_del_init(). + */ + INIT_LIST_HEAD(&etm->unknown_thread->node); + + err = thread__set_comm(etm->unknown_thread, "unknown", 0); + if (err) + goto err_delete_thread; + + if (thread__init_map_groups(etm->unknown_thread, etm->machine)) + goto err_delete_thread; + if (dump_trace) { cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu); return 0; @@ -994,16 +1438,18 @@ int cs_etm__process_auxtrace_info(union perf_event *event, err = cs_etm__synth_events(etm, session); if (err) - goto err_free_queues; + goto err_delete_thread; err = auxtrace_queues__process_index(&etm->queues, session); if (err) - goto err_free_queues; + goto err_delete_thread; etm->data_queued = etm->queues.populated; return 0; +err_delete_thread: + thread__zput(etm->unknown_thread); err_free_queues: auxtrace_queues__free(&etm->queues); session->auxtrace = NULL; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 5864d5dca616..37f8d48179ca 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -1,18 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright(C) 2015 Linaro Limited. All rights reserved. * Author: Mathieu Poirier <mathieu.poirier@linaro.org> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program. If not, see <http://www.gnu.org/licenses/>. */ #ifndef INCLUDE__UTIL_PERF_CS_ETM_H__ diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 5744c12641a5..abd38abf1d91 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -310,8 +310,8 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, if (flags & FIELD_IS_DYNAMIC) { unsigned long long tmp_val; - tmp_val = pevent_read_number(fmtf->event->pevent, - data + offset, len); + tmp_val = tep_read_number(fmtf->event->pevent, + data + offset, len); offset = tmp_val; len = offset >> 16; offset &= 0xffff; @@ -353,7 +353,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, else { unsigned long long value_int; - value_int = pevent_read_number( + value_int = tep_read_number( fmtf->event->pevent, data + offset + i * len, len); diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index b0c2b5c5d337..7123746edcf4 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -247,9 +247,9 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al, *dso_db_id = dso->db_id; if (!al->sym) { - al->sym = symbol__new(al->addr, 0, 0, "unknown"); + al->sym = symbol__new(al->addr, 0, 0, 0, "unknown"); if (al->sym) - dso__insert_symbol(dso, al->map->type, al->sym); + dso__insert_symbol(dso, al->sym); } if (al->sym) { @@ -315,8 +315,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, al.addr = node->ip; if (al.map && !al.sym) - al.sym = dso__find_symbol(al.map->dso, MAP__FUNCTION, - al.addr); + al.sym = dso__find_symbol(al.map->dso, al.addr); db_ids_from_al(dbe, &al, &dso_db_id, &sym_db_id, &offset); diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index f3a71db83947..3d6459626c2a 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -232,7 +232,6 @@ int perf_quiet_option(void) var++; } - quiet = true; return 0; } diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 36ef45b2e89d..bbed90e5d9bb 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -189,28 +189,34 @@ int dso__read_binary_type_filename(const struct dso *dso, return ret; } +enum { + COMP_ID__NONE = 0, +}; + static const struct { const char *fmt; int (*decompress)(const char *input, int output); + bool (*is_compressed)(const char *input); } compressions[] = { + [COMP_ID__NONE] = { .fmt = NULL, }, #ifdef HAVE_ZLIB_SUPPORT - { "gz", gzip_decompress_to_file }, + { "gz", gzip_decompress_to_file, gzip_is_compressed }, #endif #ifdef HAVE_LZMA_SUPPORT - { "xz", lzma_decompress_to_file }, + { "xz", lzma_decompress_to_file, lzma_is_compressed }, #endif - { NULL, NULL }, + { NULL, NULL, NULL }, }; -bool is_supported_compression(const char *ext) +static int is_supported_compression(const char *ext) { unsigned i; - for (i = 0; compressions[i].fmt; i++) { + for (i = 1; compressions[i].fmt; i++) { if (!strcmp(ext, compressions[i].fmt)) - return true; + return i; } - return false; + return COMP_ID__NONE; } bool is_kernel_module(const char *pathname, int cpumode) @@ -239,80 +245,73 @@ bool is_kernel_module(const char *pathname, int cpumode) return m.kmod; } -bool decompress_to_file(const char *ext, const char *filename, int output_fd) -{ - unsigned i; - - for (i = 0; compressions[i].fmt; i++) { - if (!strcmp(ext, compressions[i].fmt)) - return !compressions[i].decompress(filename, - output_fd); - } - return false; -} - bool dso__needs_decompress(struct dso *dso) { return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP || dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; } -static int decompress_kmodule(struct dso *dso, const char *name, char *tmpbuf) +static int decompress_kmodule(struct dso *dso, const char *name, + char *pathname, size_t len) { + char tmpbuf[] = KMOD_DECOMP_NAME; int fd = -1; - struct kmod_path m; if (!dso__needs_decompress(dso)) return -1; - if (kmod_path__parse_ext(&m, dso->long_name)) + if (dso->comp == COMP_ID__NONE) return -1; - if (!m.comp) - goto out; + /* + * We have proper compression id for DSO and yet the file + * behind the 'name' can still be plain uncompressed object. + * + * The reason is behind the logic we open the DSO object files, + * when we try all possible 'debug' objects until we find the + * data. So even if the DSO is represented by 'krava.xz' module, + * we can end up here opening ~/.debug/....23432432/debug' file + * which is not compressed. + * + * To keep this transparent, we detect this and return the file + * descriptor to the uncompressed file. + */ + if (!compressions[dso->comp].is_compressed(name)) + return open(name, O_RDONLY); fd = mkstemp(tmpbuf); if (fd < 0) { dso->load_errno = errno; - goto out; + return -1; } - if (!decompress_to_file(m.ext, name, fd)) { + if (compressions[dso->comp].decompress(name, fd)) { dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE; close(fd); fd = -1; } -out: - free(m.ext); + if (!pathname || (fd < 0)) + unlink(tmpbuf); + + if (pathname && (fd >= 0)) + strncpy(pathname, tmpbuf, len); + return fd; } int dso__decompress_kmodule_fd(struct dso *dso, const char *name) { - char tmpbuf[] = KMOD_DECOMP_NAME; - int fd; - - fd = decompress_kmodule(dso, name, tmpbuf); - unlink(tmpbuf); - return fd; + return decompress_kmodule(dso, name, NULL, 0); } int dso__decompress_kmodule_path(struct dso *dso, const char *name, char *pathname, size_t len) { - char tmpbuf[] = KMOD_DECOMP_NAME; - int fd; - - fd = decompress_kmodule(dso, name, tmpbuf); - if (fd < 0) { - unlink(tmpbuf); - return -1; - } + int fd = decompress_kmodule(dso, name, pathname, len); - strncpy(pathname, tmpbuf, len); close(fd); - return 0; + return fd >= 0 ? 0 : -1; } /* @@ -332,7 +331,7 @@ int dso__decompress_kmodule_path(struct dso *dso, const char *name, * Returns 0 if there's no strdup error, -ENOMEM otherwise. */ int __kmod_path__parse(struct kmod_path *m, const char *path, - bool alloc_name, bool alloc_ext) + bool alloc_name) { const char *name = strrchr(path, '/'); const char *ext = strrchr(path, '.'); @@ -354,6 +353,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path, if ((strncmp(name, "[kernel.kallsyms]", 17) == 0) || (strncmp(name, "[guest.kernel.kallsyms", 22) == 0) || (strncmp(name, "[vdso]", 6) == 0) || + (strncmp(name, "[vdso32]", 8) == 0) || + (strncmp(name, "[vdsox32]", 9) == 0) || (strncmp(name, "[vsyscall]", 10) == 0)) { m->kmod = false; @@ -370,10 +371,9 @@ int __kmod_path__parse(struct kmod_path *m, const char *path, return 0; } - if (is_supported_compression(ext + 1)) { - m->comp = true; + m->comp = is_supported_compression(ext + 1); + if (m->comp > COMP_ID__NONE) ext -= 3; - } /* Check .ko extension only if there's enough name left. */ if (ext > name) @@ -391,14 +391,6 @@ int __kmod_path__parse(struct kmod_path *m, const char *path, strxfrchar(m->name, '-', '_'); } - if (alloc_ext && m->comp) { - m->ext = strdup(ext + 4); - if (!m->ext) { - free((void *) m->name); - return -ENOMEM; - } - } - return 0; } @@ -411,8 +403,10 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m, dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; /* _KMODULE_COMP should be next to _KMODULE */ - if (m->kmod && m->comp) + if (m->kmod && m->comp) { dso->symtab_type++; + dso->comp = m->comp; + } dso__set_short_name(dso, strdup(m->name), true); } @@ -466,6 +460,7 @@ static int __open_dso(struct dso *dso, struct machine *machine) int fd = -EINVAL; char *root_dir = (char *)""; char *name = malloc(PATH_MAX); + bool decomp = false; if (!name) return -ENOMEM; @@ -489,12 +484,13 @@ static int __open_dso(struct dso *dso, struct machine *machine) goto out; } + decomp = true; strcpy(name, newpath); } fd = do_open(name); - if (dso__needs_decompress(dso)) + if (decomp) unlink(name); out: @@ -1014,7 +1010,7 @@ struct map *dso__new_map(const char *name) struct dso *dso = dso__new(name); if (dso) - map = map__new2(0, dso, MAP__FUNCTION); + map = map__new2(0, dso); return map; } @@ -1176,19 +1172,19 @@ int dso__name_len(const struct dso *dso) return dso->short_name_len; } -bool dso__loaded(const struct dso *dso, enum map_type type) +bool dso__loaded(const struct dso *dso) { - return dso->loaded & (1 << type); + return dso->loaded; } -bool dso__sorted_by_name(const struct dso *dso, enum map_type type) +bool dso__sorted_by_name(const struct dso *dso) { - return dso->sorted_by_name & (1 << type); + return dso->sorted_by_name; } -void dso__set_sorted_by_name(struct dso *dso, enum map_type type) +void dso__set_sorted_by_name(struct dso *dso) { - dso->sorted_by_name |= (1 << type); + dso->sorted_by_name = true; } struct dso *dso__new(const char *name) @@ -1196,12 +1192,10 @@ struct dso *dso__new(const char *name) struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1); if (dso != NULL) { - int i; strcpy(dso->name, name); dso__set_long_name(dso, dso->name, false); dso__set_short_name(dso, dso->name, false); - for (i = 0; i < MAP__NR_TYPES; ++i) - dso->symbols[i] = dso->symbol_names[i] = RB_ROOT; + dso->symbols = dso->symbol_names = RB_ROOT; dso->data.cache = RB_ROOT; dso->inlined_nodes = RB_ROOT; dso->srclines = RB_ROOT; @@ -1218,6 +1212,7 @@ struct dso *dso__new(const char *name) dso->a2l_fails = 1; dso->kernel = DSO_TYPE_USER; dso->needs_swap = DSO_SWAP__UNSET; + dso->comp = COMP_ID__NONE; RB_CLEAR_NODE(&dso->rb_node); dso->root = NULL; INIT_LIST_HEAD(&dso->node); @@ -1231,8 +1226,6 @@ struct dso *dso__new(const char *name) void dso__delete(struct dso *dso) { - int i; - if (!RB_EMPTY_NODE(&dso->rb_node)) pr_err("DSO %s is still in rbtree when being deleted!\n", dso->long_name); @@ -1240,8 +1233,7 @@ void dso__delete(struct dso *dso) /* free inlines first, as they reference symbols */ inlines__tree_delete(&dso->inlined_nodes); srcline__tree_delete(&dso->srclines); - for (i = 0; i < MAP__NR_TYPES; ++i) - symbols__delete(&dso->symbols[i]); + symbols__delete(&dso->symbols); if (dso->short_name_allocated) { zfree((char **)&dso->short_name); @@ -1451,9 +1443,7 @@ size_t __dsos__fprintf(struct list_head *head, FILE *fp) size_t ret = 0; list_for_each_entry(pos, head, node) { - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - ret += dso__fprintf(pos, i, fp); + ret += dso__fprintf(pos, fp); } return ret; @@ -1467,18 +1457,17 @@ size_t dso__fprintf_buildid(struct dso *dso, FILE *fp) return fprintf(fp, "%s", sbuild_id); } -size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp) +size_t dso__fprintf(struct dso *dso, FILE *fp) { struct rb_node *nd; size_t ret = fprintf(fp, "dso: %s (", dso->short_name); if (dso->short_name != dso->long_name) ret += fprintf(fp, "%s, ", dso->long_name); - ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type], - dso__loaded(dso, type) ? "" : "NOT "); + ret += fprintf(fp, "%sloaded, ", dso__loaded(dso) ? "" : "NOT "); ret += dso__fprintf_buildid(dso, fp); ret += fprintf(fp, ")\n"); - for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&dso->symbols); nd; nd = rb_next(nd)) { struct symbol *pos = rb_entry(nd, struct symbol, rb_node); ret += symbol__fprintf(pos, fp); } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index c229dbe0277a..c5380500bed4 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -140,14 +140,14 @@ struct dso { struct list_head node; struct rb_node rb_node; /* rbtree node sorted by long name */ struct rb_root *root; /* root of rbtree that rb_node is in */ - struct rb_root symbols[MAP__NR_TYPES]; - struct rb_root symbol_names[MAP__NR_TYPES]; + struct rb_root symbols; + struct rb_root symbol_names; struct rb_root inlined_nodes; struct rb_root srclines; struct { u64 addr; struct symbol *symbol; - } last_find_result[MAP__NR_TYPES]; + } last_find_result; void *a2l; char *symsrc_filename; unsigned int a2l_fails; @@ -164,8 +164,8 @@ struct dso { u8 short_name_allocated:1; u8 long_name_allocated:1; u8 is_64_bit:1; - u8 sorted_by_name; - u8 loaded; + bool sorted_by_name; + bool loaded; u8 rel; u8 build_id[BUILD_ID_SIZE]; u64 text_offset; @@ -175,6 +175,7 @@ struct dso { u16 short_name_len; void *dwfl; /* DWARF debug info */ struct auxtrace_cache *auxtrace_cache; + int comp; /* dso data file */ struct { @@ -202,14 +203,13 @@ struct dso { * @dso: the 'struct dso *' in which symbols itereated * @pos: the 'struct symbol *' to use as a loop cursor * @n: the 'struct rb_node *' to use as a temporary storage - * @type: the 'enum map_type' type of symbols */ -#define dso__for_each_symbol(dso, pos, n, type) \ - symbols__for_each_entry(&(dso)->symbols[(type)], pos, n) +#define dso__for_each_symbol(dso, pos, n) \ + symbols__for_each_entry(&(dso)->symbols, pos, n) -static inline void dso__set_loaded(struct dso *dso, enum map_type type) +static inline void dso__set_loaded(struct dso *dso) { - dso->loaded |= (1 << type); + dso->loaded = true; } struct dso *dso__new(const char *name); @@ -231,11 +231,16 @@ static inline void __dso__zput(struct dso **dso) #define dso__zput(dso) __dso__zput(&dso) -bool dso__loaded(const struct dso *dso, enum map_type type); +bool dso__loaded(const struct dso *dso); -bool dso__sorted_by_name(const struct dso *dso, enum map_type type); -void dso__set_sorted_by_name(struct dso *dso, enum map_type type); -void dso__sort_by_name(struct dso *dso, enum map_type type); +static inline bool dso__has_symbols(const struct dso *dso) +{ + return !RB_EMPTY_ROOT(&dso->symbols); +} + +bool dso__sorted_by_name(const struct dso *dso); +void dso__set_sorted_by_name(struct dso *dso); +void dso__sort_by_name(struct dso *dso); void dso__set_build_id(struct dso *dso, void *build_id); bool dso__build_id_equal(const struct dso *dso, u8 *build_id); @@ -246,9 +251,7 @@ int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir); char dso__symtab_origin(const struct dso *dso); int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, char *root_dir, char *filename, size_t size); -bool is_supported_compression(const char *ext); bool is_kernel_module(const char *pathname, int cpumode); -bool decompress_to_file(const char *ext, const char *filename, int output_fd); bool dso__needs_decompress(struct dso *dso); int dso__decompress_kmodule_fd(struct dso *dso, const char *name); int dso__decompress_kmodule_path(struct dso *dso, const char *name, @@ -259,17 +262,15 @@ int dso__decompress_kmodule_path(struct dso *dso, const char *name, struct kmod_path { char *name; - char *ext; - bool comp; + int comp; bool kmod; }; int __kmod_path__parse(struct kmod_path *m, const char *path, - bool alloc_name, bool alloc_ext); + bool alloc_name); -#define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false, false) -#define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) -#define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) +#define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false) +#define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true) void dso__set_module_info(struct dso *dso, struct kmod_path *m, struct machine *machine); @@ -349,9 +350,8 @@ size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, size_t __dsos__fprintf(struct list_head *head, FILE *fp); size_t dso__fprintf_buildid(struct dso *dso, FILE *fp); -size_t dso__fprintf_symbols_by_name(struct dso *dso, - enum map_type type, FILE *fp); -size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp); +size_t dso__fprintf_symbols_by_name(struct dso *dso, FILE *fp); +size_t dso__fprintf(struct dso *dso, FILE *fp); static inline bool dso__is_vmlinux(struct dso *dso) { diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index f5acda13dcfa..7eb7de5aee44 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -979,7 +979,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf) return ret < 0 ? ret : strbuf_addf(buf, "\t%s", dwarf_diename(vr_die)); } -#ifdef HAVE_DWARF_GETLOCATIONS +#ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT /** * die_get_var_innermost_scope - Get innermost scope range of given variable DIE * @sp_die: a subprogram DIE diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 6d311868d850..59f38c7693f8 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -32,6 +32,10 @@ void perf_env__exit(struct perf_env *env) for (i = 0; i < env->caches_cnt; i++) cpu_cache_level__free(&env->caches[i]); zfree(&env->caches); + + for (i = 0; i < env->nr_memory_nodes; i++) + free(env->memory_nodes[i].set); + zfree(&env->memory_nodes); } int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]) @@ -89,6 +93,37 @@ int perf_env__read_cpu_topology_map(struct perf_env *env) return 0; } +static int perf_env__read_arch(struct perf_env *env) +{ + struct utsname uts; + + if (env->arch) + return 0; + + if (!uname(&uts)) + env->arch = strdup(uts.machine); + + return env->arch ? 0 : -ENOMEM; +} + +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(); + + return env->nr_cpus_avail ? 0 : -ENOENT; +} + +const char *perf_env__raw_arch(struct perf_env *env) +{ + return env && !perf_env__read_arch(env) ? env->arch : "unknown"; +} + +int perf_env__nr_cpus_avail(struct perf_env *env) +{ + return env && !perf_env__read_nr_cpus_avail(env) ? env->nr_cpus_avail : 0; +} + void cpu_cache_level__free(struct cpu_cache_level *cache) { free(cache->type); diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index bf970f57dce0..1f3ccc368530 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -27,6 +27,12 @@ struct numa_node { struct cpu_map *map; }; +struct memory_node { + u64 node; + u64 size; + unsigned long *set; +}; + struct perf_env { char *hostname; char *os_release; @@ -43,6 +49,7 @@ struct perf_env { int nr_sibling_cores; int nr_sibling_threads; int nr_numa_nodes; + int nr_memory_nodes; int nr_pmu_mappings; int nr_groups; char *cmdline; @@ -54,6 +61,8 @@ struct perf_env { struct cpu_cache_level *caches; int caches_cnt; struct numa_node *numa_nodes; + struct memory_node *memory_nodes; + unsigned long long memory_bsize; }; extern struct perf_env perf_env; @@ -67,4 +76,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env); void cpu_cache_level__free(struct cpu_cache_level *cache); const char *perf_env__arch(struct perf_env *env); +const char *perf_env__raw_arch(struct perf_env *env); +int perf_env__nr_cpus_avail(struct perf_env *env); + #endif /* __PERF_ENV_H */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 44e603c27944..0cd42150f712 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -88,10 +88,10 @@ static const char *perf_ns__name(unsigned int id) return perf_ns__names[id]; } -static int perf_tool__process_synth_event(struct perf_tool *tool, - union perf_event *event, - struct machine *machine, - perf_event__handler_t process) +int perf_tool__process_synth_event(struct perf_tool *tool, + union perf_event *event, + struct machine *machine, + perf_event__handler_t process) { struct perf_sample synth_sample = { .pid = -1, @@ -464,8 +464,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool, { int rc = 0; struct map *pos; - struct map_groups *kmaps = &machine->kmaps; - struct maps *maps = &kmaps->maps[MAP__FUNCTION]; + struct maps *maps = machine__kernel_maps(machine); union perf_event *event = zalloc((sizeof(event->mmap) + machine->id_hdr_size)); if (event == NULL) { @@ -488,7 +487,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool, for (pos = maps__first(maps); pos; pos = map__next(pos)) { size_t size; - if (__map__is_kernel(pos)) + if (!__map__is_kmodule(pos)) continue; size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); @@ -542,10 +541,17 @@ static int __event__synthesize_thread(union perf_event *comm_event, tgid, process, machine) < 0) return -1; + /* + * send mmap only for thread group leader + * see thread__init_map_groups + */ + if (pid == tgid && + perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, + process, machine, mmap_data, + proc_map_timeout)) + return -1; - return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, - process, machine, mmap_data, - proc_map_timeout); + return 0; } if (machine__is_default_guest(machine)) @@ -869,7 +875,7 @@ static int find_symbol_cb(void *arg, const char *name, char type, * Must be a function or at least an alias, as in PARISC64, where "_text" is * an 'A' to the same address as "_stext". */ - if (!(symbol_type__is_a(type, MAP__FUNCTION) || + if (!(kallsyms__is_function(type) || type == 'A') || strcmp(name, args->name)) return 0; @@ -889,13 +895,18 @@ int kallsyms__get_function_start(const char *kallsyms_filename, return 0; } -int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) +int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused) +{ + return 0; +} + +static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) { size_t size; - const char *mmap_name; - char name_buff[PATH_MAX]; struct map *map = machine__kernel_map(machine); struct kmap *kmap; int err; @@ -918,7 +929,6 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, return -1; } - mmap_name = machine__mmap_name(machine, name_buff, sizeof(name_buff)); if (machine__is_host(machine)) { /* * kernel uses PERF_RECORD_MISC_USER for user space maps, @@ -931,7 +941,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, kmap = map__kmap(map); size = snprintf(event->mmap.filename, sizeof(event->mmap.filename), - "%s%s", mmap_name, kmap->ref_reloc_sym->name) + 1; + "%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1; size = PERF_ALIGN(size, sizeof(u64)); event->mmap.header.type = PERF_RECORD_MMAP; event->mmap.header.size = (sizeof(event->mmap) - @@ -947,6 +957,19 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, return err; } +int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + int err; + + err = __perf_event__synthesize_kernel_mmap(tool, process, machine); + if (err < 0) + return err; + + return perf_event__synthesize_extra_kmaps(tool, process, machine); +} + int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct thread_map *threads, perf_event__handler_t process, @@ -1424,7 +1447,9 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp) size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp) { bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT; - const char *in_out = out ? "OUT" : "IN "; + const char *in_out = !out ? "IN " : + !(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT) ? + "OUT " : "OUT preempt"; if (event->header.type == PERF_RECORD_SWITCH) return fprintf(fp, " %s\n", in_out); @@ -1490,9 +1515,8 @@ int perf_event__process(struct perf_tool *tool __maybe_unused, return machine__process_event(machine, event, sample); } -void thread__find_addr_map(struct thread *thread, u8 cpumode, - enum map_type type, u64 addr, - struct addr_location *al) +struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, + struct addr_location *al) { struct map_groups *mg = thread->mg; struct machine *machine = mg->machine; @@ -1506,7 +1530,7 @@ void thread__find_addr_map(struct thread *thread, u8 cpumode, if (machine == NULL) { al->map = NULL; - return; + return NULL; } if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { @@ -1534,10 +1558,10 @@ void thread__find_addr_map(struct thread *thread, u8 cpumode, !perf_host) al->filtered |= (1 << HIST_FILTER__HOST); - return; + return NULL; } try_again: - al->map = map_groups__find(mg, type, al->addr); + al->map = map_groups__find(mg, al->addr); if (al->map == NULL) { /* * If this is outside of all known maps, and is a negative @@ -1564,17 +1588,17 @@ try_again: map__load(al->map); al->addr = al->map->map_ip(al->map, al->addr); } + + return al->map; } -void thread__find_addr_location(struct thread *thread, - u8 cpumode, enum map_type type, u64 addr, - struct addr_location *al) +struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode, + u64 addr, struct addr_location *al) { - thread__find_addr_map(thread, cpumode, type, addr, al); - if (al->map != NULL) + al->sym = NULL; + if (thread__find_map(thread, cpumode, addr, al)) al->sym = map__find_symbol(al->map, al->addr); - else - al->sym = NULL; + return al->sym; } /* @@ -1591,18 +1615,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al, return -1; dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid); - /* - * Have we already created the kernel maps for this machine? - * - * This should have happened earlier, when we processed the kernel MMAP - * events, but for older perf.data files there was no such thing, so do - * it now. - */ - if (sample->cpumode == PERF_RECORD_MISC_KERNEL && - machine__kernel_map(machine) == NULL) - machine__create_kernel_maps(machine); - - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, al); + thread__find_map(thread, sample->cpumode, sample->ip, al); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : "<not found>"); @@ -1681,10 +1694,7 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr) void thread__resolve(struct thread *thread, struct addr_location *al, struct perf_sample *sample) { - thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->addr, al); - if (!al->map) - thread__find_addr_map(thread, sample->cpumode, MAP__VARIABLE, - sample->addr, al); + thread__find_map(thread, sample->cpumode, sample->addr, al); al->cpu = sample->cpu; al->sym = NULL; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 0f794744919c..bfa60bcafbde 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -750,6 +750,10 @@ int perf_event__process_exit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_tool__process_synth_event(struct perf_tool *tool, + union perf_event *event, + struct machine *machine, + perf_event__handler_t process); int perf_event__process(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -796,6 +800,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, bool mmap_data, unsigned int proc_map_timeout); +int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine); + size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp); size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp); size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index e5fc14e53c05..be440df29615 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -702,29 +702,6 @@ static int perf_evlist__resume(struct perf_evlist *evlist) return perf_evlist__set_paused(evlist, false); } -union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx) -{ - struct perf_mmap *md = &evlist->mmap[idx]; - - /* - * Check messup is required for forward overwritable ring buffer: - * memory pointed by md->prev can be overwritten in this case. - * No need for read-write ring buffer: kernel stop outputting when - * it hit md->prev (perf_mmap__consume()). - */ - return perf_mmap__read_forward(md); -} - -union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) -{ - return perf_evlist__mmap_read_forward(evlist, idx); -} - -void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) -{ - perf_mmap__consume(&evlist->mmap[idx], false); -} - static void perf_evlist__munmap_nofree(struct perf_evlist *evlist) { int i; @@ -745,7 +722,8 @@ void perf_evlist__munmap(struct perf_evlist *evlist) zfree(&evlist->overwrite_mmap); } -static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist) +static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist, + bool overwrite) { int i; struct perf_mmap *map; @@ -759,9 +737,10 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist) for (i = 0; i < evlist->nr_mmaps; i++) { map[i].fd = -1; + map[i].overwrite = overwrite; /* * When the perf_mmap() call is made we grab one refcount, plus - * one extra to let perf_evlist__mmap_consume() get the last + * one extra to let perf_mmap__consume() get the last * events after all real references (perf_mmap__get()) are * dropped. * @@ -802,7 +781,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, maps = evlist->overwrite_mmap; if (!maps) { - maps = perf_evlist__alloc_mmap(evlist); + maps = perf_evlist__alloc_mmap(evlist, true); if (!maps) return -1; evlist->overwrite_mmap = maps; @@ -824,7 +803,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, if (*output == -1) { *output = fd; - if (perf_mmap__mmap(&maps[idx], mp, *output) < 0) + if (perf_mmap__mmap(&maps[idx], mp, *output, evlist_cpu) < 0) return -1; } else { if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) @@ -1052,7 +1031,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, struct mmap_params mp; if (!evlist->mmap) - evlist->mmap = perf_evlist__alloc_mmap(evlist); + evlist->mmap = perf_evlist__alloc_mmap(evlist, false); if (!evlist->mmap) return -ENOMEM; @@ -1086,11 +1065,30 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages) int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) { + bool all_threads = (target->per_thread && target->system_wide); struct cpu_map *cpus; struct thread_map *threads; + /* + * If specify '-a' and '--per-thread' to perf record, perf record + * will override '--per-thread'. target->per_thread = false and + * target->system_wide = true. + * + * If specify '--per-thread' only to perf record, + * target->per_thread = true and target->system_wide = false. + * + * So target->per_thread && target->system_wide is false. + * For perf record, thread_map__new_str doesn't call + * thread_map__new_all_cpus. That will keep perf record's + * current behavior. + * + * For perf stat, it allows the case that target->per_thread and + * target->system_wide are all true. It means to collect system-wide + * per-thread data. thread_map__new_str will call + * thread_map__new_all_cpus to enumerate all threads. + */ threads = thread_map__new_str(target->pid, target->tid, target->uid, - target->per_thread); + all_threads); if (!threads) return -1; @@ -1797,3 +1795,18 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist) return true; } + +/* + * Events in data file are not collect in groups, but we still want + * the group display. Set the artificial group and set the leader's + * forced_leader flag to notify the display code. + */ +void perf_evlist__force_leader(struct perf_evlist *evlist) +{ + if (!evlist->nr_groups) { + struct perf_evsel *leader = perf_evlist__first(evlist); + + perf_evlist__set_leader(evlist); + leader->forced_leader = true; + } +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 336b838e6957..dc66436add98 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -129,10 +129,6 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id); void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state); -union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx); - -union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, - int idx); void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); int perf_evlist__open(struct perf_evlist *evlist); @@ -313,4 +309,7 @@ struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, union perf_event *event); bool perf_evlist__exclude_kernel(struct perf_evlist *evlist); + +void perf_evlist__force_leader(struct perf_evlist *evlist); + #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index ef351688b797..1a61628a1c12 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -244,14 +244,16 @@ void perf_evsel__init(struct perf_evsel *evsel, evsel->metric_name = NULL; evsel->metric_events = NULL; evsel->collect_stat = false; + evsel->pmu_name = NULL; } struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) { struct perf_evsel *evsel = zalloc(perf_evsel__object.size); - if (evsel != NULL) - perf_evsel__init(evsel, attr, idx); + if (!evsel) + return NULL; + perf_evsel__init(evsel, attr, idx); if (perf_evsel__is_bpf_output(evsel)) { evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | @@ -259,6 +261,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) evsel->attr.sample_period = 1; } + if (perf_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; + evsel->scale = 1e-6; + } + return evsel; } @@ -621,22 +634,34 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel) return evsel->group_name ?: "anon group"; } +/* + * Returns the group details for the specified leader, + * with following rules. + * + * For record -e '{cycles,instructions}' + * 'anon group { cycles:u, instructions:u }' + * + * For record -e 'cycles,instructions' and report --group + * 'cycles:u, instructions:u' + */ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) { - int ret; + int ret = 0; struct perf_evsel *pos; const char *group_name = perf_evsel__group_name(evsel); - ret = scnprintf(buf, size, "%s", group_name); + if (!evsel->forced_leader) + ret = scnprintf(buf, size, "%s { ", group_name); - ret += scnprintf(buf + ret, size - ret, " { %s", + ret += scnprintf(buf + ret, size - ret, "%s", perf_evsel__name(evsel)); for_each_group_member(pos, evsel) ret += scnprintf(buf + ret, size - ret, ", %s", perf_evsel__name(pos)); - ret += scnprintf(buf + ret, size - ret, " }"); + if (!evsel->forced_leader) + ret += scnprintf(buf + ret, size - ret, " }"); return ret; } @@ -835,6 +860,12 @@ static void apply_config_terms(struct perf_evsel *evsel, } } +static bool is_dummy_event(struct perf_evsel *evsel) +{ + return (evsel->attr.type == PERF_TYPE_SOFTWARE) && + (evsel->attr.config == PERF_COUNT_SW_DUMMY); +} + /* * The enable_on_exec/disabled value strategy: * @@ -917,8 +948,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, * than leader in case leader 'leads' the sampling. */ if ((leader != evsel) && leader->sample_read) { - attr->sample_freq = 0; - attr->sample_period = 0; + attr->freq = 0; + attr->sample_freq = 0; + attr->sample_period = 0; + attr->write_backward = 0; + attr->sample_id_all = 0; } if (opts->no_samples) @@ -1070,6 +1104,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, else perf_evsel__reset_sample_bit(evsel, PERIOD); } + + /* + * For initial_delay, a dummy event is added implicitly. + * The software event will trigger -EOPNOTSUPP error out, + * if BRANCH_STACK bit is set. + */ + if (opts->initial_delay && is_dummy_event(evsel)) + perf_evsel__reset_sample_bit(evsel, BRANCH_STACK); } static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) @@ -1233,7 +1275,7 @@ void perf_evsel__exit(struct perf_evsel *evsel) perf_evsel__free_fd(evsel); perf_evsel__free_id(evsel); perf_evsel__free_config_terms(evsel); - close_cgroup(evsel->cgrp); + cgroup__put(evsel->cgrp); cpu_map__put(evsel->cpus); cpu_map__put(evsel->own_cpus); thread_map__put(evsel->threads); @@ -1909,12 +1951,16 @@ try_fallback: goto fallback_missing_features; } else if (!perf_missing_features.group_read && evsel->attr.inherit && - (evsel->attr.read_format & PERF_FORMAT_GROUP)) { + (evsel->attr.read_format & PERF_FORMAT_GROUP) && + perf_evsel__is_group_leader(evsel)) { perf_missing_features.group_read = true; pr_debug2("switching off group read\n"); goto fallback_missing_features; } out_close: + if (err) + threads->err_thread = thread; + do { while (--thread >= 0) { close(FD(evsel, cpu, thread)); @@ -2177,7 +2223,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } } - if (type & PERF_SAMPLE_CALLCHAIN) { + if (evsel__has_callchain(evsel)) { const u64 max_callchain_nr = UINT64_MAX / sizeof(u64); OVERFLOW_CHECK_u64(array); @@ -2638,7 +2684,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name) { - return pevent_find_field(evsel->tp_format, name); + return tep_find_field(evsel->tp_format, name); } void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, @@ -2738,8 +2784,14 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, (paranoid = perf_event_paranoid()) > 1) { const char *name = perf_evsel__name(evsel); char *new_name; + const char *sep = ":"; + + /* Is there already the separator in the name. */ + if (strchr(name, '/') || + strchr(name, ':')) + sep = ""; - if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0) + if (asprintf(&new_name, "%s%su", name, sep) < 0) return false; if (evsel->name) @@ -2831,12 +2883,12 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "Hint: Try again after reducing the number of events.\n" "Hint: Try increasing the limit with 'ulimit -n <limit>'"); case ENOMEM: - if ((evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0 && + if (evsel__has_callchain(evsel) && access("/proc/sys/kernel/perf_event_max_stack", F_OK) == 0) return scnprintf(msg, size, "Not enough memory to setup event with callchain.\n" "Hint: Try tweaking /proc/sys/kernel/perf_event_max_stack\n" - "Hint: Current value: %d", sysctl_perf_event_max_stack); + "Hint: Current value: %d", sysctl__max_stack()); break; case ENODEV: if (target->cpu_list) @@ -2854,8 +2906,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, #if defined(__i386__) || defined(__x86_64__) if (evsel->attr.type == PERF_TYPE_HARDWARE) return scnprintf(msg, size, "%s", - "No hardware sampling interrupt available.\n" - "No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it."); + "No hardware sampling interrupt available.\n"); #endif break; case EBUSY: @@ -2878,8 +2929,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, return scnprintf(msg, size, "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n" - "/bin/dmesg may provide additional information.\n" - "No CONFIG_PERF_EVENTS=y kernel support configured?", + "/bin/dmesg | grep -i perf may provide additional information.\n", err, str_error_r(err, sbuf, sizeof(sbuf)), perf_evsel__name(evsel)); } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index a7487c6d1866..163c960614d3 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -30,7 +30,7 @@ struct perf_sample_id { u64 period; }; -struct cgroup_sel; +struct cgroup; /* * The 'struct perf_evsel_config_term' is used to pass event @@ -107,7 +107,7 @@ struct perf_evsel { struct perf_stat_evsel *stats; void *priv; u64 db_id; - struct cgroup_sel *cgrp; + struct cgroup *cgrp; void *handler; struct cpu_map *cpus; struct cpu_map *own_cpus; @@ -115,6 +115,7 @@ struct perf_evsel { unsigned int sample_size; int id_pos; int is_pos; + bool uniquified_name; bool snapshot; bool supported; bool needs_swap; @@ -125,6 +126,8 @@ struct perf_evsel { bool per_pkg; bool precise_max; bool ignore_missing_thread; + bool forced_leader; + bool use_uncore_alias; /* parse modifier helper */ int exclude_GH; int nr_members; @@ -142,6 +145,7 @@ struct perf_evsel { struct perf_evsel **metric_events; bool collect_stat; bool weak_group; + const char *pmu_name; }; union u64_swap { @@ -398,10 +402,13 @@ bool perf_evsel__is_function_event(struct perf_evsel *evsel); static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel) { - struct perf_event_attr *attr = &evsel->attr; + return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT); +} - return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) && - (attr->type == PERF_TYPE_SOFTWARE); +static inline bool perf_evsel__is_clock(struct perf_evsel *evsel) +{ + return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) || + perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK); } struct perf_attr_details { @@ -445,16 +452,28 @@ static inline int perf_evsel__group_idx(struct perf_evsel *evsel) return evsel->idx - evsel->leader->idx; } +/* Iterates group WITHOUT the leader. */ #define for_each_group_member(_evsel, _leader) \ for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); \ (_evsel) && (_evsel)->leader == (_leader); \ (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) +/* Iterates group WITH the leader. */ +#define for_each_group_evsel(_evsel, _leader) \ +for ((_evsel) = _leader; \ + (_evsel) && (_evsel)->leader == (_leader); \ + (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) + static inline bool perf_evsel__has_branch_callstack(const struct perf_evsel *evsel) { return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; } +static inline bool evsel__has_callchain(const struct perf_evsel *evsel) +{ + return (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0; +} + typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *); int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index c540d47583e7..aafbe54fd3fa 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -114,7 +114,7 @@ gen_build_id(struct buildid_note *note, fd = open("/dev/urandom", O_RDONLY); if (fd == -1) - err(1, "cannot access /dev/urandom for builid"); + err(1, "cannot access /dev/urandom for buildid"); sret = read(fd, note->build_id, sz); diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh index ff17920a5ebc..c3cef36d4176 100755 --- a/tools/perf/util/generate-cmdlist.sh +++ b/tools/perf/util/generate-cmdlist.sh @@ -38,7 +38,7 @@ do done echo "#endif /* HAVE_LIBELF_SUPPORT */" -echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)" +echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)" sed -n -e 's/^perf-\([^ ]*\)[ ].* audit*/\1/p' command-list.txt | sort | while read cmd diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index a326e0d8b5b6..3cadc252dd89 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -17,6 +17,7 @@ #include <sys/stat.h> #include <sys/utsname.h> #include <linux/time64.h> +#include <dirent.h> #include "evlist.h" #include "evsel.h" @@ -37,6 +38,7 @@ #include "asm/bug.h" #include "tool.h" #include "time-utils.h" +#include "units.h" #include "sane_ctype.h" @@ -132,6 +134,25 @@ int do_write(struct feat_fd *ff, const void *buf, size_t size) } /* Return: 0 if succeded, -ERR if failed. */ +static int do_write_bitmap(struct feat_fd *ff, unsigned long *set, u64 size) +{ + u64 *p = (u64 *) set; + int i, ret; + + ret = do_write(ff, &size, sizeof(size)); + if (ret < 0) + return ret; + + for (i = 0; (u64) i < BITS_TO_U64(size); i++) { + ret = do_write(ff, p + i, sizeof(*p)); + if (ret < 0) + return ret; + } + + return 0; +} + +/* Return: 0 if succeded, -ERR if failed. */ int write_padded(struct feat_fd *ff, const void *bf, size_t count, size_t count_aligned) { @@ -243,6 +264,36 @@ static char *do_read_string(struct feat_fd *ff) return NULL; } +/* Return: 0 if succeded, -ERR if failed. */ +static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize) +{ + unsigned long *set; + u64 size, *p; + int i, ret; + + ret = do_read_u64(ff, &size); + if (ret) + return ret; + + set = bitmap_alloc(size); + if (!set) + return -ENOMEM; + + p = (u64 *) set; + + for (i = 0; (u64) i < BITS_TO_U64(size); i++) { + ret = do_read_u64(ff, p + i); + if (ret < 0) { + free(set); + return ret; + } + } + + *pset = set; + *psize = size; + return 0; +} + static int write_tracing_data(struct feat_fd *ff, struct perf_evlist *evlist) { @@ -1196,6 +1247,176 @@ static int write_sample_time(struct feat_fd *ff, sizeof(evlist->last_sample_time)); } + +static int memory_node__read(struct memory_node *n, unsigned long idx) +{ + unsigned int phys, size = 0; + char path[PATH_MAX]; + struct dirent *ent; + DIR *dir; + +#define for_each_memory(mem, dir) \ + while ((ent = readdir(dir))) \ + if (strcmp(ent->d_name, ".") && \ + strcmp(ent->d_name, "..") && \ + sscanf(ent->d_name, "memory%u", &mem) == 1) + + scnprintf(path, PATH_MAX, + "%s/devices/system/node/node%lu", + sysfs__mountpoint(), idx); + + dir = opendir(path); + if (!dir) { + pr_warning("failed: cant' open memory sysfs data\n"); + return -1; + } + + for_each_memory(phys, dir) { + size = max(phys, size); + } + + size++; + + n->set = bitmap_alloc(size); + if (!n->set) { + closedir(dir); + return -ENOMEM; + } + + n->node = idx; + n->size = size; + + rewinddir(dir); + + for_each_memory(phys, dir) { + set_bit(phys, n->set); + } + + closedir(dir); + return 0; +} + +static int memory_node__sort(const void *a, const void *b) +{ + const struct memory_node *na = a; + const struct memory_node *nb = b; + + return na->node - nb->node; +} + +static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp) +{ + char path[PATH_MAX]; + struct dirent *ent; + DIR *dir; + u64 cnt = 0; + int ret = 0; + + scnprintf(path, PATH_MAX, "%s/devices/system/node/", + sysfs__mountpoint()); + + dir = opendir(path); + if (!dir) { + pr_debug2("%s: could't read %s, does this arch have topology information?\n", + __func__, path); + return -1; + } + + while (!ret && (ent = readdir(dir))) { + unsigned int idx; + int r; + + if (!strcmp(ent->d_name, ".") || + !strcmp(ent->d_name, "..")) + continue; + + r = sscanf(ent->d_name, "node%u", &idx); + if (r != 1) + continue; + + if (WARN_ONCE(cnt >= size, + "failed to write MEM_TOPOLOGY, way too many nodes\n")) + return -1; + + ret = memory_node__read(&nodes[cnt++], idx); + } + + *cntp = cnt; + closedir(dir); + + if (!ret) + qsort(nodes, cnt, sizeof(nodes[0]), memory_node__sort); + + return ret; +} + +#define MAX_MEMORY_NODES 2000 + +/* + * The MEM_TOPOLOGY holds physical memory map for every + * node in system. The format of data is as follows: + * + * 0 - version | for future changes + * 8 - block_size_bytes | /sys/devices/system/memory/block_size_bytes + * 16 - count | number of nodes + * + * For each node we store map of physical indexes for + * each node: + * + * 32 - node id | node index + * 40 - size | size of bitmap + * 48 - bitmap | bitmap of memory indexes that belongs to node + */ +static int write_mem_topology(struct feat_fd *ff __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + static struct memory_node nodes[MAX_MEMORY_NODES]; + u64 bsize, version = 1, i, nr; + int ret; + + ret = sysfs__read_xll("devices/system/memory/block_size_bytes", + (unsigned long long *) &bsize); + if (ret) + return ret; + + ret = build_mem_topology(&nodes[0], MAX_MEMORY_NODES, &nr); + if (ret) + return ret; + + ret = do_write(ff, &version, sizeof(version)); + if (ret < 0) + goto out; + + ret = do_write(ff, &bsize, sizeof(bsize)); + if (ret < 0) + goto out; + + ret = do_write(ff, &nr, sizeof(nr)); + if (ret < 0) + goto out; + + for (i = 0; i < nr; i++) { + struct memory_node *n = &nodes[i]; + + #define _W(v) \ + ret = do_write(ff, &n->v, sizeof(n->v)); \ + if (ret < 0) \ + goto out; + + _W(node) + _W(size) + + #undef _W + + ret = do_write_bitmap(ff, n->set, n->size); + if (ret < 0) + goto out; + } + +out: + return ret; +} + static void print_hostname(struct feat_fd *ff, FILE *fp) { fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname); @@ -1235,8 +1456,24 @@ static void print_cmdline(struct feat_fd *ff, FILE *fp) fprintf(fp, "# cmdline : "); - for (i = 0; i < nr; i++) - fprintf(fp, "%s ", ff->ph->env.cmdline_argv[i]); + for (i = 0; i < nr; i++) { + char *argv_i = strdup(ff->ph->env.cmdline_argv[i]); + if (!argv_i) { + fprintf(fp, "%s ", ff->ph->env.cmdline_argv[i]); + } else { + char *mem = argv_i; + do { + char *quote = strchr(argv_i, '\''); + if (!quote) + break; + *quote++ = '\0'; + fprintf(fp, "%s\\\'", argv_i); + argv_i = quote; + } while (1); + fprintf(fp, "%s ", argv_i); + free(mem); + } + } fputc('\n', fp); } @@ -1543,6 +1780,35 @@ static void print_sample_time(struct feat_fd *ff, FILE *fp) fprintf(fp, "# sample duration : %10.3f ms\n", d); } +static void memory_node__fprintf(struct memory_node *n, + unsigned long long bsize, FILE *fp) +{ + char buf_map[100], buf_size[50]; + unsigned long long size; + + size = bsize * bitmap_weight(n->set, n->size); + unit_number__scnprintf(buf_size, 50, size); + + bitmap_scnprintf(n->set, n->size, buf_map, 100); + fprintf(fp, "# %3" PRIu64 " [%s]: %s\n", n->node, buf_size, buf_map); +} + +static void print_mem_topology(struct feat_fd *ff, FILE *fp) +{ + struct memory_node *nodes; + int i, nr; + + nodes = ff->ph->env.memory_nodes; + nr = ff->ph->env.nr_memory_nodes; + + fprintf(fp, "# memory nodes (nr %d, block size 0x%llx):\n", + nr, ff->ph->env.memory_bsize); + + for (i = 0; i < nr; i++) { + memory_node__fprintf(&nodes[i], ff->ph->env.memory_bsize, fp); + } +} + static int __event_process_build_id(struct build_id_event *bev, char *filename, struct perf_session *session) @@ -1860,6 +2126,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) int cpu_nr = ff->ph->env.nr_cpus_avail; u64 size = 0; struct perf_header *ph = ff->ph; + bool do_core_id_test = true; ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu)); if (!ph->env.cpu) @@ -1914,6 +2181,13 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) return 0; } + /* On s390 the socket_id number is not related to the numbers of cpus. + * The socket_id number might be higher than the numbers of cpus. + * This depends on the configuration. + */ + if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4)) + do_core_id_test = false; + for (i = 0; i < (u32)cpu_nr; i++) { if (do_read_u32(ff, &nr)) goto free_cpu; @@ -1923,7 +2197,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) if (do_read_u32(ff, &nr)) goto free_cpu; - if (nr != (u32)-1 && nr > (u32)cpu_nr) { + if (do_core_id_test && nr != (u32)-1 && nr > (u32)cpu_nr) { pr_debug("socket_id number is too big." "You may need to upgrade the perf tool.\n"); goto free_cpu; @@ -2205,6 +2479,58 @@ static int process_sample_time(struct feat_fd *ff, void *data __maybe_unused) return 0; } +static int process_mem_topology(struct feat_fd *ff, + void *data __maybe_unused) +{ + struct memory_node *nodes; + u64 version, i, nr, bsize; + int ret = -1; + + if (do_read_u64(ff, &version)) + return -1; + + if (version != 1) + return -1; + + if (do_read_u64(ff, &bsize)) + return -1; + + if (do_read_u64(ff, &nr)) + return -1; + + nodes = zalloc(sizeof(*nodes) * nr); + if (!nodes) + return -1; + + for (i = 0; i < nr; i++) { + struct memory_node n; + + #define _R(v) \ + if (do_read_u64(ff, &n.v)) \ + goto out; \ + + _R(node) + _R(size) + + #undef _R + + if (do_read_bitmap(ff, &n.set, &n.size)) + goto out; + + nodes[i] = n; + } + + ff->ph->env.memory_bsize = bsize; + ff->ph->env.memory_nodes = nodes; + ff->ph->env.nr_memory_nodes = nr; + ret = 0; + +out: + if (ret) + free(nodes); + return ret; +} + struct feature_ops { int (*write)(struct feat_fd *ff, struct perf_evlist *evlist); void (*print)(struct feat_fd *ff, FILE *fp); @@ -2258,11 +2584,12 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPR(NUMA_TOPOLOGY, numa_topology, true), FEAT_OPN(BRANCH_STACK, branch_stack, false), FEAT_OPR(PMU_MAPPINGS, pmu_mappings, false), - FEAT_OPN(GROUP_DESC, group_desc, false), + FEAT_OPR(GROUP_DESC, group_desc, false), FEAT_OPN(AUXTRACE, auxtrace, false), FEAT_OPN(STAT, stat, false), FEAT_OPN(CACHE, cache, true), FEAT_OPR(SAMPLE_TIME, sample_time, false), + FEAT_OPR(MEM_TOPOLOGY, mem_topology, true), }; struct header_print_data { @@ -2318,7 +2645,12 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) if (ret == -1) return -1; - fprintf(fp, "# captured on: %s", ctime(&st.st_ctime)); + fprintf(fp, "# captured on : %s", ctime(&st.st_ctime)); + + fprintf(fp, "# header version : %u\n", header->version); + fprintf(fp, "# data offset : %" PRIu64 "\n", header->data_offset); + fprintf(fp, "# data size : %" PRIu64 "\n", header->data_size); + fprintf(fp, "# feat offset : %" PRIu64 "\n", header->feat_offset); perf_header__process_sections(header, fd, &hd, perf_file_section__fprintf_info); @@ -2872,7 +3204,7 @@ static int read_attr(int fd, struct perf_header *ph, } static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, - struct pevent *pevent) + struct tep_handle *pevent) { struct event_format *event; char bf[128]; @@ -2886,7 +3218,7 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, return -1; } - event = pevent_find_event(pevent, evsel->attr.config); + event = tep_find_event(pevent, evsel->attr.config); if (event == NULL) { pr_debug("cannot find event format for %d\n", (int)evsel->attr.config); return -1; @@ -2904,7 +3236,7 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, } static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist, - struct pevent *pevent) + struct tep_handle *pevent) { struct perf_evsel *pos; @@ -3001,8 +3333,6 @@ int perf_session__read_header(struct perf_session *session) lseek(fd, tmp, SEEK_SET); } - symbol_conf.nr_events = nr_attrs; - perf_header__process_sections(header, fd, &session->tevent, perf_file_section__process); @@ -3105,8 +3435,17 @@ int perf_event__synthesize_features(struct perf_tool *tool, return ret; } } + + /* Send HEADER_LAST_FEATURE mark. */ + fe = ff.buf; + fe->feat_id = HEADER_LAST_FEATURE; + fe->header.type = PERF_RECORD_HEADER_FEATURE; + fe->header.size = sizeof(*fe); + + ret = process(tool, ff.buf, NULL, NULL); + free(ff.buf); - return 0; + return ret; } int perf_event__process_feature(struct perf_tool *tool, @@ -3122,7 +3461,7 @@ int perf_event__process_feature(struct perf_tool *tool, pr_warning("invalid record type %d in pipe-mode\n", type); return 0; } - if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) { + if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) { pr_warning("invalid record type %d in pipe-mode\n", type); return -1; } @@ -3419,8 +3758,6 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]); } - symbol_conf.nr_events = evlist->nr_entries; - return 0; } diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index f28aaaa3a440..6d7fe44aadc0 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -2,6 +2,7 @@ #ifndef __PERF_HEADER_H #define __PERF_HEADER_H +#include <linux/stddef.h> #include <linux/perf_event.h> #include <sys/types.h> #include <stdbool.h> @@ -36,6 +37,7 @@ enum { HEADER_STAT, HEADER_CACHE, HEADER_SAMPLE_TIME, + HEADER_MEM_TOPOLOGY, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; @@ -174,4 +176,5 @@ int write_padded(struct feat_fd *fd, const void *bf, int get_cpuid(char *buffer, size_t sz); char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused); +int strcmp_cpuid_str(const char *s1, const char *s2); #endif /* __PERF_HEADER_H */ diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index b6140950301e..828cb9794c76 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -6,6 +6,7 @@ #include "session.h" #include "namespaces.h" #include "sort.h" +#include "units.h" #include "evlist.h" #include "evsel.h" #include "annotate.h" @@ -14,6 +15,7 @@ #include "ui/progress.h" #include <errno.h> #include <math.h> +#include <inttypes.h> #include <sys/param.h> static bool hists__filter_entry_by_dso(struct hists *hists, @@ -368,9 +370,11 @@ void hists__delete_entries(struct hists *hists) static int hist_entry__init(struct hist_entry *he, struct hist_entry *template, - bool sample_self) + bool sample_self, + size_t callchain_size) { *he = *template; + he->callchain_size = callchain_size; if (symbol_conf.cumulate_callchain) { he->stat_acc = malloc(sizeof(he->stat)); @@ -408,7 +412,7 @@ static int hist_entry__init(struct hist_entry *he, map__get(he->mem_info->daddr.map); } - if (symbol_conf.use_callchain) + if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) callchain_init(he->callchain); if (he->raw_data) { @@ -471,7 +475,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, he = ops->new(callchain_size); if (he) { - err = hist_entry__init(he, template, sample_self); + err = hist_entry__init(he, template, sample_self, callchain_size); if (err) { ops->free(he); he = NULL; @@ -490,7 +494,7 @@ static u8 symbol__parent_filter(const struct symbol *parent) static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period) { - if (!symbol_conf.use_callchain) + if (!hist_entry__has_callchains(he) || !symbol_conf.use_callchain) return; he->hists->callchain_period += period; @@ -536,7 +540,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, * This mem info was allocated from sample__resolve_mem * and will not be used anymore. */ - zfree(&entry->mem_info); + mem_info__zput(entry->mem_info); /* If the map of an existing hist_entry has * become out-of-date due to an exec() or @@ -617,9 +621,11 @@ __hists__add_entry(struct hists *hists, .raw_data = sample->raw_data, .raw_size = sample->raw_size, .ops = ops, - }; + }, *he = hists__findnew_entry(hists, &entry, al, sample_self); - return hists__findnew_entry(hists, &entry, al, sample_self); + if (!hists->has_callchains && he && he->callchain_size != 0) + hists->has_callchains = true; + return he; } struct hist_entry *hists__add_entry(struct hists *hists, @@ -879,7 +885,7 @@ iter_prepare_cumulative_entry(struct hist_entry_iter *iter, * cumulated only one time to prevent entries more than 100% * overhead. */ - he_cache = malloc(sizeof(*he_cache) * (iter->max_stack + 1)); + he_cache = malloc(sizeof(*he_cache) * (callchain_cursor.nr + 1)); if (he_cache == NULL) return -ENOMEM; @@ -984,7 +990,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, iter->he = he; he_cache[iter->curr++] = he; - if (symbol_conf.use_callchain) + if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) callchain_append(he->callchain, &cursor, sample->period); return 0; } @@ -1037,7 +1043,7 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, int err, err2; struct map *alm = NULL; - if (al && al->map) + if (al) alm = map__get(al->map); err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent, @@ -1045,8 +1051,6 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, if (err) return err; - iter->max_stack = max_stack_depth; - err = iter->ops->prepare_entry(iter, al); if (err) goto out; @@ -1141,7 +1145,7 @@ void hist_entry__delete(struct hist_entry *he) if (he->mem_info) { map__zput(he->mem_info->iaddr.map); map__zput(he->mem_info->daddr.map); - zfree(&he->mem_info); + mem_info__zput(he->mem_info); } zfree(&he->stat_acc); @@ -1373,7 +1377,8 @@ static int hists__hierarchy_insert_entry(struct hists *hists, if (new_he) { new_he->leaf = true; - if (symbol_conf.use_callchain) { + if (hist_entry__has_callchains(new_he) && + symbol_conf.use_callchain) { callchain_cursor_reset(&callchain_cursor); if (callchain_merge(&callchain_cursor, new_he->callchain, @@ -1414,7 +1419,7 @@ static int hists__collapse_insert_entry(struct hists *hists, if (symbol_conf.cumulate_callchain) he_stat__add_stat(iter->stat_acc, he->stat_acc); - if (symbol_conf.use_callchain) { + if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) { callchain_cursor_reset(&callchain_cursor); if (callchain_merge(&callchain_cursor, iter->callchain, @@ -1757,7 +1762,7 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro bool use_callchain; if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph) - use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN; + use_callchain = evsel__has_callchain(evsel); else use_callchain = symbol_conf.use_callchain; @@ -2456,6 +2461,85 @@ u64 hists__total_period(struct hists *hists) hists->stats.total_period; } +int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool show_freq) +{ + char unit; + int printed; + const struct dso *dso = hists->dso_filter; + const struct thread *thread = hists->thread_filter; + int socket_id = hists->socket_filter; + unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; + u64 nr_events = hists->stats.total_period; + struct perf_evsel *evsel = hists_to_evsel(hists); + const char *ev_name = perf_evsel__name(evsel); + char buf[512], sample_freq_str[64] = ""; + size_t buflen = sizeof(buf); + char ref[30] = " show reference callgraph, "; + bool enable_ref = false; + + if (symbol_conf.filter_relative) { + nr_samples = hists->stats.nr_non_filtered_samples; + nr_events = hists->stats.total_non_filtered_period; + } + + if (perf_evsel__is_group_event(evsel)) { + struct perf_evsel *pos; + + perf_evsel__group_desc(evsel, buf, buflen); + ev_name = buf; + + for_each_group_member(pos, evsel) { + struct hists *pos_hists = evsel__hists(pos); + + if (symbol_conf.filter_relative) { + nr_samples += pos_hists->stats.nr_non_filtered_samples; + nr_events += pos_hists->stats.total_non_filtered_period; + } else { + nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE]; + nr_events += pos_hists->stats.total_period; + } + } + } + + if (symbol_conf.show_ref_callgraph && + strstr(ev_name, "call-graph=no")) + enable_ref = true; + + if (show_freq) + scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->attr.sample_freq); + + nr_samples = convert_unit(nr_samples, &unit); + printed = scnprintf(bf, size, + "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64, + nr_samples, unit, evsel->nr_members > 1 ? "s" : "", + ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events); + + + if (hists->uid_filter_str) + printed += snprintf(bf + printed, size - printed, + ", UID: %s", hists->uid_filter_str); + if (thread) { + if (hists__has(hists, thread)) { + printed += scnprintf(bf + printed, size - printed, + ", Thread: %s(%d)", + (thread->comm_set ? thread__comm_str(thread) : ""), + thread->tid); + } else { + printed += scnprintf(bf + printed, size - printed, + ", Thread: %s", + (thread->comm_set ? thread__comm_str(thread) : "")); + } + } + if (dso) + printed += scnprintf(bf + printed, size - printed, + ", DSO: %s", dso->short_name); + if (socket_id > -1) + printed += scnprintf(bf + printed, size - printed, + ", Processor Socket: %d", socket_id); + + return printed; +} + int parse_filter_percentage(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused) { diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 02721b579746..3badd7f1e1b8 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -61,6 +61,7 @@ enum hist_column { HISTC_SRCLINE_TO, HISTC_TRACE, HISTC_SYM_SIZE, + HISTC_DSO_SIZE, HISTC_NR_COLS, /* Last entry */ }; @@ -84,6 +85,7 @@ struct hists { struct events_stats stats; u64 event_stream; u16 col_len[HISTC_NR_COLS]; + bool has_callchains; int socket_filter; struct perf_hpp_list *hpp_list; struct list_head hpp_formats; @@ -107,7 +109,6 @@ struct hist_entry_iter { int curr; bool hide_unresolved; - int max_stack; struct perf_evsel *evsel; struct perf_sample *sample; @@ -180,7 +181,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, - bool use_callchain); + bool ignore_callchains); size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp); void hists__filter_by_dso(struct hists *hists); @@ -220,6 +221,11 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel) return &hevsel->hists; } +static __pure inline bool hists__has_callchains(struct hists *hists) +{ + return hists->has_callchains; +} + int hists__init(void); int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list); @@ -419,19 +425,24 @@ struct hist_browser_timer { int refresh; }; +struct annotation_options; + #ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel, - struct hist_browser_timer *hbt); + struct hist_browser_timer *hbt, + struct annotation_options *annotation_opts); int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, - struct hist_browser_timer *hbt); + struct hist_browser_timer *hbt, + struct annotation_options *annotation_opts); int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, - bool warn_lost_event); + bool warn_lost_event, + struct annotation_options *annotation_options); int script_browse(const char *script_opt); #else static inline @@ -440,20 +451,23 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, float min_pcnt __maybe_unused, struct perf_env *env __maybe_unused, - bool warn_lost_event __maybe_unused) + bool warn_lost_event __maybe_unused, + struct annotation_options *annotation_options __maybe_unused) { return 0; } static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused, struct perf_evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused, + struct annotation_options *annotation_options __maybe_unused) { return 0; } static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, struct perf_evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused, + struct annotation_options *annotation_opts __maybe_unused) { return 0; } @@ -504,5 +518,11 @@ int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...); int __hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp, struct perf_hpp_list *hpp_list); int hists__fprintf_headers(struct hists *hists, FILE *fp); +int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool show_freq); + +static inline int hists__scnprintf_title(struct hists *hists, char *bf, size_t size) +{ + return __hists__scnprintf_title(hists, bf, size, true); +} #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index 72db2744876d..7f0c83b6332b 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -335,8 +335,7 @@ static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip) if (!thread) return -1; - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al); - if (!al.map || !al.map->dso) + if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso) goto out_put; len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf, diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h index e23578c7b1be..2669c9f748e4 100644 --- a/tools/perf/util/intel-pt-decoder/insn.h +++ b/tools/perf/util/intel-pt-decoder/insn.h @@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +#define POP_SS_OPCODE 0x1f +#define MOV_SREG_OPCODE 0x8e + +/* + * Intel SDM Vol.3A 6.8.3 states; + * "Any single-step trap that would be delivered following the MOV to SS + * instruction or POP to SS instruction (because EFLAGS.TF is 1) is + * suppressed." + * This function returns true if @insn is MOV SS or POP SS. On these + * instructions, single stepping is suppressed. + */ +static inline int insn_masking_exception(struct insn *insn) +{ + return insn->opcode.bytes[0] == POP_SS_OPCODE || + (insn->opcode.bytes[0] == MOV_SREG_OPCODE && + X86_MODRM_REG(insn->modrm.bytes[0]) == 2); +} + #endif /* _ASM_X86_INSN_H */ 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 aa1593ce551d..d404bed7003a 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -113,6 +113,7 @@ struct intel_pt_decoder { bool have_cyc; bool fixup_last_mtc; bool have_last_ip; + enum intel_pt_param_flags flags; uint64_t pos; uint64_t last_ip; uint64_t ip; @@ -226,6 +227,8 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->return_compression = params->return_compression; decoder->branch_enable = params->branch_enable; + decoder->flags = params->flags; + decoder->period = params->period; decoder->period_type = params->period_type; @@ -1097,6 +1100,15 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder) return ret; } +static inline bool intel_pt_fup_with_nlip(struct intel_pt_decoder *decoder, + struct intel_pt_insn *intel_pt_insn, + uint64_t ip, int err) +{ + return decoder->flags & INTEL_PT_FUP_WITH_NLIP && !err && + intel_pt_insn->branch == INTEL_PT_BR_INDIRECT && + ip == decoder->ip + intel_pt_insn->length; +} + static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) { struct intel_pt_insn intel_pt_insn; @@ -1109,10 +1121,11 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) err = intel_pt_walk_insn(decoder, &intel_pt_insn, ip); if (err == INTEL_PT_RETURN) return 0; - if (err == -EAGAIN) { + if (err == -EAGAIN || + intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) { if (intel_pt_fup_event(decoder)) return 0; - return err; + return -EAGAIN; } decoder->set_fup_tx_flags = false; if (err) @@ -1376,8 +1389,8 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder) { intel_pt_log("ERROR: Buffer overflow\n"); intel_pt_clear_tx_flags(decoder); - decoder->have_tma = false; decoder->cbr = 0; + decoder->timestamp_insn_cnt = 0; decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC; decoder->overflow = true; return -EOVERFLOW; @@ -1603,7 +1616,6 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder) case INTEL_PT_PSB: case INTEL_PT_TSC: case INTEL_PT_TMA: - case INTEL_PT_CBR: case INTEL_PT_MODE_TSX: case INTEL_PT_BAD: case INTEL_PT_PSBEND: @@ -1616,8 +1628,13 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder) case INTEL_PT_PWRX: intel_pt_log("ERROR: Missing TIP after FUP\n"); decoder->pkt_state = INTEL_PT_STATE_ERR3; + decoder->pkt_step = 0; return -ENOENT; + case INTEL_PT_CBR: + intel_pt_calc_cbr(decoder); + break; + case INTEL_PT_OVF: return intel_pt_overflow(decoder); @@ -2390,14 +2407,6 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) return &decoder->state; } -static bool intel_pt_at_psb(unsigned char *buf, size_t len) -{ - if (len < INTEL_PT_PSB_LEN) - return false; - return memmem(buf, INTEL_PT_PSB_LEN, INTEL_PT_PSB_STR, - INTEL_PT_PSB_LEN); -} - /** * intel_pt_next_psb - move buffer pointer to the start of the next PSB packet. * @buf: pointer to buffer pointer @@ -2486,6 +2495,7 @@ static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len) * @buf: buffer * @len: size of buffer * @tsc: TSC value returned + * @rem: returns remaining size when TSC is found * * Find a TSC packet in @buf and return the TSC value. This function assumes * that @buf starts at a PSB and that PSB+ will contain TSC and so stops if a @@ -2493,7 +2503,8 @@ static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len) * * Return: %true if TSC is found, false otherwise. */ -static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc) +static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc, + size_t *rem) { struct intel_pt_pkt packet; int ret; @@ -2504,6 +2515,7 @@ static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc) return false; if (packet.type == INTEL_PT_TSC) { *tsc = packet.payload; + *rem = len; return true; } if (packet.type == INTEL_PT_PSBEND) @@ -2554,6 +2566,8 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2) * @len_a: size of first buffer * @buf_b: second buffer * @len_b: size of second buffer + * @consecutive: returns true if there is data in buf_b that is consecutive + * to buf_a * * If the trace contains TSC we can look at the last TSC of @buf_a and the * first TSC of @buf_b in order to determine if the buffers overlap, and then @@ -2566,33 +2580,41 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2) static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a, size_t len_a, unsigned char *buf_b, - size_t len_b) + size_t len_b, bool *consecutive) { uint64_t tsc_a, tsc_b; unsigned char *p; - size_t len; + size_t len, rem_a, rem_b; p = intel_pt_last_psb(buf_a, len_a); if (!p) return buf_b; /* No PSB in buf_a => no overlap */ len = len_a - (p - buf_a); - if (!intel_pt_next_tsc(p, len, &tsc_a)) { + if (!intel_pt_next_tsc(p, len, &tsc_a, &rem_a)) { /* The last PSB+ in buf_a is incomplete, so go back one more */ len_a -= len; p = intel_pt_last_psb(buf_a, len_a); if (!p) return buf_b; /* No full PSB+ => assume no overlap */ len = len_a - (p - buf_a); - if (!intel_pt_next_tsc(p, len, &tsc_a)) + if (!intel_pt_next_tsc(p, len, &tsc_a, &rem_a)) return buf_b; /* No TSC in buf_a => assume no overlap */ } while (1) { /* Ignore PSB+ with no TSC */ - if (intel_pt_next_tsc(buf_b, len_b, &tsc_b) && - intel_pt_tsc_cmp(tsc_a, tsc_b) < 0) - return buf_b; /* tsc_a < tsc_b => no overlap */ + if (intel_pt_next_tsc(buf_b, len_b, &tsc_b, &rem_b)) { + int cmp = intel_pt_tsc_cmp(tsc_a, tsc_b); + + /* Same TSC, so buffers are consecutive */ + if (!cmp && rem_b >= rem_a) { + *consecutive = true; + return buf_b + len_b - (rem_b - rem_a); + } + if (cmp < 0) + return buf_b; /* tsc_a < tsc_b => no overlap */ + } if (!intel_pt_step_psb(&buf_b, &len_b)) return buf_b + len_b; /* No PSB in buf_b => no data */ @@ -2606,6 +2628,8 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a, * @buf_b: second buffer * @len_b: size of second buffer * @have_tsc: can use TSC packets to detect overlap + * @consecutive: returns true if there is data in buf_b that is consecutive + * to buf_a * * When trace samples or snapshots are recorded there is the possibility that * the data overlaps. Note that, for the purposes of decoding, data is only @@ -2616,7 +2640,7 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a, */ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a, unsigned char *buf_b, size_t len_b, - bool have_tsc) + bool have_tsc, bool *consecutive) { unsigned char *found; @@ -2628,7 +2652,8 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a, return buf_b; /* No overlap */ if (have_tsc) { - found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b); + found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b, + consecutive); if (found) return found; } @@ -2643,28 +2668,16 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a, } /* Now len_b >= len_a */ - if (len_b > len_a) { - /* The leftover buffer 'b' must start at a PSB */ - while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) { - if (!intel_pt_step_psb(&buf_a, &len_a)) - return buf_b; /* No overlap */ - } - } - while (1) { /* Potential overlap so check the bytes */ found = memmem(buf_a, len_a, buf_b, len_a); - if (found) + if (found) { + *consecutive = true; return buf_b + len_a; + } /* Try again at next PSB in buffer 'a' */ if (!intel_pt_step_psb(&buf_a, &len_a)) return buf_b; /* No overlap */ - - /* The leftover buffer 'b' must start at a PSB */ - while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) { - if (!intel_pt_step_psb(&buf_a, &len_a)) - return buf_b; /* No overlap */ - } } } 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 921b22e8ca0e..51c18d67f4ca 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -60,6 +60,14 @@ enum { INTEL_PT_ERR_MAX, }; +enum intel_pt_param_flags { + /* + * FUP packet can contain next linear instruction pointer instead of + * current linear instruction pointer. + */ + INTEL_PT_FUP_WITH_NLIP = 1 << 0, +}; + struct intel_pt_state { enum intel_pt_sample_type type; int err; @@ -106,6 +114,7 @@ struct intel_pt_params { unsigned int mtc_period; uint32_t tsc_ctc_ratio_n; uint32_t tsc_ctc_ratio_d; + enum intel_pt_param_flags flags; }; struct intel_pt_decoder; @@ -117,7 +126,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder); unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a, unsigned char *buf_b, size_t len_b, - bool have_tsc); + bool have_tsc, bool *consecutive); int intel_pt__strerror(int code, char *buf, size_t buflen); 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 ba4c9dd18643..d426761a549d 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 @@ -366,7 +366,7 @@ static int intel_pt_get_cyc(unsigned int byte, const unsigned char *buf, if (len < offs) return INTEL_PT_NEED_MORE_BYTES; byte = buf[offs++]; - payload |= (byte >> 1) << shift; + payload |= ((uint64_t)byte >> 1) << shift; } packet->type = INTEL_PT_CYC; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 3773d9c54f45..aec68908d604 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -132,6 +132,7 @@ struct intel_pt_queue { struct intel_pt *pt; unsigned int queue_nr; struct auxtrace_buffer *buffer; + struct auxtrace_buffer *old_buffer; void *decoder; const struct intel_pt_state *state; struct ip_callchain *chain; @@ -143,6 +144,7 @@ struct intel_pt_queue { bool stop; bool step_through_buffers; bool use_buffer_pid_tid; + bool sync_switch; pid_t pid, tid; int cpu; int switch_state; @@ -207,49 +209,28 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf, static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a, struct auxtrace_buffer *b) { + bool consecutive = false; void *start; start = intel_pt_find_overlap(a->data, a->size, b->data, b->size, - pt->have_tsc); + pt->have_tsc, &consecutive); if (!start) return -EINVAL; b->use_size = b->data + b->size - start; b->use_data = start; + if (b->use_size && consecutive) + b->consecutive = true; return 0; } -static void intel_pt_use_buffer_pid_tid(struct intel_pt_queue *ptq, - struct auxtrace_queue *queue, - struct auxtrace_buffer *buffer) -{ - if (queue->cpu == -1 && buffer->cpu != -1) - ptq->cpu = buffer->cpu; - - ptq->pid = buffer->pid; - ptq->tid = buffer->tid; - - intel_pt_log("queue %u cpu %d pid %d tid %d\n", - ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid); - - thread__zput(ptq->thread); - - if (ptq->tid != -1) { - if (ptq->pid != -1) - ptq->thread = machine__findnew_thread(ptq->pt->machine, - ptq->pid, - ptq->tid); - else - ptq->thread = machine__find_thread(ptq->pt->machine, -1, - ptq->tid); - } -} - /* This function assumes data is processed sequentially only */ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data) { struct intel_pt_queue *ptq = data; - struct auxtrace_buffer *buffer = ptq->buffer, *old_buffer = buffer; + struct auxtrace_buffer *buffer = ptq->buffer; + struct auxtrace_buffer *old_buffer = ptq->old_buffer; struct auxtrace_queue *queue; + bool might_overlap; if (ptq->stop) { b->len = 0; @@ -257,7 +238,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data) } queue = &ptq->pt->queues.queue_array[ptq->queue_nr]; -next: + buffer = auxtrace_buffer__next(queue, buffer); if (!buffer) { if (old_buffer) @@ -276,7 +257,8 @@ next: return -ENOMEM; } - if (ptq->pt->snapshot_mode && !buffer->consecutive && old_buffer && + might_overlap = ptq->pt->snapshot_mode || ptq->pt->sampling_mode; + if (might_overlap && !buffer->consecutive && old_buffer && intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer)) return -ENOMEM; @@ -289,33 +271,24 @@ next: } b->ref_timestamp = buffer->reference; - /* - * If in snapshot mode and the buffer has no usable data, get next - * buffer and again check overlap against old_buffer. - */ - if (ptq->pt->snapshot_mode && !b->len) - goto next; - - if (old_buffer) - auxtrace_buffer__drop_data(old_buffer); - - if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode && - !buffer->consecutive)) { + if (!old_buffer || (might_overlap && !buffer->consecutive)) { b->consecutive = false; b->trace_nr = buffer->buffer_nr + 1; } else { b->consecutive = true; } - if (ptq->use_buffer_pid_tid && (ptq->pid != buffer->pid || - ptq->tid != buffer->tid)) - intel_pt_use_buffer_pid_tid(ptq, queue, buffer); - if (ptq->step_through_buffers) ptq->stop = true; - if (!b->len) + if (b->len) { + if (old_buffer) + auxtrace_buffer__drop_data(old_buffer); + ptq->old_buffer = buffer; + } else { + auxtrace_buffer__drop_data(buffer); return intel_pt_get_trace(b, data); + } return 0; } @@ -469,8 +442,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, } while (1) { - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, *ip, &al); - if (!al.map || !al.map->dso) + if (!thread__find_map(thread, cpumode, *ip, &al) || !al.map->dso) return -EINVAL; if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR && @@ -623,8 +595,7 @@ static int __intel_pt_pgd_ip(uint64_t ip, void *data) if (!thread) return -EINVAL; - thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al); - if (!al.map || !al.map->dso) + if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso) return -EINVAL; offset = al.map->map_ip(al.map, ip); @@ -778,6 +749,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, unsigned int queue_nr) { struct intel_pt_params params = { .get_trace = 0, }; + struct perf_env *env = pt->machine->env; struct intel_pt_queue *ptq; ptq = zalloc(sizeof(struct intel_pt_queue)); @@ -859,6 +831,9 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, } } + if (env->cpuid && !strncmp(env->cpuid, "GenuineIntel,6,92,", 18)) + params.flags |= INTEL_PT_FUP_WITH_NLIP; + ptq->decoder = intel_pt_decoder_new(¶ms); if (!ptq->decoder) goto out_free; @@ -954,16 +929,15 @@ static int intel_pt_setup_queue(struct intel_pt *pt, ptq->cpu = queue->cpu; ptq->tid = queue->tid; - if (pt->sampling_mode) { - if (pt->timeless_decoding) - ptq->step_through_buffers = true; - if (pt->timeless_decoding || !pt->have_sched_switch) - ptq->use_buffer_pid_tid = true; - } + if (pt->sampling_mode && !pt->snapshot_mode && + pt->timeless_decoding) + ptq->step_through_buffers = true; + + ptq->sync_switch = pt->sync_switch; } if (!ptq->on_heap && - (!pt->sync_switch || + (!ptq->sync_switch || ptq->switch_state != INTEL_PT_SS_EXPECTING_SWITCH_EVENT)) { const struct intel_pt_state *state; int ret; @@ -1546,11 +1520,12 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) if (pt->synth_opts.last_branch) intel_pt_update_last_branch_rb(ptq); - if (!pt->sync_switch) + if (!ptq->sync_switch) return 0; if (intel_pt_is_switch_ip(ptq, state->to_ip)) { switch (ptq->switch_state) { + case INTEL_PT_SS_NOT_TRACING: case INTEL_PT_SS_UNKNOWN: case INTEL_PT_SS_EXPECTING_SWITCH_IP: err = intel_pt_next_tid(pt, ptq); @@ -1593,7 +1568,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip) if (map__load(map)) return 0; - start = dso__first_symbol(map->dso, MAP__FUNCTION); + start = dso__first_symbol(map->dso); for (sym = start; sym; sym = dso__next_symbol(sym)) { if (sym->binding == STB_GLOBAL && @@ -1627,6 +1602,21 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip) return switch_ip; } +static void intel_pt_enable_sync_switch(struct intel_pt *pt) +{ + unsigned int i; + + pt->sync_switch = true; + + for (i = 0; i < pt->queues.nr_queues; i++) { + struct auxtrace_queue *queue = &pt->queues.queue_array[i]; + struct intel_pt_queue *ptq = queue->priv; + + if (ptq) + ptq->sync_switch = true; + } +} + static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp) { const struct intel_pt_state *state = ptq->state; @@ -1643,7 +1633,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp) if (pt->switch_ip) { intel_pt_log("switch_ip: %"PRIx64" ptss_ip: %"PRIx64"\n", pt->switch_ip, pt->ptss_ip); - pt->sync_switch = true; + intel_pt_enable_sync_switch(pt); } } } @@ -1659,9 +1649,9 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp) if (state->err) { if (state->err == INTEL_PT_ERR_NODATA) return 1; - if (pt->sync_switch && + if (ptq->sync_switch && state->from_ip >= pt->kernel_start) { - pt->sync_switch = false; + ptq->sync_switch = false; intel_pt_next_tid(pt, ptq); } if (pt->synth_opts.errors) { @@ -1687,7 +1677,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp) state->timestamp, state->est_timestamp); ptq->timestamp = state->est_timestamp; /* Use estimated TSC in unknown switch state */ - } else if (pt->sync_switch && + } else if (ptq->sync_switch && ptq->switch_state == INTEL_PT_SS_UNKNOWN && intel_pt_is_switch_ip(ptq, state->to_ip) && ptq->next_tid == -1) { @@ -1834,7 +1824,7 @@ static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid, return 1; ptq = intel_pt_cpu_to_ptq(pt, cpu); - if (!ptq) + if (!ptq || !ptq->sync_switch) return 1; switch (ptq->switch_state) { @@ -2075,9 +2065,6 @@ static int intel_pt_process_auxtrace_event(struct perf_session *session, struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt, auxtrace); - if (pt->sampling_mode) - return 0; - if (!pt->data_queued) { struct auxtrace_buffer *buffer; off_t data_offset; diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index 4952b429caa7..19262f98cd4e 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -14,19 +14,22 @@ #include "config.h" #include "util.h" #include <sys/wait.h> +#include <subcmd/exec-cmd.h> #define CLANG_BPF_CMD_DEFAULT_TEMPLATE \ "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\ "-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE " \ - "$CLANG_OPTIONS $KERNEL_INC_OPTIONS " \ + "$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \ "-Wno-unused-value -Wno-pointer-sign " \ "-working-directory $WORKING_DIR " \ - "-c \"$CLANG_SOURCE\" -target bpf -O2 -o -" + "-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE" struct llvm_param llvm_param = { .clang_path = "clang", + .llc_path = "llc", .clang_bpf_cmd_template = CLANG_BPF_CMD_DEFAULT_TEMPLATE, .clang_opt = NULL, + .opts = NULL, .kbuild_dir = NULL, .kbuild_opts = NULL, .user_set_param = false, @@ -50,6 +53,8 @@ int perf_llvm_config(const char *var, const char *value) llvm_param.kbuild_opts = strdup(value); else if (!strcmp(var, "dump-obj")) llvm_param.dump_obj = !!perf_config_bool(var, value); + else if (!strcmp(var, "opts")) + llvm_param.opts = strdup(value); else { pr_debug("Invalid LLVM config option: %s\n", value); return -1; @@ -212,7 +217,7 @@ version_notice(void) " \t\thttp://llvm.org/apt\n\n" " \tIf you are using old version of clang, change 'clang-bpf-cmd-template'\n" " \toption in [llvm] section of ~/.perfconfig to:\n\n" -" \t \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS \\\n" +" \t \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS \\\n" " \t -working-directory $WORKING_DIR -c $CLANG_SOURCE \\\n" " \t -emit-llvm -o - | /path/to/llc -march=bpf -filetype=obj -o -\"\n" " \t(Replace /path/to/llc with path to your llc)\n\n" @@ -265,16 +270,16 @@ static const char *kinc_fetch_script = "#!/usr/bin/env sh\n" "if ! test -d \"$KBUILD_DIR\"\n" "then\n" -" exit -1\n" +" exit 1\n" "fi\n" "if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n" "then\n" -" exit -1\n" +" exit 1\n" "fi\n" "TMPDIR=`mktemp -d`\n" "if test -z \"$TMPDIR\"\n" "then\n" -" exit -1\n" +" exit 1\n" "fi\n" "cat << EOF > $TMPDIR/Makefile\n" "obj-y := dummy.o\n" @@ -429,10 +434,15 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, unsigned int kernel_version; char linux_version_code_str[64]; const char *clang_opt = llvm_param.clang_opt; - char clang_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64]; + char clang_path[PATH_MAX], llc_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64]; char serr[STRERR_BUFSIZE]; - char *kbuild_dir = NULL, *kbuild_include_opts = NULL; + char *kbuild_dir = NULL, *kbuild_include_opts = NULL, + *perf_bpf_include_opts = NULL; const char *template = llvm_param.clang_bpf_cmd_template; + char *pipe_template = NULL; + const char *opts = llvm_param.opts; + char *command_echo = NULL, *command_out; + char *perf_include_dir = system_path(PERF_INCLUDE_DIR); if (path[0] != '-' && realpath(path, abspath) == NULL) { err = errno; @@ -470,14 +480,36 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, snprintf(linux_version_code_str, sizeof(linux_version_code_str), "0x%x", kernel_version); - + if (asprintf(&perf_bpf_include_opts, "-I%s/bpf", perf_include_dir) < 0) + goto errout; force_set_env("NR_CPUS", nr_cpus_avail_str); force_set_env("LINUX_VERSION_CODE", linux_version_code_str); force_set_env("CLANG_EXEC", clang_path); force_set_env("CLANG_OPTIONS", clang_opt); force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts); + force_set_env("PERF_BPF_INC_OPTIONS", perf_bpf_include_opts); force_set_env("WORKING_DIR", kbuild_dir ? : "."); + if (opts) { + err = search_program(llvm_param.llc_path, "llc", llc_path); + if (err) { + pr_err("ERROR:\tunable to find llc.\n" + "Hint:\tTry to install latest clang/llvm to support BPF. Check your $PATH\n" + " \tand 'llc-path' option in [llvm] section of ~/.perfconfig.\n"); + version_notice(); + goto errout; + } + + if (asprintf(&pipe_template, "%s -emit-llvm | %s -march=bpf %s -filetype=obj -o -", + template, llc_path, opts) < 0) { + pr_err("ERROR:\tnot enough memory to setup command line\n"); + goto errout; + } + + template = pipe_template; + + } + /* * Since we may reset clang's working dir, path of source file * should be transferred into absolute path, except we want @@ -487,6 +519,16 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, (path[0] == '-') ? path : abspath); pr_debug("llvm compiling command template: %s\n", template); + + if (asprintf(&command_echo, "echo -n \"%s\"", template) < 0) + goto errout; + + err = read_from_pipe(command_echo, (void **) &command_out, NULL); + if (err) + goto errout; + + pr_debug("llvm compiling command : %s\n", command_out); + err = read_from_pipe(template, &obj_buf, &obj_buf_sz); if (err) { pr_err("ERROR:\tunable to compile %s\n", path); @@ -497,8 +539,12 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, goto errout; } + free(command_echo); + free(command_out); free(kbuild_dir); free(kbuild_include_opts); + free(perf_bpf_include_opts); + free(perf_include_dir); if (!p_obj_buf) free(obj_buf); @@ -509,9 +555,13 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, *p_obj_buf_sz = obj_buf_sz; return 0; errout: + free(command_echo); free(kbuild_dir); free(kbuild_include_opts); free(obj_buf); + free(perf_bpf_include_opts); + free(perf_include_dir); + free(pipe_template); if (p_obj_buf) *p_obj_buf = NULL; if (p_obj_buf_sz) diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h index d3ad8deb5db4..bf3f3f4c4fe2 100644 --- a/tools/perf/util/llvm-utils.h +++ b/tools/perf/util/llvm-utils.h @@ -11,6 +11,8 @@ struct llvm_param { /* Path of clang executable */ const char *clang_path; + /* Path of llc executable */ + const char *llc_path; /* * Template of clang bpf compiling. 5 env variables * can be used: @@ -23,6 +25,13 @@ struct llvm_param { const char *clang_bpf_cmd_template; /* Will be filled in $CLANG_OPTIONS */ const char *clang_opt; + /* + * If present it'll add -emit-llvm to $CLANG_OPTIONS to pipe + * the clang output to llc, useful for new llvm options not + * yet selectable via 'clang -mllvm option', such as -mattr=dwarfris + * in clang 6.0/llvm 7 + */ + const char *opts; /* Where to find kbuild system */ const char *kbuild_dir; /* diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index 07498eaddc08..b1dd29a9d915 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -3,9 +3,13 @@ #include <lzma.h> #include <stdio.h> #include <linux/compiler.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> #include "compress.h" #include "util.h" #include "debug.h" +#include <unistd.h> #define BUFSIZE 8192 @@ -99,3 +103,19 @@ err_fclose: fclose(infile); return err; } + +bool lzma_is_compressed(const char *input) +{ + int fd = open(input, O_RDONLY); + const uint8_t magic[6] = { 0xFD, '7', 'z', 'X', 'Z', 0x00 }; + char buf[6] = { 0 }; + ssize_t rc; + + if (fd < 0) + return -1; + + rc = read(fd, buf, sizeof(buf)); + close(fd); + return rc == sizeof(buf) ? + memcmp(buf, magic, sizeof(buf)) == 0 : false; +} diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b05a67464c03..c4acd2001db0 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -24,6 +24,7 @@ #include "sane_ctype.h" #include <symbol/kallsyms.h> +#include <linux/mman.h> static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock); @@ -48,8 +49,23 @@ static void machine__threads_init(struct machine *machine) } } +static int machine__set_mmap_name(struct machine *machine) +{ + if (machine__is_host(machine)) + machine->mmap_name = strdup("[kernel.kallsyms]"); + else if (machine__is_default_guest(machine)) + machine->mmap_name = strdup("[guest.kernel.kallsyms]"); + else if (asprintf(&machine->mmap_name, "[guest.kernel.kallsyms.%d]", + machine->pid) < 0) + machine->mmap_name = NULL; + + return machine->mmap_name ? 0 : -ENOMEM; +} + int machine__init(struct machine *machine, const char *root_dir, pid_t pid) { + int err = -ENOMEM; + memset(machine, 0, sizeof(*machine)); map_groups__init(&machine->kmaps, machine); RB_CLEAR_NODE(&machine->rb_node); @@ -66,20 +82,22 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->kptr_restrict_warned = false; machine->comm_exec = false; machine->kernel_start = 0; - - memset(machine->vmlinux_maps, 0, sizeof(machine->vmlinux_maps)); + machine->vmlinux_map = NULL; machine->root_dir = strdup(root_dir); if (machine->root_dir == NULL) return -ENOMEM; + if (machine__set_mmap_name(machine)) + goto out; + if (pid != HOST_KERNEL_ID) { struct thread *thread = machine__findnew_thread(machine, -1, pid); char comm[64]; if (thread == NULL) - return -ENOMEM; + goto out; snprintf(comm, sizeof(comm), "[guest/%d]", pid); thread__set_comm(thread, comm, 0); @@ -87,7 +105,13 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) } machine->current_tid = NULL; + err = 0; +out: + if (err) { + zfree(&machine->root_dir); + zfree(&machine->mmap_name); + } return 0; } @@ -113,13 +137,11 @@ struct machine *machine__new_kallsyms(void) struct machine *machine = machine__new_host(); /* * FIXME: - * 1) MAP__FUNCTION will go away when we stop loading separate maps for - * functions and data objects. - * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely + * 1) We should switch to machine__load_kallsyms(), i.e. not explicitely * ask for not using the kcore parsing code, once this one is fixed * to create a map per module. */ - if (machine && __machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION, true) <= 0) { + if (machine && machine__load_kallsyms(machine, "/proc/kallsyms") <= 0) { machine__delete(machine); machine = NULL; } @@ -180,6 +202,7 @@ void machine__exit(struct machine *machine) dsos__exit(&machine->dsos); machine__exit_vdso(machine); zfree(&machine->root_dir); + zfree(&machine->mmap_name); zfree(&machine->current_tid); for (i = 0; i < THREADS__TABLE_SIZE; i++) { @@ -322,20 +345,6 @@ void machines__process_guests(struct machines *machines, } } -char *machine__mmap_name(struct machine *machine, char *bf, size_t size) -{ - if (machine__is_host(machine)) - snprintf(bf, size, "[%s]", "kernel.kallsyms"); - else if (machine__is_default_guest(machine)) - snprintf(bf, size, "[%s]", "guest.kernel.kallsyms"); - else { - snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms", - machine->pid); - } - - return bf; -} - void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size) { struct rb_node *node; @@ -399,23 +408,16 @@ out_err: } /* - * Caller must eventually drop thread->refcnt returned with a successful - * lookup/new thread inserted. + * Front-end cache - TID lookups come in blocks, + * so most of the time we dont have to look up + * the full rbtree: */ -static struct thread *____machine__findnew_thread(struct machine *machine, - struct threads *threads, - pid_t pid, pid_t tid, - bool create) +static struct thread* +__threads__get_last_match(struct threads *threads, struct machine *machine, + int pid, int tid) { - struct rb_node **p = &threads->entries.rb_node; - struct rb_node *parent = NULL; struct thread *th; - /* - * Front-end cache - TID lookups come in blocks, - * so most of the time we dont have to look up - * the full rbtree: - */ th = threads->last_match; if (th != NULL) { if (th->tid == tid) { @@ -426,12 +428,57 @@ static struct thread *____machine__findnew_thread(struct machine *machine, threads->last_match = NULL; } + return NULL; +} + +static struct thread* +threads__get_last_match(struct threads *threads, struct machine *machine, + int pid, int tid) +{ + struct thread *th = NULL; + + if (perf_singlethreaded) + th = __threads__get_last_match(threads, machine, pid, tid); + + return th; +} + +static void +__threads__set_last_match(struct threads *threads, struct thread *th) +{ + threads->last_match = th; +} + +static void +threads__set_last_match(struct threads *threads, struct thread *th) +{ + if (perf_singlethreaded) + __threads__set_last_match(threads, th); +} + +/* + * Caller must eventually drop thread->refcnt returned with a successful + * lookup/new thread inserted. + */ +static struct thread *____machine__findnew_thread(struct machine *machine, + struct threads *threads, + pid_t pid, pid_t tid, + bool create) +{ + struct rb_node **p = &threads->entries.rb_node; + struct rb_node *parent = NULL; + struct thread *th; + + th = threads__get_last_match(threads, machine, pid, tid); + if (th) + return th; + while (*p != NULL) { parent = *p; th = rb_entry(parent, struct thread, rb_node); if (th->tid == tid) { - threads->last_match = th; + threads__set_last_match(threads, th); machine__update_thread_pid(machine, th, pid); return thread__get(th); } @@ -468,7 +515,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, * It is now in the rbtree, get a ref */ thread__get(th); - threads->last_match = th; + threads__set_last_match(threads, th); ++threads->nr; } @@ -662,8 +709,7 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start, if (kmod_path__parse_name(&m, filename)) return NULL; - map = map_groups__find_by_name(&machine->kmaps, MAP__FUNCTION, - m.name); + map = map_groups__find_by_name(&machine->kmaps, m.name); if (map) { /* * If the map's dso is an offline module, give dso__load() @@ -678,7 +724,7 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start, if (dso == NULL) goto out; - map = map__new2(start, dso, MAP__FUNCTION); + map = map__new2(start, dso); if (map == NULL) goto out; @@ -771,24 +817,18 @@ size_t machine__fprintf(struct machine *machine, FILE *fp) static struct dso *machine__get_kernel(struct machine *machine) { - const char *vmlinux_name = NULL; + const char *vmlinux_name = machine->mmap_name; struct dso *kernel; if (machine__is_host(machine)) { - vmlinux_name = symbol_conf.vmlinux_name; - if (!vmlinux_name) - vmlinux_name = DSO__NAME_KALLSYMS; + if (symbol_conf.vmlinux_name) + vmlinux_name = symbol_conf.vmlinux_name; kernel = machine__findnew_kernel(machine, vmlinux_name, "[kernel]", DSO_TYPE_KERNEL); } else { - char bf[PATH_MAX]; - - if (machine__is_default_guest(machine)) + if (symbol_conf.default_guest_vmlinux_name) vmlinux_name = symbol_conf.default_guest_vmlinux_name; - if (!vmlinux_name) - vmlinux_name = machine__mmap_name(machine, bf, - sizeof(bf)); kernel = machine__findnew_kernel(machine, vmlinux_name, "[guest.kernel]", @@ -805,8 +845,8 @@ struct process_args { u64 start; }; -static void machine__get_kallsyms_filename(struct machine *machine, char *buf, - size_t bufsz) +void machine__get_kallsyms_filename(struct machine *machine, char *buf, + size_t bufsz) { if (machine__is_default_guest(machine)) scnprintf(buf, bufsz, "%s", symbol_conf.default_guest_kallsyms); @@ -849,68 +889,171 @@ static int machine__get_running_kernel_start(struct machine *machine, return 0; } -int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) +int machine__create_extra_kernel_map(struct machine *machine, + struct dso *kernel, + struct extra_kernel_map *xm) { - int type; - u64 start = 0; + struct kmap *kmap; + struct map *map; - if (machine__get_running_kernel_start(machine, NULL, &start)) + map = map__new2(xm->start, kernel); + if (!map) return -1; - /* In case of renewal the kernel map, destroy previous one */ - machine__destroy_kernel_maps(machine); + map->end = xm->end; + map->pgoff = xm->pgoff; - for (type = 0; type < MAP__NR_TYPES; ++type) { - struct kmap *kmap; - struct map *map; + kmap = map__kmap(map); - machine->vmlinux_maps[type] = map__new2(start, kernel, type); - if (machine->vmlinux_maps[type] == NULL) - return -1; + kmap->kmaps = &machine->kmaps; + strlcpy(kmap->name, xm->name, KMAP_NAME_LEN); - machine->vmlinux_maps[type]->map_ip = - machine->vmlinux_maps[type]->unmap_ip = - identity__map_ip; - map = __machine__kernel_map(machine, type); - kmap = map__kmap(map); - if (!kmap) - return -1; + map_groups__insert(&machine->kmaps, map); - kmap->kmaps = &machine->kmaps; - map_groups__insert(&machine->kmaps, map); - } + pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n", + kmap->name, map->start, map->end); + + map__put(map); return 0; } -void machine__destroy_kernel_maps(struct machine *machine) +static u64 find_entry_trampoline(struct dso *dso) { - int type; + /* Duplicates are removed so lookup all aliases */ + const char *syms[] = { + "_entry_trampoline", + "__entry_trampoline_start", + "entry_SYSCALL_64_trampoline", + }; + struct symbol *sym = dso__first_symbol(dso); + unsigned int i; + + for (; sym; sym = dso__next_symbol(sym)) { + if (sym->binding != STB_GLOBAL) + continue; + for (i = 0; i < ARRAY_SIZE(syms); i++) { + if (!strcmp(sym->name, syms[i])) + return sym->start; + } + } - for (type = 0; type < MAP__NR_TYPES; ++type) { - struct kmap *kmap; - struct map *map = __machine__kernel_map(machine, type); + return 0; +} - if (map == NULL) +/* + * These values can be used for kernels that do not have symbols for the entry + * trampolines in kallsyms. + */ +#define X86_64_CPU_ENTRY_AREA_PER_CPU 0xfffffe0000000000ULL +#define X86_64_CPU_ENTRY_AREA_SIZE 0x2c000 +#define X86_64_ENTRY_TRAMPOLINE 0x6000 + +/* Map x86_64 PTI entry trampolines */ +int machine__map_x86_64_entry_trampolines(struct machine *machine, + struct dso *kernel) +{ + struct map_groups *kmaps = &machine->kmaps; + struct maps *maps = &kmaps->maps; + int nr_cpus_avail, cpu; + bool found = false; + struct map *map; + u64 pgoff; + + /* + * In the vmlinux case, pgoff is a virtual address which must now be + * mapped to a vmlinux offset. + */ + for (map = maps__first(maps); map; map = map__next(map)) { + struct kmap *kmap = __map__kmap(map); + struct map *dest_map; + + if (!kmap || !is_entry_trampoline(kmap->name)) continue; - kmap = map__kmap(map); - map_groups__remove(&machine->kmaps, map); - if (kmap && kmap->ref_reloc_sym) { - /* - * ref_reloc_sym is shared among all maps, so free just - * on one of them. - */ - if (type == MAP__FUNCTION) { - zfree((char **)&kmap->ref_reloc_sym->name); - zfree(&kmap->ref_reloc_sym); - } else - kmap->ref_reloc_sym = NULL; - } + dest_map = map_groups__find(kmaps, map->pgoff); + if (dest_map != map) + map->pgoff = dest_map->map_ip(dest_map, map->pgoff); + found = true; + } + if (found || machine->trampolines_mapped) + return 0; + + pgoff = find_entry_trampoline(kernel); + if (!pgoff) + return 0; + + nr_cpus_avail = machine__nr_cpus_avail(machine); + + /* Add a 1 page map for each CPU's entry trampoline */ + for (cpu = 0; cpu < nr_cpus_avail; cpu++) { + u64 va = X86_64_CPU_ENTRY_AREA_PER_CPU + + cpu * X86_64_CPU_ENTRY_AREA_SIZE + + X86_64_ENTRY_TRAMPOLINE; + struct extra_kernel_map xm = { + .start = va, + .end = va + page_size, + .pgoff = pgoff, + }; + + strlcpy(xm.name, ENTRY_TRAMPOLINE_NAME, KMAP_NAME_LEN); + + if (machine__create_extra_kernel_map(machine, kernel, &xm) < 0) + return -1; + } + + machine->trampolines_mapped = nr_cpus_avail; + + return 0; +} + +int __weak machine__create_extra_kernel_maps(struct machine *machine __maybe_unused, + struct dso *kernel __maybe_unused) +{ + return 0; +} + +static int +__machine__create_kernel_maps(struct machine *machine, struct dso *kernel) +{ + struct kmap *kmap; + struct map *map; + + /* In case of renewal the kernel map, destroy previous one */ + machine__destroy_kernel_maps(machine); + + machine->vmlinux_map = map__new2(0, kernel); + if (machine->vmlinux_map == NULL) + return -1; - map__put(machine->vmlinux_maps[type]); - machine->vmlinux_maps[type] = NULL; + machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip; + map = machine__kernel_map(machine); + kmap = map__kmap(map); + if (!kmap) + return -1; + + kmap->kmaps = &machine->kmaps; + map_groups__insert(&machine->kmaps, map); + + return 0; +} + +void machine__destroy_kernel_maps(struct machine *machine) +{ + struct kmap *kmap; + struct map *map = machine__kernel_map(machine); + + if (map == NULL) + return; + + kmap = map__kmap(map); + map_groups__remove(&machine->kmaps, map); + if (kmap && kmap->ref_reloc_sym) { + zfree((char **)&kmap->ref_reloc_sym->name); + zfree(&kmap->ref_reloc_sym); } + + map__zput(machine->vmlinux_map); } int machines__create_guest_kernel_maps(struct machines *machines) @@ -987,49 +1130,35 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid) return machine__create_kernel_maps(machine); } -int __machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type, bool no_kcore) +int machine__load_kallsyms(struct machine *machine, const char *filename) { struct map *map = machine__kernel_map(machine); - int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore); + int ret = __dso__load_kallsyms(map->dso, filename, map, true); if (ret > 0) { - dso__set_loaded(map->dso, type); + dso__set_loaded(map->dso); /* * Since /proc/kallsyms will have multiple sessions for the * kernel, with modules between them, fixup the end of all * sections. */ - __map_groups__fixup_end(&machine->kmaps, type); + map_groups__fixup_end(&machine->kmaps); } return ret; } -int machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type) -{ - return __machine__load_kallsyms(machine, filename, type, false); -} - -int machine__load_vmlinux_path(struct machine *machine, enum map_type type) +int machine__load_vmlinux_path(struct machine *machine) { struct map *map = machine__kernel_map(machine); int ret = dso__load_vmlinux_path(map->dso, map); if (ret > 0) - dso__set_loaded(map->dso, type); + dso__set_loaded(map->dso); return ret; } -static void map_groups__fixup_end(struct map_groups *mg) -{ - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - __map_groups__fixup_end(mg, i); -} - static char *get_kernel_version(const char *root_dir) { char version[PATH_MAX]; @@ -1066,10 +1195,9 @@ static bool is_kmod_dso(struct dso *dso) static int map_groups__set_module_path(struct map_groups *mg, const char *path, struct kmod_path *m) { - struct map *map; char *long_name; + struct map *map = map_groups__find_by_name(mg, m->name); - map = map_groups__find_by_name(mg, MAP__FUNCTION, m->name); if (map == NULL) return 0; @@ -1084,8 +1212,10 @@ static int map_groups__set_module_path(struct map_groups *mg, const char *path, * Full name could reveal us kmod compression, so * we need to update the symtab_type if needed. */ - if (m->comp && is_kmod_dso(map->dso)) + if (m->comp && is_kmod_dso(map->dso)) { map->dso->symtab_type++; + map->dso->comp = m->comp; + } return 0; } @@ -1215,10 +1345,24 @@ static int machine__create_modules(struct machine *machine) return 0; } +static void machine__set_kernel_mmap(struct machine *machine, + u64 start, u64 end) +{ + machine->vmlinux_map->start = start; + machine->vmlinux_map->end = end; + /* + * Be a bit paranoid here, some perf.data file came with + * a zero sized synthesized MMAP event for the kernel. + */ + if (start == 0 && end == 0) + machine->vmlinux_map->end = ~0ULL; +} + int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); const char *name = NULL; + struct map *map; u64 addr = 0; int ret; @@ -1226,9 +1370,8 @@ int machine__create_kernel_maps(struct machine *machine) return -1; ret = __machine__create_kernel_maps(machine, kernel); - dso__put(kernel); if (ret < 0) - return -1; + goto out_put; if (symbol_conf.use_modules && machine__create_modules(machine) < 0) { if (machine__is_host(machine)) @@ -1239,38 +1382,37 @@ int machine__create_kernel_maps(struct machine *machine) "continuing anyway...\n", machine->pid); } - /* - * Now that we have all the maps created, just set the ->end of them: - */ - map_groups__fixup_end(&machine->kmaps); - if (!machine__get_running_kernel_start(machine, &name, &addr)) { if (name && - maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) { + map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, name, addr)) { machine__destroy_kernel_maps(machine); - return -1; + ret = -1; + goto out_put; } - } - return 0; -} + /* we have a real start address now, so re-order the kmaps */ + map = machine__kernel_map(machine); -static void machine__set_kernel_mmap_len(struct machine *machine, - union perf_event *event) -{ - int i; + map__get(map); + map_groups__remove(&machine->kmaps, map); - for (i = 0; i < MAP__NR_TYPES; i++) { - machine->vmlinux_maps[i]->start = event->mmap.start; - machine->vmlinux_maps[i]->end = (event->mmap.start + - event->mmap.len); - /* - * Be a bit paranoid here, some perf.data file came with - * a zero sized synthesized MMAP event for the kernel. - */ - if (machine->vmlinux_maps[i]->end == 0) - machine->vmlinux_maps[i]->end = ~0ULL; + /* assume it's the last in the kmaps */ + machine__set_kernel_mmap(machine, addr, ~0ULL); + + map_groups__insert(&machine->kmaps, map); + map__put(map); } + + if (machine__create_extra_kernel_maps(machine, kernel)) + pr_debug("Problems creating extra kernel maps, continuing anyway...\n"); + + /* update end address of the kernel map using adjacent module address */ + map = map__next(machine__kernel_map(machine)); + if (map) + machine__set_kernel_mmap(machine, addr, map->start); +out_put: + dso__put(kernel); + return ret; } static bool machine__uses_kcore(struct machine *machine) @@ -1285,11 +1427,36 @@ static bool machine__uses_kcore(struct machine *machine) return false; } +static bool perf_event__is_extra_kernel_mmap(struct machine *machine, + union perf_event *event) +{ + return machine__is(machine, "x86_64") && + is_entry_trampoline(event->mmap.filename); +} + +static int machine__process_extra_kernel_map(struct machine *machine, + union perf_event *event) +{ + struct map *kernel_map = machine__kernel_map(machine); + struct dso *kernel = kernel_map ? kernel_map->dso : NULL; + struct extra_kernel_map xm = { + .start = event->mmap.start, + .end = event->mmap.start + event->mmap.len, + .pgoff = event->mmap.pgoff, + }; + + if (kernel == NULL) + return -1; + + strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN); + + return machine__create_extra_kernel_map(machine, kernel, &xm); +} + static int machine__process_kernel_mmap_event(struct machine *machine, union perf_event *event) { struct map *map; - char kmmap_prefix[PATH_MAX]; enum dso_kernel_type kernel_type; bool is_kernel_mmap; @@ -1297,15 +1464,14 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (machine__uses_kcore(machine)) return 0; - machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix)); if (machine__is_host(machine)) kernel_type = DSO_TYPE_KERNEL; else kernel_type = DSO_TYPE_GUEST_KERNEL; is_kernel_mmap = memcmp(event->mmap.filename, - kmmap_prefix, - strlen(kmmap_prefix) - 1) == 0; + machine->mmap_name, + strlen(machine->mmap_name) - 1) == 0; if (event->mmap.filename[0] == '/' || (!is_kernel_mmap && event->mmap.filename[0] == '[')) { map = machine__findnew_module_map(machine, event->mmap.start, @@ -1316,7 +1482,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, map->end = map->start + event->mmap.len; } else if (is_kernel_mmap) { const char *symbol_name = (event->mmap.filename + - strlen(kmmap_prefix)); + strlen(machine->mmap_name)); /* * Should be there already, from the build-id table in * the header. @@ -1357,7 +1523,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, up_read(&machine->dsos.lock); if (kernel == NULL) - kernel = machine__findnew_dso(machine, kmmap_prefix); + kernel = machine__findnew_dso(machine, machine->mmap_name); if (kernel == NULL) goto out_problem; @@ -1370,7 +1536,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (strstr(kernel->long_name, "vmlinux")) dso__set_short_name(kernel, "[kernel.vmlinux]", false); - machine__set_kernel_mmap_len(machine, event); + machine__set_kernel_mmap(machine, event->mmap.start, + event->mmap.start + event->mmap.len); /* * Avoid using a zero address (kptr_restrict) for the ref reloc @@ -1378,9 +1545,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine, * time /proc/sys/kernel/kptr_restrict was non zero. */ if (event->mmap.pgoff != 0) { - maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, - symbol_name, - event->mmap.pgoff); + map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, + symbol_name, + event->mmap.pgoff); } if (machine__is_default_guest(machine)) { @@ -1389,6 +1556,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine, */ dso__load(kernel, machine__kernel_map(machine)); } + } else if (perf_event__is_extra_kernel_mmap(machine, event)) { + return machine__process_extra_kernel_map(machine, event); } return 0; out_problem: @@ -1401,7 +1570,6 @@ int machine__process_mmap2_event(struct machine *machine, { struct thread *thread; struct map *map; - enum map_type type; int ret = 0; if (dump_trace) @@ -1420,11 +1588,6 @@ int machine__process_mmap2_event(struct machine *machine, if (thread == NULL) goto out_problem; - if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) - type = MAP__VARIABLE; - else - type = MAP__FUNCTION; - map = map__new(machine, event->mmap2.start, event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj, @@ -1432,7 +1595,7 @@ int machine__process_mmap2_event(struct machine *machine, event->mmap2.ino_generation, event->mmap2.prot, event->mmap2.flags, - event->mmap2.filename, type, thread); + event->mmap2.filename, thread); if (map == NULL) goto out_problem_map; @@ -1459,7 +1622,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event { struct thread *thread; struct map *map; - enum map_type type; + u32 prot = 0; int ret = 0; if (dump_trace) @@ -1478,16 +1641,14 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event if (thread == NULL) goto out_problem; - if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) - type = MAP__VARIABLE; - else - type = MAP__FUNCTION; + if (!(event->header.misc & PERF_RECORD_MISC_MMAP_DATA)) + prot = PROT_EXEC; map = map__new(machine, event->mmap.start, event->mmap.len, event->mmap.pgoff, - 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, prot, 0, event->mmap.filename, - type, thread); + thread); if (map == NULL) goto out_problem_map; @@ -1514,7 +1675,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th, struct threads *threads = machine__threads(machine, th->tid); if (threads->last_match == th) - threads->last_match = NULL; + threads__set_last_match(threads, NULL); BUG_ON(refcount_read(&th->refcnt) == 0); if (lock) @@ -1663,7 +1824,7 @@ static void ip__resolve_ams(struct thread *thread, * Thus, we have to try consecutively until we find a match * or else, the symbol is unknown */ - thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al); + thread__find_cpumode_addr_location(thread, ip, &al); ams->addr = ip; ams->al_addr = al.addr; @@ -1680,15 +1841,7 @@ static void ip__resolve_data(struct thread *thread, memset(&al, 0, sizeof(al)); - thread__find_addr_location(thread, m, MAP__VARIABLE, addr, &al); - if (al.map == NULL) { - /* - * some shared data regions have execute bit set which puts - * their mapping in the MAP__FUNCTION type array. - * Check there as a fallback option before dropping the sample. - */ - thread__find_addr_location(thread, m, MAP__FUNCTION, addr, &al); - } + thread__find_symbol(thread, m, addr, &al); ams->addr = addr; ams->al_addr = al.addr; @@ -1700,7 +1853,7 @@ static void ip__resolve_data(struct thread *thread, struct mem_info *sample__resolve_mem(struct perf_sample *sample, struct addr_location *al) { - struct mem_info *mi = zalloc(sizeof(*mi)); + struct mem_info *mi = mem_info__new(); if (!mi) return NULL; @@ -1757,8 +1910,7 @@ static int add_callchain_ip(struct thread *thread, al.filtered = 0; al.sym = NULL; if (!cpumode) { - thread__find_cpumode_addr_location(thread, MAP__FUNCTION, - ip, &al); + thread__find_cpumode_addr_location(thread, ip, &al); } else { if (ip >= PERF_CONTEXT_MAX) { switch (ip) { @@ -1783,8 +1935,7 @@ static int add_callchain_ip(struct thread *thread, } return 0; } - thread__find_addr_location(thread, *cpumode, MAP__FUNCTION, - ip, &al); + thread__find_symbol(thread, *cpumode, ip, &al); } if (al.sym != NULL) { @@ -1809,7 +1960,7 @@ static int add_callchain_ip(struct thread *thread, } srcline = callchain_srcline(al.map, al.sym, al.addr); - return callchain_cursor_append(cursor, al.addr, al.map, al.sym, + return callchain_cursor_append(cursor, ip, al.map, al.sym, branch, flags, nr_loop_iter, iter_cycles, branch_from, srcline); } @@ -2161,6 +2312,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) { struct callchain_cursor *cursor = arg; const char *srcline = NULL; + u64 addr; if (symbol_conf.hide_unresolved && entry->sym == NULL) return 0; @@ -2168,7 +2320,13 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0) return 0; - srcline = callchain_srcline(entry->map, entry->sym, entry->ip); + /* + * Convert entry->ip from a virtual address to an offset in + * its corresponding binary. + */ + addr = map__map_ip(entry->map, entry->ip); + + srcline = callchain_srcline(entry->map, entry->sym, addr); return callchain_cursor_append(cursor, entry->ip, entry->map, entry->sym, false, NULL, 0, 0, 0, srcline); @@ -2341,6 +2499,20 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, return 0; } +/* + * Compares the raw arch string. N.B. see instead perf_env__arch() 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); +} + +int machine__nr_cpus_avail(struct machine *machine) +{ + return machine ? perf_env__nr_cpus_avail(machine->env) : 0; +} + int machine__get_kernel_start(struct machine *machine) { struct map *map = machine__kernel_map(machine); @@ -2357,7 +2529,12 @@ int machine__get_kernel_start(struct machine *machine) machine->kernel_start = 1ULL << 63; if (map) { err = map__load(map); - if (!err) + /* + * On x86_64, PTI entry trampolines are less than the + * start of kernel text, but still above 2^63. So leave + * kernel_start = 1ULL << 63 for x86_64. + */ + if (!err && !machine__is(machine, "x86_64")) machine->kernel_start = map->start; } return err; @@ -2372,7 +2549,7 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch { struct machine *machine = vmachine; struct map *map; - struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map); + struct symbol *sym = machine__find_kernel_symbol(machine, *addrp, &map); if (sym == NULL) return NULL; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 5ce860b64c74..d856b85862e2 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -43,18 +43,20 @@ struct machine { bool comm_exec; bool kptr_restrict_warned; char *root_dir; + char *mmap_name; struct threads threads[THREADS__TABLE_SIZE]; struct vdso_info *vdso_info; struct perf_env *env; struct dsos dsos; struct map_groups kmaps; - struct map *vmlinux_maps[MAP__NR_TYPES]; + struct map *vmlinux_map; u64 kernel_start; pid_t *current_tid; union { /* Tool specific area */ void *priv; u64 db_id; }; + bool trampolines_mapped; }; static inline struct threads *machine__threads(struct machine *machine, pid_t tid) @@ -63,16 +65,22 @@ static inline struct threads *machine__threads(struct machine *machine, pid_t ti return &machine->threads[(unsigned int)tid % THREADS__TABLE_SIZE]; } +/* + * The main kernel (vmlinux) map + */ static inline -struct map *__machine__kernel_map(struct machine *machine, enum map_type type) +struct map *machine__kernel_map(struct machine *machine) { - return machine->vmlinux_maps[type]; + return machine->vmlinux_map; } +/* + * kernel (the one returned by machine__kernel_map()) plus kernel modules maps + */ static inline -struct map *machine__kernel_map(struct machine *machine) +struct maps *machine__kernel_maps(struct machine *machine) { - return __machine__kernel_map(machine, MAP__FUNCTION); + return &machine->kmaps.maps; } int machine__get_kernel_start(struct machine *machine); @@ -142,8 +150,6 @@ struct machine *machines__find(struct machines *machines, pid_t pid); struct machine *machines__findnew(struct machines *machines, pid_t pid); void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size); -char *machine__mmap_name(struct machine *machine, char *bf, size_t size); - void machines__set_comm_exec(struct machines *machines, bool comm_exec); struct machine *machine__new_host(void); @@ -183,6 +189,9 @@ static inline bool machine__is_host(struct machine *machine) return machine ? machine->pid == HOST_KERNEL_ID : false; } +bool machine__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); struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid); @@ -191,46 +200,27 @@ struct dso *machine__findnew_dso(struct machine *machine, const char *filename); size_t machine__fprintf(struct machine *machine, FILE *fp); static inline -struct symbol *machine__find_kernel_symbol(struct machine *machine, - enum map_type type, u64 addr, +struct symbol *machine__find_kernel_symbol(struct machine *machine, u64 addr, struct map **mapp) { - return map_groups__find_symbol(&machine->kmaps, type, addr, mapp); + return map_groups__find_symbol(&machine->kmaps, addr, mapp); } static inline struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine, - enum map_type type, const char *name, + const char *name, struct map **mapp) { - return map_groups__find_symbol_by_name(&machine->kmaps, type, name, mapp); -} - -static inline -struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr, - struct map **mapp) -{ - return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr, - mapp); -} - -static inline -struct symbol *machine__find_kernel_function_by_name(struct machine *machine, - const char *name, - struct map **mapp) -{ - return map_groups__find_function_by_name(&machine->kmaps, name, mapp); + return map_groups__find_symbol_by_name(&machine->kmaps, name, mapp); } struct map *machine__findnew_module_map(struct machine *machine, u64 start, const char *filename); int arch__fix_module_text_start(u64 *start, const char *name); -int __machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type, bool no_kcore); -int machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type); -int machine__load_vmlinux_path(struct machine *machine, enum map_type type); +int machine__load_kallsyms(struct machine *machine, const char *filename); + +int machine__load_vmlinux_path(struct machine *machine); size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, bool (skip)(struct dso *dso, int parm), int parm); @@ -239,7 +229,6 @@ size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp, bool (skip)(struct dso *dso, int parm), int parm); void machine__destroy_kernel_maps(struct machine *machine); -int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel); int machine__create_kernel_maps(struct machine *machine); int machines__create_kernel_maps(struct machines *machines, pid_t pid); @@ -276,8 +265,29 @@ pid_t machine__get_current_tid(struct machine *machine, int cpu); int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid, pid_t tid); /* - * For use with libtraceevent's pevent_set_function_resolver() + * For use with libtraceevent's tep_set_function_resolver() */ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp); +void machine__get_kallsyms_filename(struct machine *machine, char *buf, + size_t bufsz); + +int machine__create_extra_kernel_maps(struct machine *machine, + struct dso *kernel); + +/* Kernel-space maps for symbols that are outside the main kernel map and module maps */ +struct extra_kernel_map { + u64 start; + u64 end; + u64 pgoff; + char name[KMAP_NAME_LEN]; +}; + +int machine__create_extra_kernel_map(struct machine *machine, + struct dso *kernel, + struct extra_kernel_map *xm); + +int machine__map_x86_64_entry_trampolines(struct machine *machine, + struct dso *kernel); + #endif /* __PERF_MACHINE_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 8fe57031e1a8..6a6929f208b4 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -22,11 +22,6 @@ static void __maps__insert(struct maps *maps, struct map *map); -const char *map_type__name[MAP__NR_TYPES] = { - [MAP__FUNCTION] = "Functions", - [MAP__VARIABLE] = "Variables", -}; - static inline int is_anon_memory(const char *filename, u32 flags) { return flags & MAP_HUGETLB || @@ -129,10 +124,8 @@ static inline bool replace_android_lib(const char *filename, char *newfilename) return false; } -void map__init(struct map *map, enum map_type type, - u64 start, u64 end, u64 pgoff, struct dso *dso) +void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso) { - map->type = type; map->start = start; map->end = end; map->pgoff = pgoff; @@ -149,7 +142,7 @@ void map__init(struct map *map, enum map_type type, struct map *map__new(struct machine *machine, u64 start, u64 len, u64 pgoff, u32 d_maj, u32 d_min, u64 ino, u64 ino_gen, u32 prot, u32 flags, char *filename, - enum map_type type, struct thread *thread) + struct thread *thread) { struct map *map = malloc(sizeof(*map)); struct nsinfo *nsi = NULL; @@ -173,7 +166,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, map->flags = flags; nsi = nsinfo__get(thread->nsinfo); - if ((anon || no_dso) && nsi && type == MAP__FUNCTION) { + if ((anon || no_dso) && nsi && (prot & PROT_EXEC)) { snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", nsi->pid); filename = newfilename; @@ -203,7 +196,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, if (dso == NULL) goto out_delete; - map__init(map, type, start, start + len, pgoff, dso); + map__init(map, start, start + len, pgoff, dso); if (anon || no_dso) { map->map_ip = map->unmap_ip = identity__map_ip; @@ -213,8 +206,8 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, * functions still return NULL, and we avoid the * unnecessary map__load warning. */ - if (type != MAP__FUNCTION) - dso__set_loaded(dso, map->type); + if (!(prot & PROT_EXEC)) + dso__set_loaded(dso); } dso->nsinfo = nsi; dso__put(dso); @@ -231,7 +224,7 @@ out_delete: * they are loaded) and for vmlinux, where only after we load all the * symbols we'll know where it starts and ends. */ -struct map *map__new2(u64 start, struct dso *dso, enum map_type type) +struct map *map__new2(u64 start, struct dso *dso) { struct map *map = calloc(1, (sizeof(*map) + (dso->kernel ? sizeof(struct kmap) : 0))); @@ -239,7 +232,7 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type) /* * ->end will be filled after we load all the symbols */ - map__init(map, type, start, 0, 0, dso); + map__init(map, start, 0, 0, dso); } return map; @@ -256,7 +249,19 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type) */ bool __map__is_kernel(const struct map *map) { - return __machine__kernel_map(map->groups->machine, map->type) == map; + return machine__kernel_map(map->groups->machine) == map; +} + +bool __map__is_extra_kernel_map(const struct map *map) +{ + struct kmap *kmap = __map__kmap((struct map *)map); + + return kmap && kmap->name[0]; +} + +bool map__has_symbols(const struct map *map) +{ + return dso__has_symbols(map->dso); } static void map__exit(struct map *map) @@ -279,7 +284,7 @@ void map__put(struct map *map) void map__fixup_start(struct map *map) { - struct rb_root *symbols = &map->dso->symbols[map->type]; + struct rb_root *symbols = &map->dso->symbols; struct rb_node *nd = rb_first(symbols); if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); @@ -289,7 +294,7 @@ void map__fixup_start(struct map *map) void map__fixup_end(struct map *map) { - struct rb_root *symbols = &map->dso->symbols[map->type]; + struct rb_root *symbols = &map->dso->symbols; struct rb_node *nd = rb_last(symbols); if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); @@ -304,7 +309,7 @@ int map__load(struct map *map) const char *name = map->dso->long_name; int nr; - if (dso__loaded(map->dso, map->type)) + if (dso__loaded(map->dso)) return 0; nr = dso__load(map->dso, map); @@ -348,7 +353,7 @@ struct symbol *map__find_symbol(struct map *map, u64 addr) if (map__load(map) < 0) return NULL; - return dso__find_symbol(map->dso, map->type, addr); + return dso__find_symbol(map->dso, addr); } struct symbol *map__find_symbol_by_name(struct map *map, const char *name) @@ -356,10 +361,10 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name) if (map__load(map) < 0) return NULL; - if (!dso__sorted_by_name(map->dso, map->type)) - dso__sort_by_name(map->dso, map->type); + if (!dso__sorted_by_name(map->dso)) + dso__sort_by_name(map->dso); - return dso__find_symbol_by_name(map->dso, map->type, name); + return dso__find_symbol_by_name(map->dso, name); } struct map *map__clone(struct map *from) @@ -376,20 +381,6 @@ struct map *map__clone(struct map *from) return map; } -int map__overlap(struct map *l, struct map *r) -{ - if (l->start > r->start) { - struct map *t = l; - l = r; - r = t; - } - - if (l->end > r->start) - return 1; - - return 0; -} - size_t map__fprintf(struct map *map, FILE *fp) { return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n", @@ -410,16 +401,20 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp) return fprintf(fp, "%s", dsoname); } +char *map__srcline(struct map *map, u64 addr, struct symbol *sym) +{ + if (map == NULL) + return SRCLINE_UNKNOWN; + return get_srcline(map->dso, map__rip_2objdump(map, addr), sym, true, true, addr); +} + int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, FILE *fp) { - char *srcline; int ret = 0; if (map && map->dso) { - srcline = get_srcline(map->dso, - map__rip_2objdump(map, addr), NULL, - true, true, addr); + char *srcline = map__srcline(map, addr, NULL); if (srcline != SRCLINE_UNKNOWN) ret = fprintf(fp, "%s%s", prefix, srcline); free_srcline(srcline); @@ -440,6 +435,20 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, */ u64 map__rip_2objdump(struct map *map, u64 rip) { + struct kmap *kmap = __map__kmap(map); + + /* + * vmlinux does not have program headers for PTI entry trampolines and + * kcore may not either. However the trampoline object code is on the + * main kernel map, so just use that instead. + */ + if (kmap && is_entry_trampoline(kmap->name) && kmap->kmaps && kmap->kmaps->machine) { + struct map *kernel_map = machine__kernel_map(kmap->kmaps->machine); + + if (kernel_map) + map = kernel_map; + } + if (!map->dso->adjust_symbols) return rip; @@ -494,10 +503,7 @@ static void maps__init(struct maps *maps) void map_groups__init(struct map_groups *mg, struct machine *machine) { - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) { - maps__init(&mg->maps[i]); - } + maps__init(&mg->maps); mg->machine = machine; refcount_set(&mg->refcnt, 1); } @@ -525,22 +531,12 @@ static void maps__exit(struct maps *maps) void map_groups__exit(struct map_groups *mg) { - int i; - - for (i = 0; i < MAP__NR_TYPES; ++i) - maps__exit(&mg->maps[i]); + maps__exit(&mg->maps); } bool map_groups__empty(struct map_groups *mg) { - int i; - - for (i = 0; i < MAP__NR_TYPES; ++i) { - if (maps__first(&mg->maps[i])) - return false; - } - - return true; + return !maps__first(&mg->maps); } struct map_groups *map_groups__new(struct machine *machine) @@ -566,10 +562,9 @@ void map_groups__put(struct map_groups *mg) } struct symbol *map_groups__find_symbol(struct map_groups *mg, - enum map_type type, u64 addr, - struct map **mapp) + u64 addr, struct map **mapp) { - struct map *map = map_groups__find(mg, type, addr); + struct map *map = map_groups__find(mg, addr); /* Ensure map is loaded before using map->map_ip */ if (map != NULL && map__load(map) >= 0) { @@ -581,6 +576,13 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg, return NULL; } +static bool map__contains_symbol(struct map *map, struct symbol *sym) +{ + u64 ip = map->unmap_ip(map, sym->start); + + return ip >= map->start && ip < map->end; +} + struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp) { @@ -596,6 +598,10 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, if (sym == NULL) continue; + if (!map__contains_symbol(pos, sym)) { + sym = NULL; + continue; + } if (mapp != NULL) *mapp = pos; goto out; @@ -608,13 +614,10 @@ out: } struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, - enum map_type type, const char *name, struct map **mapp) { - struct symbol *sym = maps__find_symbol_by_name(&mg->maps[type], name, mapp); - - return sym; + return maps__find_symbol_by_name(&mg->maps, name, mapp); } int map_groups__find_ams(struct addr_map_symbol *ams) @@ -622,8 +625,7 @@ int map_groups__find_ams(struct addr_map_symbol *ams) if (ams->addr < ams->map->start || ams->addr >= ams->map->end) { if (ams->map->groups == NULL) return -1; - ams->map = map_groups__find(ams->map->groups, ams->map->type, - ams->addr); + ams->map = map_groups__find(ams->map->groups, ams->addr); if (ams->map == NULL) return -1; } @@ -646,7 +648,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp) printed += fprintf(fp, "Map:"); printed += map__fprintf(pos, fp); if (verbose > 2) { - printed += dso__fprintf(pos->dso, pos->type, fp); + printed += dso__fprintf(pos->dso, fp); printed += fprintf(fp, "--\n"); } } @@ -656,44 +658,56 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp) return printed; } -size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, - FILE *fp) -{ - size_t printed = fprintf(fp, "%s:\n", map_type__name[type]); - return printed += maps__fprintf(&mg->maps[type], fp); -} - size_t map_groups__fprintf(struct map_groups *mg, FILE *fp) { - size_t printed = 0, i; - for (i = 0; i < MAP__NR_TYPES; ++i) - printed += __map_groups__fprintf_maps(mg, i, fp); - return printed; + return maps__fprintf(&mg->maps, fp); } static void __map_groups__insert(struct map_groups *mg, struct map *map) { - __maps__insert(&mg->maps[map->type], map); + __maps__insert(&mg->maps, map); map->groups = mg; } static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) { struct rb_root *root; - struct rb_node *next; + struct rb_node *next, *first; int err = 0; down_write(&maps->lock); root = &maps->entries; - next = rb_first(root); + /* + * Find first map where end > map->start. + * Same as find_vma() in kernel. + */ + next = root->rb_node; + first = NULL; + while (next) { + struct map *pos = rb_entry(next, struct map, rb_node); + + if (pos->end > map->start) { + first = next; + if (pos->start <= map->start) + break; + next = next->rb_left; + } else + next = next->rb_right; + } + + next = first; while (next) { struct map *pos = rb_entry(next, struct map, rb_node); next = rb_next(&pos->rb_node); - if (!map__overlap(pos, map)) - continue; + /* + * Stop if current map starts after map->end. + * Maps are ordered by start: next will not overlap for sure. + */ + if (pos->start >= map->end) + break; if (verbose >= 2) { @@ -758,19 +772,18 @@ out: int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE *fp) { - return maps__fixup_overlappings(&mg->maps[map->type], map, fp); + return maps__fixup_overlappings(&mg->maps, map, fp); } /* * XXX This should not really _copy_ te maps, but refcount them. */ -int map_groups__clone(struct thread *thread, - struct map_groups *parent, enum map_type type) +int map_groups__clone(struct thread *thread, struct map_groups *parent) { struct map_groups *mg = thread->mg; int err = -ENOMEM; struct map *map; - struct maps *maps = &parent->maps[type]; + struct maps *maps = &parent->maps; down_read(&maps->lock); @@ -877,15 +890,22 @@ struct map *map__next(struct map *map) return NULL; } -struct kmap *map__kmap(struct map *map) +struct kmap *__map__kmap(struct map *map) { - if (!map->dso || !map->dso->kernel) { - pr_err("Internal error: map__kmap with a non-kernel map\n"); + if (!map->dso || !map->dso->kernel) return NULL; - } return (struct kmap *)(map + 1); } +struct kmap *map__kmap(struct map *map) +{ + struct kmap *kmap = __map__kmap(map); + + if (!kmap) + pr_err("Internal error: map__kmap with a non-kernel map\n"); + return kmap; +} + struct map_groups *map__kmaps(struct map *map) { struct kmap *kmap = map__kmap(map); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index edeb7291c8e1..e0f327b51e66 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -8,19 +8,11 @@ #include <linux/rbtree.h> #include <pthread.h> #include <stdio.h> +#include <string.h> #include <stdbool.h> #include <linux/types.h> #include "rwsem.h" -enum map_type { - MAP__FUNCTION = 0, - MAP__VARIABLE, -}; - -#define MAP__NR_TYPES (MAP__VARIABLE + 1) - -extern const char *map_type__name[MAP__NR_TYPES]; - struct dso; struct ip_callchain; struct ref_reloc_sym; @@ -35,7 +27,6 @@ struct map { }; u64 start; u64 end; - u8 /* enum map_type */ type; bool erange_warned; u32 priv; u32 prot; @@ -56,9 +47,12 @@ struct map { refcount_t refcnt; }; +#define KMAP_NAME_LEN 256 + struct kmap { struct ref_reloc_sym *ref_reloc_sym; struct map_groups *kmaps; + char name[KMAP_NAME_LEN]; }; struct maps { @@ -67,7 +61,7 @@ struct maps { }; struct map_groups { - struct maps maps[MAP__NR_TYPES]; + struct maps maps; struct machine *machine; refcount_t refcnt; }; @@ -85,6 +79,7 @@ static inline struct map_groups *map_groups__get(struct map_groups *mg) void map_groups__put(struct map_groups *mg); +struct kmap *__map__kmap(struct map *map); struct kmap *map__kmap(struct map *map); struct map_groups *map__kmaps(struct map *map); @@ -103,6 +98,10 @@ static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip) return ip; } +static inline size_t map__size(const struct map *map) +{ + return map->end - map->start; +} /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */ u64 map__rip_2objdump(struct map *map, u64 rip); @@ -121,7 +120,7 @@ struct thread; * Note: caller must ensure map->dso is not NULL (map is loaded). */ #define map__for_each_symbol(map, pos, n) \ - dso__for_each_symbol(map->dso, pos, n, map->type) + dso__for_each_symbol(map->dso, pos, n) /* map__for_each_symbol_with_name - iterate over the symbols in the given map * that have the given name @@ -140,13 +139,13 @@ struct thread; #define map__for_each_symbol_by_name(map, sym_name, pos) \ __map__for_each_symbol_by_name(map, sym_name, (pos)) -void map__init(struct map *map, enum map_type type, +void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct machine *machine, u64 start, u64 len, u64 pgoff, u32 d_maj, u32 d_min, u64 ino, u64 ino_gen, u32 prot, u32 flags, - char *filename, enum map_type type, struct thread *thread); -struct map *map__new2(u64 start, struct dso *dso, enum map_type type); + char *filename, struct thread *thread); +struct map *map__new2(u64 start, struct dso *dso); void map__delete(struct map *map); struct map *map__clone(struct map *map); @@ -167,9 +166,9 @@ static inline void __map__zput(struct map **map) #define map__zput(map) __map__zput(&map) -int map__overlap(struct map *l, struct map *r); size_t map__fprintf(struct map *map, FILE *fp); size_t map__fprintf_dsoname(struct map *map, FILE *fp); +char *map__srcline(struct map *map, u64 addr, struct symbol *sym); int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, FILE *fp); @@ -181,8 +180,6 @@ void map__fixup_end(struct map *map); void map__reloc_vmlinux(struct map *map); -size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, - FILE *fp); void maps__insert(struct maps *maps, struct map *map); void maps__remove(struct maps *maps, struct map *map); struct map *maps__find(struct maps *maps, u64 addr); @@ -193,34 +190,29 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, void map_groups__init(struct map_groups *mg, struct machine *machine); void map_groups__exit(struct map_groups *mg); int map_groups__clone(struct thread *thread, - struct map_groups *parent, enum map_type type); + struct map_groups *parent); size_t map_groups__fprintf(struct map_groups *mg, FILE *fp); -int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, - u64 addr); +int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, + u64 addr); static inline void map_groups__insert(struct map_groups *mg, struct map *map) { - maps__insert(&mg->maps[map->type], map); + maps__insert(&mg->maps, map); map->groups = mg; } static inline void map_groups__remove(struct map_groups *mg, struct map *map) { - maps__remove(&mg->maps[map->type], map); + maps__remove(&mg->maps, map); } -static inline struct map *map_groups__find(struct map_groups *mg, - enum map_type type, u64 addr) +static inline struct map *map_groups__find(struct map_groups *mg, u64 addr) { - return maps__find(&mg->maps[type], addr); + return maps__find(&mg->maps, addr); } -static inline struct map *map_groups__first(struct map_groups *mg, - enum map_type type) -{ - return maps__first(&mg->maps[type]); -} +struct map *map_groups__first(struct map_groups *mg); static inline struct map *map_groups__next(struct map *map) { @@ -228,11 +220,9 @@ static inline struct map *map_groups__next(struct map *map) } struct symbol *map_groups__find_symbol(struct map_groups *mg, - enum map_type type, u64 addr, - struct map **mapp); + u64 addr, struct map **mapp); struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, - enum map_type type, const char *name, struct map **mapp); @@ -240,24 +230,26 @@ struct addr_map_symbol; int map_groups__find_ams(struct addr_map_symbol *ams); -static inline -struct symbol *map_groups__find_function_by_name(struct map_groups *mg, - const char *name, struct map **mapp) -{ - return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp); -} - int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE *fp); -struct map *map_groups__find_by_name(struct map_groups *mg, - enum map_type type, const char *name); +struct map *map_groups__find_by_name(struct map_groups *mg, const char *name); bool __map__is_kernel(const struct map *map); +bool __map__is_extra_kernel_map(const struct map *map); static inline bool __map__is_kmodule(const struct map *map) { - return !__map__is_kernel(map); + return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map); +} + +bool map__has_symbols(const struct map *map); + +#define ENTRY_TRAMPOLINE_NAME "__entry_SYSCALL_64_trampoline" + +static inline bool is_entry_trampoline(const char *name) +{ + return !strcmp(name, ENTRY_TRAMPOLINE_NAME); } #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c new file mode 100644 index 000000000000..c6fd81c02586 --- /dev/null +++ b/tools/perf/util/mem2node.c @@ -0,0 +1,134 @@ +#include <errno.h> +#include <inttypes.h> +#include <linux/bitmap.h> +#include "mem2node.h" +#include "util.h" + +struct phys_entry { + struct rb_node rb_node; + u64 start; + u64 end; + u64 node; +}; + +static void phys_entry__insert(struct phys_entry *entry, struct rb_root *root) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct phys_entry *e; + + while (*p != NULL) { + parent = *p; + e = rb_entry(parent, struct phys_entry, rb_node); + + if (entry->start < e->start) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&entry->rb_node, parent, p); + rb_insert_color(&entry->rb_node, root); +} + +static void +phys_entry__init(struct phys_entry *entry, u64 start, u64 bsize, u64 node) +{ + entry->start = start; + entry->end = start + bsize; + entry->node = node; + RB_CLEAR_NODE(&entry->rb_node); +} + +int mem2node__init(struct mem2node *map, struct perf_env *env) +{ + struct memory_node *n, *nodes = &env->memory_nodes[0]; + struct phys_entry *entries, *tmp_entries; + u64 bsize = env->memory_bsize; + int i, j = 0, max = 0; + + memset(map, 0x0, sizeof(*map)); + map->root = RB_ROOT; + + for (i = 0; i < env->nr_memory_nodes; i++) { + n = &nodes[i]; + max += bitmap_weight(n->set, n->size); + } + + entries = zalloc(sizeof(*entries) * max); + if (!entries) + return -ENOMEM; + + for (i = 0; i < env->nr_memory_nodes; i++) { + u64 bit; + + n = &nodes[i]; + + for (bit = 0; bit < n->size; bit++) { + u64 start; + + if (!test_bit(bit, n->set)) + continue; + + start = bit * bsize; + + /* + * Merge nearby areas, we walk in order + * through the bitmap, so no need to sort. + */ + if (j > 0) { + struct phys_entry *prev = &entries[j - 1]; + + if ((prev->end == start) && + (prev->node == n->node)) { + prev->end += bsize; + continue; + } + } + + phys_entry__init(&entries[j++], start, bsize, n->node); + } + } + + /* Cut unused entries, due to merging. */ + tmp_entries = realloc(entries, sizeof(*entries) * j); + if (tmp_entries) + entries = tmp_entries; + + for (i = 0; i < j; i++) { + pr_debug("mem2node %03" PRIu64 " [0x%016" PRIx64 "-0x%016" PRIx64 "]\n", + entries[i].node, entries[i].start, entries[i].end); + + phys_entry__insert(&entries[i], &map->root); + } + + map->entries = entries; + return 0; +} + +void mem2node__exit(struct mem2node *map) +{ + zfree(&map->entries); +} + +int mem2node__node(struct mem2node *map, u64 addr) +{ + struct rb_node **p, *parent = NULL; + struct phys_entry *entry; + + p = &map->root.rb_node; + while (*p != NULL) { + parent = *p; + entry = rb_entry(parent, struct phys_entry, rb_node); + if (addr < entry->start) + p = &(*p)->rb_left; + else if (addr >= entry->end) + p = &(*p)->rb_right; + else + goto out; + } + + entry = NULL; +out: + return entry ? (int) entry->node : -1; +} diff --git a/tools/perf/util/mem2node.h b/tools/perf/util/mem2node.h new file mode 100644 index 000000000000..59c4752a2181 --- /dev/null +++ b/tools/perf/util/mem2node.h @@ -0,0 +1,19 @@ +#ifndef __MEM2NODE_H +#define __MEM2NODE_H + +#include <linux/rbtree.h> +#include "env.h" + +struct phys_entry; + +struct mem2node { + struct rb_root root; + struct phys_entry *entries; + int cnt; +}; + +int mem2node__init(struct mem2node *map, struct perf_env *env); +void mem2node__exit(struct mem2node *map); +int mem2node__node(struct mem2node *map, u64 addr); + +#endif /* __MEM2NODE_H */ diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 1ddc3d1d0147..a28f9b5cc4ff 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -326,8 +326,8 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, if (raw) s = (char *)pe->metric_name; else { - if (asprintf(&s, "%s\n\t[%s]", - pe->metric_name, pe->desc) < 0) + if (asprintf(&s, "%s\n%*s%s]", + pe->metric_name, 8, "[", pe->desc) < 0) return; } @@ -490,3 +490,25 @@ out: metricgroup__free_egroups(&group_list); return ret; } + +bool metricgroup__has_metric(const char *metric) +{ + struct pmu_events_map *map = perf_pmu__find_map(NULL); + struct pmu_event *pe; + int i; + + if (!map) + return false; + + for (i = 0; ; i++) { + pe = &map->table[i]; + + if (!pe->name && !pe->metric_group && !pe->metric_name) + break; + if (!pe->metric_expr) + continue; + if (match_metric(pe->metric_name, metric)) + return true; + } + return false; +} diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 06854e125ee7..8a155dba0581 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -28,4 +28,5 @@ int metricgroup__parse_groups(const struct option *opt, struct rblist *metric_events); void metricgroup__print(bool metrics, bool groups, char *filter, bool raw); +bool metricgroup__has_metric(const char *metric); #endif diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 91531a7c8fbf..215f69f41672 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -64,25 +64,6 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map, } /* - * legacy interface for mmap read. - * Don't use it. Use perf_mmap__read_event(). - */ -union perf_event *perf_mmap__read_forward(struct perf_mmap *map) -{ - u64 head; - - /* - * Check if event was unmapped due to a POLLHUP/POLLERR. - */ - if (!refcount_read(&map->refcnt)) - return NULL; - - head = perf_mmap__read_head(map); - - return perf_mmap__read(map, &map->prev, head); -} - -/* * Read event from ring buffer one by one. * Return one event for each call. * @@ -94,9 +75,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map) * } * perf_mmap__read_done() */ -union perf_event *perf_mmap__read_event(struct perf_mmap *map, - bool overwrite, - u64 *startp, u64 end) +union perf_event *perf_mmap__read_event(struct perf_mmap *map) { union perf_event *event; @@ -106,17 +85,14 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map, if (!refcount_read(&map->refcnt)) return NULL; - if (startp == NULL) - return NULL; - /* non-overwirte doesn't pause the ringbuffer */ - if (!overwrite) - end = perf_mmap__read_head(map); + if (!map->overwrite) + map->end = perf_mmap__read_head(map); - event = perf_mmap__read(map, startp, end); + event = perf_mmap__read(map, &map->start, map->end); - if (!overwrite) - map->prev = *startp; + if (!map->overwrite) + map->prev = map->start; return event; } @@ -139,9 +115,9 @@ void perf_mmap__put(struct perf_mmap *map) perf_mmap__munmap(map); } -void perf_mmap__consume(struct perf_mmap *map, bool overwrite) +void perf_mmap__consume(struct perf_mmap *map) { - if (!overwrite) { + if (!map->overwrite) { u64 old = map->prev; perf_mmap__write_tail(map, old); @@ -188,10 +164,10 @@ void perf_mmap__munmap(struct perf_mmap *map) auxtrace_mmap__munmap(&map->auxtrace_mmap); } -int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd) +int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu) { /* - * The last one will be done at perf_evlist__mmap_consume(), so that we + * The last one will be done at perf_mmap__consume(), so that we * make sure we don't prevent tools from consuming every last event in * the ring buffer. * @@ -215,6 +191,7 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd) return -1; } map->fd = fd; + map->cpu = cpu; if (auxtrace_mmap__mmap(&map->auxtrace_mmap, &mp->auxtrace_mp, map->base, fd)) @@ -223,19 +200,18 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd) return 0; } -static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end) +static int overwrite_rb_find_range(void *buf, int mask, u64 *start, u64 *end) { struct perf_event_header *pheader; - u64 evt_head = head; + u64 evt_head = *start; int size = mask + 1; - pr_debug2("overwrite_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head); - pheader = (struct perf_event_header *)(buf + (head & mask)); - *start = head; + pr_debug2("%s: buf=%p, start=%"PRIx64"\n", __func__, buf, *start); + pheader = (struct perf_event_header *)(buf + (*start & mask)); while (true) { - if (evt_head - head >= (unsigned int)size) { + if (evt_head - *start >= (unsigned int)size) { pr_debug("Finished reading overwrite ring buffer: rewind\n"); - if (evt_head - head > (unsigned int)size) + if (evt_head - *start > (unsigned int)size) evt_head -= pheader->size; *end = evt_head; return 0; @@ -259,27 +235,26 @@ static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u6 /* * Report the start and end of the available data in ringbuffer */ -int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, - u64 *startp, u64 *endp) +static int __perf_mmap__read_init(struct perf_mmap *md) { u64 head = perf_mmap__read_head(md); u64 old = md->prev; unsigned char *data = md->base + page_size; unsigned long size; - *startp = overwrite ? head : old; - *endp = overwrite ? old : head; + md->start = md->overwrite ? head : old; + md->end = md->overwrite ? old : head; - if (*startp == *endp) + if (md->start == md->end) return -EAGAIN; - size = *endp - *startp; + size = md->end - md->start; if (size > (unsigned long)(md->mask) + 1) { - if (!overwrite) { + if (!md->overwrite) { WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n"); md->prev = head; - perf_mmap__consume(md, overwrite); + perf_mmap__consume(md); return -EAGAIN; } @@ -287,33 +262,43 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, * Backward ring buffer is full. We still have a chance to read * most of data from it. */ - if (overwrite_rb_find_range(data, md->mask, head, startp, endp)) + if (overwrite_rb_find_range(data, md->mask, &md->start, &md->end)) return -EINVAL; } return 0; } -int perf_mmap__push(struct perf_mmap *md, bool overwrite, - void *to, int push(void *to, void *buf, size_t size)) +int perf_mmap__read_init(struct perf_mmap *map) +{ + /* + * Check if event was unmapped due to a POLLHUP/POLLERR. + */ + if (!refcount_read(&map->refcnt)) + return -ENOENT; + + return __perf_mmap__read_init(map); +} + +int perf_mmap__push(struct perf_mmap *md, void *to, + int push(void *to, void *buf, size_t size)) { u64 head = perf_mmap__read_head(md); - u64 end, start; unsigned char *data = md->base + page_size; unsigned long size; void *buf; int rc = 0; - rc = perf_mmap__read_init(md, overwrite, &start, &end); + rc = perf_mmap__read_init(md); if (rc < 0) return (rc == -EAGAIN) ? 0 : -1; - size = end - start; + size = md->end - md->start; - if ((start & md->mask) + size != (end & md->mask)) { - buf = &data[start & md->mask]; - size = md->mask + 1 - (start & md->mask); - start += size; + if ((md->start & md->mask) + size != (md->end & md->mask)) { + buf = &data[md->start & md->mask]; + size = md->mask + 1 - (md->start & md->mask); + md->start += size; if (push(to, buf, size) < 0) { rc = -1; @@ -321,9 +306,9 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, } } - buf = &data[start & md->mask]; - size = end - start; - start += size; + buf = &data[md->start & md->mask]; + size = md->end - md->start; + md->start += size; if (push(to, buf, size) < 0) { rc = -1; @@ -331,7 +316,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite, } md->prev = head; - perf_mmap__consume(md, overwrite); + perf_mmap__consume(md); out: return rc; } @@ -344,5 +329,11 @@ out: */ void perf_mmap__read_done(struct perf_mmap *map) { + /* + * Check if event was unmapped due to a POLLHUP/POLLERR. + */ + if (!refcount_read(&map->refcnt)) + return; + map->prev = perf_mmap__read_head(map); } diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index ec7d3a24e276..05a6d47c7956 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -18,8 +18,12 @@ struct perf_mmap { void *base; int mask; int fd; + int cpu; refcount_t refcnt; u64 prev; + u64 start; + u64 end; + bool overwrite; struct auxtrace_mmap auxtrace_mmap; char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8); }; @@ -57,13 +61,13 @@ struct mmap_params { struct auxtrace_mmap_params auxtrace_mp; }; -int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd); +int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu); void perf_mmap__munmap(struct perf_mmap *map); void perf_mmap__get(struct perf_mmap *map); void perf_mmap__put(struct perf_mmap *map); -void perf_mmap__consume(struct perf_mmap *map, bool overwrite); +void perf_mmap__consume(struct perf_mmap *map); static inline u64 perf_mmap__read_head(struct perf_mmap *mm) { @@ -86,16 +90,13 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) union perf_event *perf_mmap__read_forward(struct perf_mmap *map); -union perf_event *perf_mmap__read_event(struct perf_mmap *map, - bool overwrite, - u64 *startp, u64 end); +union perf_event *perf_mmap__read_event(struct perf_mmap *map); -int perf_mmap__push(struct perf_mmap *md, bool backward, - void *to, int push(void *to, void *buf, size_t size)); +int perf_mmap__push(struct perf_mmap *md, void *to, + int push(void *to, void *buf, size_t size)); size_t perf_mmap__mmap_len(struct perf_mmap *map); -int perf_mmap__read_init(struct perf_mmap *md, bool overwrite, - u64 *startp, u64 *endp); +int perf_mmap__read_init(struct perf_mmap *md); void perf_mmap__read_done(struct perf_mmap *map); #endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 5be021701f34..cf8bd123cf73 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -139,6 +139,9 @@ struct nsinfo *nsinfo__copy(struct nsinfo *nsi) { struct nsinfo *nnsi; + if (nsi == NULL) + return NULL; + nnsi = calloc(1, sizeof(*nnsi)); if (nnsi != NULL) { nnsi->pid = nsi->pid; diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 760558dcfd18..cae1a9a39722 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -10,6 +10,7 @@ #define __PERF_NAMESPACES_H #include <sys/types.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include <linux/refcount.h> #include <linux/types.h> diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 34589c427e52..f8cd3e7c9186 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -156,13 +156,12 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { (strcmp(sys_dirent->d_name, ".")) && \ (strcmp(sys_dirent->d_name, ".."))) -static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) +static int tp_event_has_id(const char *dir_path, struct dirent *evt_dir) { char evt_path[MAXPATHLEN]; int fd; - snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path, - sys_dir->d_name, evt_dir->d_name); + snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, evt_dir->d_name); fd = open(evt_path, O_RDONLY); if (fd < 0) return -EINVAL; @@ -171,12 +170,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) return 0; } -#define for_each_event(sys_dirent, evt_dir, evt_dirent) \ +#define for_each_event(dir_path, evt_dir, evt_dirent) \ while ((evt_dirent = readdir(evt_dir)) != NULL) \ if (evt_dirent->d_type == DT_DIR && \ (strcmp(evt_dirent->d_name, ".")) && \ (strcmp(evt_dirent->d_name, "..")) && \ - (!tp_event_has_id(sys_dirent, evt_dirent))) + (!tp_event_has_id(dir_path, evt_dirent))) #define MAX_EVENT_LENGTH 512 @@ -190,24 +189,24 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) int fd; u64 id; char evt_path[MAXPATHLEN]; - char dir_path[MAXPATHLEN]; + char *dir_path; - sys_dir = opendir(tracing_events_path); + sys_dir = tracing_events__opendir(); if (!sys_dir) return NULL; for_each_subsystem(sys_dir, sys_dirent) { - - snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent->d_name); + dir_path = get_events_file(sys_dirent->d_name); + if (!dir_path) + continue; evt_dir = opendir(dir_path); if (!evt_dir) - continue; + goto next; - for_each_event(sys_dirent, evt_dir, evt_dirent) { + for_each_event(dir_path, evt_dir, evt_dirent) { - snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, - evt_dirent->d_name); + scnprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, + evt_dirent->d_name); fd = open(evt_path, O_RDONLY); if (fd < 0) continue; @@ -218,6 +217,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) close(fd); id = atoll(id_buf); if (id == config) { + put_events_file(dir_path); closedir(evt_dir); closedir(sys_dir); path = zalloc(sizeof(*path)); @@ -242,6 +242,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) } } closedir(evt_dir); +next: + put_events_file(dir_path); } closedir(sys_dir); @@ -512,14 +514,19 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx, struct parse_events_error *err, struct list_head *head_config) { - char evt_path[MAXPATHLEN]; + char *evt_path; struct dirent *evt_ent; DIR *evt_dir; int ret = 0, found = 0; - snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name); + evt_path = get_events_file(sys_name); + if (!evt_path) { + tracepoint_error(err, errno, sys_name, evt_name); + return -1; + } evt_dir = opendir(evt_path); if (!evt_dir) { + put_events_file(evt_path); tracepoint_error(err, errno, sys_name, evt_name); return -1; } @@ -545,6 +552,7 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx, ret = -1; } + put_events_file(evt_path); closedir(evt_dir); return ret; } @@ -570,7 +578,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx, DIR *events_dir; int ret = 0; - events_dir = opendir(tracing_events_path); + events_dir = tracing_events__opendir(); if (!events_dir) { tracepoint_error(err, errno, sys_name, evt_name); return -1; @@ -1217,15 +1225,18 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, get_config_name(head_config), &config_terms); } -static int __parse_events_add_pmu(struct parse_events_state *parse_state, +int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, - struct list_head *head_config, bool auto_merge_stats) + struct list_head *head_config, + bool auto_merge_stats, + bool use_alias) { struct perf_event_attr attr; struct perf_pmu_info info; struct perf_pmu *pmu; struct perf_evsel *evsel; struct parse_events_error *err = parse_state->error; + bool use_uncore_alias; LIST_HEAD(config_terms); pmu = perf_pmu__find(name); @@ -1244,10 +1255,18 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state, memset(&attr, 0, sizeof(attr)); } + use_uncore_alias = (pmu->is_uncore && use_alias); + if (!head_config) { attr.type = pmu->type; evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats); - return evsel ? 0 : -ENOMEM; + if (evsel) { + evsel->pmu_name = name; + evsel->use_uncore_alias = use_uncore_alias; + return 0; + } else { + return -ENOMEM; + } } if (perf_pmu__check_alias(pmu, head_config, &info)) @@ -1276,18 +1295,13 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state, evsel->snapshot = info.snapshot; evsel->metric_expr = info.metric_expr; evsel->metric_name = info.metric_name; + evsel->pmu_name = name; + evsel->use_uncore_alias = use_uncore_alias; } return evsel ? 0 : -ENOMEM; } -int parse_events_add_pmu(struct parse_events_state *parse_state, - struct list_head *list, char *name, - struct list_head *head_config) -{ - return __parse_events_add_pmu(parse_state, list, name, head_config, false); -} - int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, struct list_head **listp) { @@ -1317,8 +1331,9 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, return -1; list_add_tail(&term->list, head); - if (!__parse_events_add_pmu(parse_state, list, - pmu->name, head, true)) { + if (!parse_events_add_pmu(parse_state, list, + pmu->name, head, + true, true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; @@ -1340,7 +1355,120 @@ int parse_events__modifier_group(struct list_head *list, return parse_events__modifier_event(list, event_mod, true); } -void parse_events__set_leader(char *name, struct list_head *list) +/* + * Check if the two uncore PMUs are from the same uncore block + * The format of the uncore PMU name is uncore_#blockname_#pmuidx + */ +static bool is_same_uncore_block(const char *pmu_name_a, const char *pmu_name_b) +{ + char *end_a, *end_b; + + end_a = strrchr(pmu_name_a, '_'); + end_b = strrchr(pmu_name_b, '_'); + + if (!end_a || !end_b) + return false; + + if ((end_a - pmu_name_a) != (end_b - pmu_name_b)) + return false; + + return (strncmp(pmu_name_a, pmu_name_b, end_a - pmu_name_a) == 0); +} + +static int +parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list, + struct parse_events_state *parse_state) +{ + struct perf_evsel *evsel, *leader; + uintptr_t *leaders; + bool is_leader = true; + int i, nr_pmu = 0, total_members, ret = 0; + + leader = list_first_entry(list, struct perf_evsel, node); + evsel = list_last_entry(list, struct perf_evsel, node); + total_members = evsel->idx - leader->idx + 1; + + leaders = calloc(total_members, sizeof(uintptr_t)); + if (WARN_ON(!leaders)) + return 0; + + /* + * Going through the whole group and doing sanity check. + * All members must use alias, and be from the same uncore block. + * Also, storing the leader events in an array. + */ + __evlist__for_each_entry(list, evsel) { + + /* Only split the uncore group which members use alias */ + if (!evsel->use_uncore_alias) + goto out; + + /* The events must be from the same uncore block */ + if (!is_same_uncore_block(leader->pmu_name, evsel->pmu_name)) + goto out; + + if (!is_leader) + continue; + /* + * If the event's PMU name starts to repeat, it must be a new + * event. That can be used to distinguish the leader from + * other members, even they have the same event name. + */ + if ((leader != evsel) && (leader->pmu_name == evsel->pmu_name)) { + is_leader = false; + continue; + } + /* The name is always alias name */ + WARN_ON(strcmp(leader->name, evsel->name)); + + /* Store the leader event for each PMU */ + leaders[nr_pmu++] = (uintptr_t) evsel; + } + + /* only one event alias */ + if (nr_pmu == total_members) { + parse_state->nr_groups--; + goto handled; + } + + /* + * An uncore event alias is a joint name which means the same event + * runs on all PMUs of a block. + * Perf doesn't support mixed events from different PMUs in the same + * group. The big group has to be split into multiple small groups + * which only include the events from the same PMU. + * + * Here the uncore event aliases must be from the same uncore block. + * The number of PMUs must be same for each alias. The number of new + * small groups equals to the number of PMUs. + * Setting the leader event for corresponding members in each group. + */ + i = 0; + __evlist__for_each_entry(list, evsel) { + if (i >= nr_pmu) + i = 0; + evsel->leader = (struct perf_evsel *) leaders[i++]; + } + + /* The number of members and group name are same for each group */ + for (i = 0; i < nr_pmu; i++) { + evsel = (struct perf_evsel *) leaders[i]; + evsel->nr_members = total_members / nr_pmu; + evsel->group_name = name ? strdup(name) : NULL; + } + + /* Take the new small groups into account */ + parse_state->nr_groups += nr_pmu - 1; + +handled: + ret = 1; +out: + free(leaders); + return ret; +} + +void parse_events__set_leader(char *name, struct list_head *list, + struct parse_events_state *parse_state) { struct perf_evsel *leader; @@ -1349,6 +1477,9 @@ void parse_events__set_leader(char *name, struct list_head *list) return; } + if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state)) + return; + __perf_evlist__set_leader(list); leader = list_entry(list->next, struct perf_evsel, node); leader->group_name = name ? strdup(name) : NULL; @@ -1716,7 +1847,7 @@ int parse_events(struct perf_evlist *evlist, const char *str, struct perf_evsel *last; if (list_empty(&parse_state.list)) { - WARN_ONCE(true, "WARNING: event parser found nothing"); + WARN_ONCE(true, "WARNING: event parser found nothing\n"); return -1; } @@ -1860,8 +1991,11 @@ static int set_filter(struct perf_evsel *evsel, const void *arg) int nr_addr_filters = 0; struct perf_pmu *pmu = NULL; - if (evsel == NULL) - goto err; + if (evsel == NULL) { + fprintf(stderr, + "--filter option should follow a -e tracepoint or HW tracer option\n"); + return -1; + } if (evsel->attr.type == PERF_TYPE_TRACEPOINT) { if (perf_evsel__append_tp_filter(evsel, str) < 0) { @@ -1883,8 +2017,11 @@ static int set_filter(struct perf_evsel *evsel, const void *arg) perf_pmu__scan_file(pmu, "nr_addr_filters", "%d", &nr_addr_filters); - if (!nr_addr_filters) - goto err; + if (!nr_addr_filters) { + fprintf(stderr, + "This CPU does not support address filtering\n"); + return -1; + } if (perf_evsel__append_addr_filter(evsel, str) < 0) { fprintf(stderr, @@ -1893,12 +2030,6 @@ static int set_filter(struct perf_evsel *evsel, const void *arg) } return 0; - -err: - fprintf(stderr, - "--filter option should follow a -e tracepoint or HW tracer option\n"); - - return -1; } int parse_filter(const struct option *opt, const char *str, @@ -1969,13 +2100,13 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, DIR *sys_dir, *evt_dir; struct dirent *sys_dirent, *evt_dirent; char evt_path[MAXPATHLEN]; - char dir_path[MAXPATHLEN]; + char *dir_path; char **evt_list = NULL; unsigned int evt_i = 0, evt_num = 0; bool evt_num_known = false; restart: - sys_dir = opendir(tracing_events_path); + sys_dir = tracing_events__opendir(); if (!sys_dir) return; @@ -1990,13 +2121,14 @@ restart: !strglobmatch(sys_dirent->d_name, subsys_glob)) continue; - snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent->d_name); + dir_path = get_events_file(sys_dirent->d_name); + if (!dir_path) + continue; evt_dir = opendir(dir_path); if (!evt_dir) - continue; + goto next; - for_each_event(sys_dirent, evt_dir, evt_dirent) { + for_each_event(dir_path, evt_dir, evt_dirent) { if (event_glob != NULL && !strglobmatch(evt_dirent->d_name, event_glob)) continue; @@ -2010,11 +2142,15 @@ restart: sys_dirent->d_name, evt_dirent->d_name); evt_list[evt_i] = strdup(evt_path); - if (evt_list[evt_i] == NULL) + if (evt_list[evt_i] == NULL) { + put_events_file(dir_path); goto out_close_evt_dir; + } evt_i++; } closedir(evt_dir); +next: + put_events_file(dir_path); } closedir(sys_dir); @@ -2062,21 +2198,21 @@ int is_valid_tracepoint(const char *event_string) DIR *sys_dir, *evt_dir; struct dirent *sys_dirent, *evt_dirent; char evt_path[MAXPATHLEN]; - char dir_path[MAXPATHLEN]; + char *dir_path; - sys_dir = opendir(tracing_events_path); + sys_dir = tracing_events__opendir(); if (!sys_dir) return 0; for_each_subsystem(sys_dir, sys_dirent) { - - snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent->d_name); + dir_path = get_events_file(sys_dirent->d_name); + if (!dir_path) + continue; evt_dir = opendir(dir_path); if (!evt_dir) - continue; + goto next; - for_each_event(sys_dirent, evt_dir, evt_dirent) { + for_each_event(dir_path, evt_dir, evt_dirent) { snprintf(evt_path, MAXPATHLEN, "%s:%s", sys_dirent->d_name, evt_dirent->d_name); if (!strcmp(evt_path, event_string)) { @@ -2086,6 +2222,8 @@ int is_valid_tracepoint(const char *event_string) } } closedir(evt_dir); +next: + put_events_file(dir_path); } closedir(sys_dir); return 0; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 88108cd11b4c..4473dac27aee 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -167,7 +167,9 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type, u64 len); int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, - struct list_head *head_config); + struct list_head *head_config, + bool auto_merge_stats, + bool use_alias); int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, @@ -178,7 +180,8 @@ int parse_events_copy_term_list(struct list_head *old, enum perf_pmu_event_symbol_type perf_pmu__parse_check(const char *name); -void parse_events__set_leader(char *name, struct list_head *list); +void parse_events__set_leader(char *name, struct list_head *list, + struct parse_events_state *parse_state); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); void parse_events_evlist_error(struct parse_events_state *parse_state, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 655ecff636a8..5f761f3ed0f3 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -53,7 +53,21 @@ static int str(yyscan_t scanner, int token) YYSTYPE *yylval = parse_events_get_lval(scanner); char *text = parse_events_get_text(scanner); - yylval->str = strdup(text); + if (text[0] != '\'') { + yylval->str = strdup(text); + } else { + /* + * If a text tag specified on the command line + * contains opening single quite ' then it is + * expected that the tag ends with single quote + * as well, like this: + * name=\'CPU_CLK_UNHALTED.THREAD:cmask=1\' + * quotes need to be escaped to bypass shell + * processing. + */ + yylval->str = strndup(&text[1], strlen(text) - 2); + } + return token; } @@ -175,7 +189,8 @@ 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_*?\.:]+)? /* If you add a modifier you need to update check_modifier() */ @@ -344,6 +359,7 @@ r{num_raw_hex} { return raw(yyscanner); } {bpf_object} { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); } {bpf_source} { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_SOURCE); } {name} { return pmu_str_check(yyscanner); } +{name_tag} { return str(yyscanner, PE_NAME); } "/" { BEGIN(config); return '/'; } - { return '-'; } , { BEGIN(event); return ','; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index e81a20ea8d7d..da8fe57691b8 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -8,6 +8,7 @@ #define YYDEBUG 1 +#include <fnmatch.h> #include <linux/compiler.h> #include <linux/list.h> #include <linux/types.h> @@ -72,6 +73,7 @@ static void inc_group_count(struct list_head *list, %type <num> value_sym %type <head> event_config %type <head> opt_event_config +%type <head> opt_pmu_config %type <term> event_term %type <head> event_pmu %type <head> event_legacy_symbol @@ -160,7 +162,7 @@ PE_NAME '{' events '}' struct list_head *list = $3; inc_group_count(list, _parse_state); - parse_events__set_leader($1, list); + parse_events__set_leader($1, list, _parse_state); $$ = list; } | @@ -169,7 +171,7 @@ PE_NAME '{' events '}' struct list_head *list = $2; inc_group_count(list, _parse_state); - parse_events__set_leader(NULL, list); + parse_events__set_leader(NULL, list, _parse_state); $$ = list; } @@ -223,17 +225,26 @@ event_def: event_pmu | event_bpf_file event_pmu: -PE_NAME opt_event_config +PE_NAME opt_pmu_config { + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list, *orig_terms, *terms; if (parse_events_copy_term_list($2, &orig_terms)) YYABORT; + if (error) + error->idx = @1.first_column; + ALLOC_LIST(list); - if (parse_events_add_pmu(_parse_state, list, $1, $2)) { + if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) { struct perf_pmu *pmu = NULL; int ok = 0; + char *pattern; + + if (asprintf(&pattern, "%s*", $1) < 0) + YYABORT; while ((pmu = perf_pmu__scan(pmu)) != NULL) { char *name = pmu->name; @@ -241,14 +252,19 @@ PE_NAME opt_event_config if (!strncmp(name, "uncore_", 7) && strncmp($1, "uncore_", 7)) name += 7; - if (!strncmp($1, name, strlen($1))) { - if (parse_events_copy_term_list(orig_terms, &terms)) + if (!fnmatch(pattern, name, 0)) { + if (parse_events_copy_term_list(orig_terms, &terms)) { + free(pattern); YYABORT; - if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms)) + } + if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true, false)) ok++; parse_events_terms__delete(terms); } } + + free(pattern); + if (!ok) YYABORT; } @@ -486,6 +502,17 @@ opt_event_config: $$ = NULL; } +opt_pmu_config: +'/' event_config '/' +{ + $$ = $2; +} +| +'/' '/' +{ + $$ = NULL; +} + start_terms: event_config { struct parse_events_state *parse_state = _parse_state; diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 57e38fdf0b34..afd68524ffa9 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -234,6 +234,74 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias, return 0; } +static void perf_pmu_assign_str(char *name, const char *field, char **old_str, + char **new_str) +{ + if (!*old_str) + goto set_new; + + if (*new_str) { /* Have new string, check with old */ + if (strcasecmp(*old_str, *new_str)) + pr_debug("alias %s differs in field '%s'\n", + name, field); + zfree(old_str); + } else /* Nothing new --> keep old string */ + return; +set_new: + *old_str = *new_str; + *new_str = NULL; +} + +static void perf_pmu_update_alias(struct perf_pmu_alias *old, + struct perf_pmu_alias *newalias) +{ + perf_pmu_assign_str(old->name, "desc", &old->desc, &newalias->desc); + perf_pmu_assign_str(old->name, "long_desc", &old->long_desc, + &newalias->long_desc); + perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic); + perf_pmu_assign_str(old->name, "metric_expr", &old->metric_expr, + &newalias->metric_expr); + perf_pmu_assign_str(old->name, "metric_name", &old->metric_name, + &newalias->metric_name); + perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str); + old->scale = newalias->scale; + old->per_pkg = newalias->per_pkg; + old->snapshot = newalias->snapshot; + memcpy(old->unit, newalias->unit, sizeof(old->unit)); +} + +/* Delete an alias entry. */ +static void perf_pmu_free_alias(struct perf_pmu_alias *newalias) +{ + zfree(&newalias->name); + zfree(&newalias->desc); + zfree(&newalias->long_desc); + zfree(&newalias->topic); + zfree(&newalias->str); + zfree(&newalias->metric_expr); + zfree(&newalias->metric_name); + parse_events_terms__purge(&newalias->terms); + free(newalias); +} + +/* Merge an alias, search in alias list. If this name is already + * present merge both of them to combine all information. + */ +static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias, + struct list_head *alist) +{ + struct perf_pmu_alias *a; + + list_for_each_entry(a, alist, list) { + if (!strcasecmp(newalias->name, a->name)) { + perf_pmu_update_alias(a, newalias); + perf_pmu_free_alias(newalias); + return true; + } + } + return false; +} + static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, char *desc, char *val, char *long_desc, char *topic, @@ -241,9 +309,11 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, char *metric_expr, char *metric_name) { + struct parse_events_term *term; struct perf_pmu_alias *alias; int ret; int num; + char newval[256]; alias = malloc(sizeof(*alias)); if (!alias) @@ -262,6 +332,27 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, return ret; } + /* Scan event and remove leading zeroes, spaces, newlines, some + * platforms have terms specified as + * event=0x0091 (read from files ../<PMU>/events/<FILE> + * and terms specified as event=0x91 (read from JSON files). + * + * Rebuild string to make alias->str member comparable. + */ + memset(newval, 0, sizeof(newval)); + ret = 0; + list_for_each_entry(term, &alias->terms, list) { + if (ret) + ret += scnprintf(newval + ret, sizeof(newval) - ret, + ","); + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) + ret += scnprintf(newval + ret, sizeof(newval) - ret, + "%s=%#x", term->config, term->val.num); + else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) + ret += scnprintf(newval + ret, sizeof(newval) - ret, + "%s=%s", term->config, term->val.str); + } + alias->name = strdup(name); if (dir) { /* @@ -285,9 +376,10 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, snprintf(alias->unit, sizeof(alias->unit), "%s", unit); } alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1; - alias->str = strdup(val); + alias->str = strdup(newval); - list_add_tail(&alias->list, list); + if (!perf_pmu_merge_alias(alias, list)) + list_add_tail(&alias->list, list); return 0; } @@ -303,6 +395,9 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI buf[ret] = 0; + /* Remove trailing newline from sysfs file */ + rtrim(buf); + return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL, NULL, NULL, NULL); } @@ -351,7 +446,7 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) if (pmu_alias_info_file(name)) continue; - snprintf(path, PATH_MAX, "%s/%s", dir, name); + scnprintf(path, PATH_MAX, "%s/%s", dir, name); file = fopen(path, "r"); if (!file) { @@ -539,9 +634,10 @@ static bool pmu_is_uncore(const char *name) /* * PMU CORE devices have different name other than cpu in sysfs on some - * platforms. looking for possible sysfs files to identify as core device. + * platforms. + * Looking for possible sysfs files to identify the arm core device. */ -static int is_pmu_core(const char *name) +static int is_arm_pmu_core(const char *name) { struct stat st; char path[PATH_MAX]; @@ -550,12 +646,6 @@ static int is_pmu_core(const char *name) if (!sysfs) return 0; - /* Look for cpu sysfs (x86 and others) */ - scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu", sysfs); - if ((stat(path, &st) == 0) && - (strncmp(name, "cpu", strlen("cpu")) == 0)) - return 1; - /* Look for cpu sysfs (specific to arm) */ scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus", sysfs, name); @@ -576,6 +666,34 @@ char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused) return NULL; } +/* Return zero when the cpuid from the mapfile.csv matches the + * cpuid string generated on this platform. + * Otherwise return non-zero. + */ +int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) +{ + regex_t re; + regmatch_t pmatch[1]; + int match; + + if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) { + /* Warn unable to generate match particular string. */ + pr_info("Invalid regular expression %s\n", mapcpuid); + return 1; + } + + match = !regexec(&re, cpuid, 1, pmatch, 0); + regfree(&re); + if (match) { + size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so); + + /* Verify the entire string matched. */ + if (match_len == strlen(cpuid)) + return 0; + } + return 1; +} + static char *perf_pmu__getcpuid(struct perf_pmu *pmu) { char *cpuid; @@ -610,31 +728,14 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu) i = 0; for (;;) { - regex_t re; - regmatch_t pmatch[1]; - int match; - map = &pmu_events_map[i++]; if (!map->table) { map = NULL; break; } - if (regcomp(&re, map->cpuid, REG_EXTENDED) != 0) { - /* Warn unable to generate match particular string. */ - pr_info("Invalid regular expression %s\n", map->cpuid); + if (!strcmp_cpuid_str(map->cpuid, cpuid)) break; - } - - match = !regexec(&re, cpuid, 1, pmatch, 0); - regfree(&re); - if (match) { - size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so); - - /* Verify the entire string matched. */ - if (match_len == strlen(cpuid)) - break; - } } free(cpuid); return map; @@ -651,6 +752,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) struct pmu_events_map *map; struct pmu_event *pe; const char *name = pmu->name; + const char *pname; map = perf_pmu__find_map(pmu); if (!map) @@ -669,11 +771,9 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) break; } - if (!is_pmu_core(name)) { - /* check for uncore devices */ - if (pe->pmu == NULL) - continue; - if (strncmp(pe->pmu, name, strlen(pe->pmu))) + if (!is_arm_pmu_core(name)) { + pname = pe->pmu ? pe->pmu : "cpu"; + if (strncmp(pname, name, strlen(pname))) continue; } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index e1dbc9821617..f119eb628dbb 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -111,17 +111,6 @@ void exit_probe_symbol_maps(void) symbol__exit(); } -static struct symbol *__find_kernel_function_by_name(const char *name, - struct map **mapp) -{ - return machine__find_kernel_function_by_name(host_machine, name, mapp); -} - -static struct symbol *__find_kernel_function(u64 addr, struct map **mapp) -{ - return machine__find_kernel_function(host_machine, addr, mapp); -} - static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void) { /* kmap->ref_reloc_sym should be set if host_machine is initialized */ @@ -149,7 +138,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr, if (reloc_sym && strcmp(name, reloc_sym->name) == 0) *addr = (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr; else { - sym = __find_kernel_function_by_name(name, &map); + sym = machine__find_kernel_symbol_by_name(host_machine, name, &map); if (!sym) return -ENOENT; *addr = map->unmap_ip(map, sym->start) - @@ -161,8 +150,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr, static struct map *kernel_get_module_map(const char *module) { - struct map_groups *grp = &host_machine->kmaps; - struct maps *maps = &grp->maps[MAP__FUNCTION]; + struct maps *maps = machine__kernel_maps(host_machine); struct map *pos; /* A file path -- this is an offline module */ @@ -177,8 +165,7 @@ static struct map *kernel_get_module_map(const char *module) if (strncmp(pos->dso->short_name + 1, module, pos->dso->short_name_len - 2) == 0 && module[pos->dso->short_name_len - 2] == '\0') { - map__get(pos); - return pos; + return map__get(pos); } } return NULL; @@ -341,7 +328,7 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso) char module_name[128]; snprintf(module_name, sizeof(module_name), "[%s]", module); - map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name); + map = map_groups__find_by_name(&host_machine->kmaps, module_name); if (map) { dso = map->dso; goto found; @@ -2098,7 +2085,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp, } if (addr) { addr += tp->offset; - sym = __find_kernel_function(addr, &map); + sym = machine__find_kernel_symbol(host_machine, addr, &map); } } @@ -3504,19 +3491,18 @@ int show_available_funcs(const char *target, struct nsinfo *nsi, (target) ? : "kernel"); goto end; } - if (!dso__sorted_by_name(map->dso, map->type)) - dso__sort_by_name(map->dso, map->type); + if (!dso__sorted_by_name(map->dso)) + dso__sort_by_name(map->dso); /* Show all (filtered) symbols */ setup_pager(); - for (nd = rb_first(&map->dso->symbol_names[map->type]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&map->dso->symbol_names); nd; nd = rb_next(nd)) { struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); if (strfilter__compare(_filter, pos->sym.name)) printf("%s\n", pos->sym.name); - } - + } end: map__put(map); exit_probe_symbol_maps(); diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 4ae1123c6794..b76088fadf3d 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -84,8 +84,7 @@ int open_trace_file(const char *trace_file, bool readwrite) char buf[PATH_MAX]; int ret; - ret = e_snprintf(buf, PATH_MAX, "%s/%s", - tracing_path, trace_file); + ret = e_snprintf(buf, PATH_MAX, "%s/%s", tracing_path_mount(), trace_file); if (ret >= 0) { pr_debug("Opening %s write=%d\n", buf, readwrite); if (readwrite && !probe_event_dry_run) diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index a5731de0e5eb..c37fbef1711d 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -423,20 +423,20 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, pr_warning("Failed to get the type of %s.\n", varname); return -ENOENT; } - pr_debug2("Var real type: (%x)\n", (unsigned)dwarf_dieoffset(&type)); + pr_debug2("Var real type: %s (%x)\n", dwarf_diename(&type), + (unsigned)dwarf_dieoffset(&type)); tag = dwarf_tag(&type); if (field->name[0] == '[' && (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type)) { - if (field->next) - /* Save original type for next field */ - memcpy(die_mem, &type, sizeof(*die_mem)); + /* Save original type for next field or type */ + memcpy(die_mem, &type, sizeof(*die_mem)); /* Get the type of this array */ if (die_get_real_type(&type, &type) == NULL) { pr_warning("Failed to get the type of %s.\n", varname); return -ENOENT; } - pr_debug2("Array real type: (%x)\n", + pr_debug2("Array real type: %s (%x)\n", dwarf_diename(&type), (unsigned)dwarf_dieoffset(&type)); if (tag == DW_TAG_pointer_type) { ref = zalloc(sizeof(struct probe_trace_arg_ref)); @@ -448,9 +448,6 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, *ref_ptr = ref; } ref->offset += dwarf_bytesize(&type) * field->index; - if (!field->next) - /* Save vr_die for converting types */ - memcpy(die_mem, vr_die, sizeof(*die_mem)); goto next; } else if (tag == DW_TAG_pointer_type) { /* Check the pointer and dereference */ diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index b1e999bd21ef..ce501ba14b08 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -11,6 +11,31 @@ #include "cpumap.h" #include "print_binary.h" #include "thread_map.h" +#include "mmap.h" + +#if PY_MAJOR_VERSION < 3 +#define _PyUnicode_FromString(arg) \ + PyString_FromString(arg) +#define _PyUnicode_AsString(arg) \ + PyString_AsString(arg) +#define _PyUnicode_FromFormat(...) \ + PyString_FromFormat(__VA_ARGS__) +#define _PyLong_FromLong(arg) \ + PyInt_FromLong(arg) + +#else + +#define _PyUnicode_FromString(arg) \ + PyUnicode_FromString(arg) +#define _PyUnicode_FromFormat(...) \ + PyUnicode_FromFormat(__VA_ARGS__) +#define _PyLong_FromLong(arg) \ + PyLong_FromLong(arg) +#endif + +#ifndef Py_TYPE +#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type) +#endif /* * Provide these two so that we don't have to link against callchain.c and @@ -49,7 +74,11 @@ int eprintf(int level, int var, const char *fmt, ...) # define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size, #endif +#if PY_MAJOR_VERSION < 3 PyMODINIT_FUNC initperf(void); +#else +PyMODINIT_FUNC PyInit_perf(void); +#endif #define member_def(type, member, ptype, help) \ { #member, ptype, \ @@ -107,7 +136,7 @@ static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent) pevent->event.mmap.pgoff, pevent->event.mmap.filename) < 0) { ret = PyErr_NoMemory(); } else { - ret = PyString_FromString(s); + ret = _PyUnicode_FromString(s); free(s); } return ret; @@ -138,7 +167,7 @@ static PyMemberDef pyrf_task_event__members[] = { static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent) { - return PyString_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, " + return _PyUnicode_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, " "ptid: %u, time: %" PRIu64 "}", pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit", pevent->event.fork.pid, @@ -171,7 +200,7 @@ static PyMemberDef pyrf_comm_event__members[] = { static PyObject *pyrf_comm_event__repr(struct pyrf_event *pevent) { - return PyString_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }", + return _PyUnicode_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }", pevent->event.comm.pid, pevent->event.comm.tid, pevent->event.comm.comm); @@ -202,7 +231,7 @@ static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent) { struct throttle_event *te = (struct throttle_event *)(&pevent->event.header + 1); - return PyString_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64 + return _PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64 ", stream_id: %" PRIu64 " }", pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un", te->time, te->id, te->stream_id); @@ -237,7 +266,7 @@ static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent) pevent->event.lost.id, pevent->event.lost.lost) < 0) { ret = PyErr_NoMemory(); } else { - ret = PyString_FromString(s); + ret = _PyUnicode_FromString(s); free(s); } return ret; @@ -264,7 +293,7 @@ static PyMemberDef pyrf_read_event__members[] = { static PyObject *pyrf_read_event__repr(struct pyrf_event *pevent) { - return PyString_FromFormat("{ type: read, pid: %u, tid: %u }", + return _PyUnicode_FromFormat("{ type: read, pid: %u, tid: %u }", pevent->event.read.pid, pevent->event.read.tid); /* @@ -299,7 +328,7 @@ static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent) if (asprintf(&s, "{ type: sample }") < 0) { ret = PyErr_NoMemory(); } else { - ret = PyString_FromString(s); + ret = _PyUnicode_FromString(s); free(s); } return ret; @@ -313,7 +342,7 @@ static bool is_tracepoint(struct pyrf_event *pevent) static PyObject* tracepoint_field(struct pyrf_event *pe, struct format_field *field) { - struct pevent *pevent = field->event->pevent; + struct tep_handle *pevent = field->event->pevent; void *data = pe->sample.raw_data; PyObject *ret = NULL; unsigned long long val; @@ -323,21 +352,21 @@ tracepoint_field(struct pyrf_event *pe, struct format_field *field) offset = field->offset; len = field->size; if (field->flags & FIELD_IS_DYNAMIC) { - val = pevent_read_number(pevent, data + offset, len); + val = tep_read_number(pevent, data + offset, len); offset = val; len = offset >> 16; offset &= 0xffff; } if (field->flags & FIELD_IS_STRING && is_printable_array(data + offset, len)) { - ret = PyString_FromString((char *)data + offset); + ret = _PyUnicode_FromString((char *)data + offset); } else { ret = PyByteArray_FromStringAndSize((const char *) data + offset, len); field->flags &= ~FIELD_IS_STRING; } } else { - val = pevent_read_number(pevent, data + field->offset, - field->size); + val = tep_read_number(pevent, data + field->offset, + field->size); if (field->flags & FIELD_IS_POINTER) ret = PyLong_FromUnsignedLong((unsigned long) val); else if (field->flags & FIELD_IS_SIGNED) @@ -352,7 +381,7 @@ tracepoint_field(struct pyrf_event *pe, struct format_field *field) static PyObject* get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name) { - const char *str = PyString_AsString(PyObject_Str(attr_name)); + const char *str = _PyUnicode_AsString(PyObject_Str(attr_name)); struct perf_evsel *evsel = pevent->evsel; struct format_field *field; @@ -366,7 +395,7 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name) evsel->tp_format = tp_format; } - field = pevent_find_any_field(evsel->tp_format, str); + field = tep_find_any_field(evsel->tp_format, str); if (!field) return NULL; @@ -416,7 +445,7 @@ static PyObject *pyrf_context_switch_event__repr(struct pyrf_event *pevent) !!(pevent->event.header.misc & PERF_RECORD_MISC_SWITCH_OUT)) < 0) { ret = PyErr_NoMemory(); } else { - ret = PyString_FromString(s); + ret = _PyUnicode_FromString(s); free(s); } return ret; @@ -528,7 +557,7 @@ static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus, static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus) { cpu_map__put(pcpus->cpus); - pcpus->ob_type->tp_free((PyObject*)pcpus); + Py_TYPE(pcpus)->tp_free((PyObject*)pcpus); } static Py_ssize_t pyrf_cpu_map__length(PyObject *obj) @@ -597,7 +626,7 @@ static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads, static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads) { thread_map__put(pthreads->threads); - pthreads->ob_type->tp_free((PyObject*)pthreads); + Py_TYPE(pthreads)->tp_free((PyObject*)pthreads); } static Py_ssize_t pyrf_thread_map__length(PyObject *obj) @@ -759,7 +788,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel, static void pyrf_evsel__delete(struct pyrf_evsel *pevsel) { perf_evsel__exit(&pevsel->evsel); - pevsel->ob_type->tp_free((PyObject*)pevsel); + Py_TYPE(pevsel)->tp_free((PyObject*)pevsel); } static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, @@ -850,7 +879,7 @@ static int pyrf_evlist__init(struct pyrf_evlist *pevlist, static void pyrf_evlist__delete(struct pyrf_evlist *pevlist) { perf_evlist__exit(&pevlist->evlist); - pevlist->ob_type->tp_free((PyObject*)pevlist); + Py_TYPE(pevlist)->tp_free((PyObject*)pevlist); } static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist, @@ -902,12 +931,16 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, for (i = 0; i < evlist->pollfd.nr; ++i) { PyObject *file; +#if PY_MAJOR_VERSION < 3 FILE *fp = fdopen(evlist->pollfd.entries[i].fd, "r"); if (fp == NULL) goto free_list; file = PyFile_FromFile(fp, "perf", "r", NULL); +#else + file = PyFile_FromFd(evlist->pollfd.entries[i].fd, "perf", "r", -1, NULL, NULL, NULL, 1); +#endif if (file == NULL) goto free_list; @@ -944,6 +977,20 @@ static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist, return Py_BuildValue("i", evlist->nr_entries); } +static struct perf_mmap *get_md(struct perf_evlist *evlist, int cpu) +{ + int i; + + for (i = 0; i < evlist->nr_mmaps; i++) { + struct perf_mmap *md = &evlist->mmap[i]; + + if (md->cpu == cpu) + return md; + } + + return NULL; +} + static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, PyObject *args, PyObject *kwargs) { @@ -951,13 +998,21 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, union perf_event *event; int sample_id_all = 1, cpu; static char *kwlist[] = { "cpu", "sample_id_all", NULL }; + struct perf_mmap *md; int err; if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist, &cpu, &sample_id_all)) return NULL; - event = perf_evlist__mmap_read(evlist, cpu); + md = get_md(evlist, cpu); + if (!md) + return NULL; + + if (perf_mmap__read_init(md) < 0) + goto end; + + event = perf_mmap__read_event(md); if (event != NULL) { PyObject *pyevent = pyrf_event__new(event); struct pyrf_event *pevent = (struct pyrf_event *)pyevent; @@ -967,22 +1022,24 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, return PyErr_NoMemory(); evsel = perf_evlist__event2evsel(evlist, event); - if (!evsel) + if (!evsel) { + Py_INCREF(Py_None); return Py_None; + } pevent->evsel = evsel; err = perf_evsel__parse_sample(evsel, event, &pevent->sample); /* Consume the even only after we parsed it out. */ - perf_evlist__mmap_consume(evlist, cpu); + perf_mmap__consume(md); if (err) return PyErr_Format(PyExc_OSError, "perf: can't parse sample, err=%d", err); return pyevent; } - +end: Py_INCREF(Py_None); return Py_None; } @@ -1194,9 +1251,9 @@ static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel, tp_format = trace_event__tp_format(sys, name); if (IS_ERR(tp_format)) - return PyInt_FromLong(-1); + return _PyLong_FromLong(-1); - return PyInt_FromLong(tp_format->id); + return _PyLong_FromLong(tp_format->id); } static PyMethodDef perf__methods[] = { @@ -1209,11 +1266,31 @@ static PyMethodDef perf__methods[] = { { .ml_name = NULL, } }; +#if PY_MAJOR_VERSION < 3 PyMODINIT_FUNC initperf(void) +#else +PyMODINIT_FUNC PyInit_perf(void) +#endif { PyObject *obj; int i; - PyObject *dict, *module = Py_InitModule("perf", perf__methods); + PyObject *dict; +#if PY_MAJOR_VERSION < 3 + PyObject *module = Py_InitModule("perf", perf__methods); +#else + static struct PyModuleDef moduledef = { + PyModuleDef_HEAD_INIT, + "perf", /* m_name */ + "", /* m_doc */ + -1, /* m_size */ + perf__methods, /* m_methods */ + NULL, /* m_reload */ + NULL, /* m_traverse */ + NULL, /* m_clear */ + NULL, /* m_free */ + }; + PyObject *module = PyModule_Create(&moduledef); +#endif if (module == NULL || pyrf_event__setup_types() < 0 || @@ -1221,7 +1298,11 @@ PyMODINIT_FUNC initperf(void) pyrf_evsel__setup_types() < 0 || pyrf_thread_map__setup_types() < 0 || pyrf_cpu_map__setup_types() < 0) +#if PY_MAJOR_VERSION < 3 return; +#else + return module; +#endif /* The page_size is placed in util object. */ page_size = sysconf(_SC_PAGE_SIZE); @@ -1270,7 +1351,7 @@ PyMODINIT_FUNC initperf(void) goto error; for (i = 0; perf__constants[i].name != NULL; i++) { - obj = PyInt_FromLong(perf__constants[i].value); + obj = _PyLong_FromLong(perf__constants[i].value); if (obj == NULL) goto error; PyDict_SetItemString(dict, perf__constants[i].name, obj); @@ -1280,6 +1361,9 @@ PyMODINIT_FUNC initperf(void) error: if (PyErr_Occurred()) PyErr_SetString(PyExc_ImportError, "perf: Init failed!"); +#if PY_MAJOR_VERSION >= 3 + return module; +#endif } /* diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c deleted file mode 100644 index 22eaa201aa27..000000000000 --- a/tools/perf/util/quote.c +++ /dev/null @@ -1,62 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <errno.h> -#include <stdlib.h> -#include "strbuf.h" -#include "quote.h" -#include "util.h" - -/* Help to copy the thing properly quoted for the shell safety. - * any single quote is replaced with '\'', any exclamation point - * is replaced with '\!', and the whole thing is enclosed in a - * - * E.g. - * original sq_quote result - * name ==> name ==> 'name' - * a b ==> a b ==> 'a b' - * a'b ==> a'\''b ==> 'a'\''b' - * a!b ==> a'\!'b ==> 'a'\!'b' - */ -static inline int need_bs_quote(char c) -{ - return (c == '\'' || c == '!'); -} - -static int sq_quote_buf(struct strbuf *dst, const char *src) -{ - char *to_free = NULL; - int ret; - - if (dst->buf == src) - to_free = strbuf_detach(dst, NULL); - - ret = strbuf_addch(dst, '\''); - while (!ret && *src) { - size_t len = strcspn(src, "'!"); - ret = strbuf_add(dst, src, len); - src += len; - while (!ret && need_bs_quote(*src)) - ret = strbuf_addf(dst, "'\\%c\'", *src++); - } - if (!ret) - ret = strbuf_addch(dst, '\''); - free(to_free); - - return ret; -} - -int sq_quote_argv(struct strbuf *dst, const char** argv, size_t maxlen) -{ - int i, ret; - - /* Copy into destination buffer. */ - ret = strbuf_grow(dst, 255); - for (i = 0; !ret && argv[i]; ++i) { - ret = strbuf_addch(dst, ' '); - if (ret) - break; - ret = sq_quote_buf(dst, argv[i]); - if (maxlen && dst->len > maxlen) - return -ENOSPC; - } - return ret; -} diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h deleted file mode 100644 index 274bf26d3511..000000000000 --- a/tools/perf/util/quote.h +++ /dev/null @@ -1,31 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PERF_QUOTE_H -#define __PERF_QUOTE_H - -#include <stddef.h> - -/* Help to copy the thing properly quoted for the shell safety. - * any single quote is replaced with '\'', any exclamation point - * is replaced with '\!', and the whole thing is enclosed in a - * single quote pair. - * - * For example, if you are passing the result to system() as an - * argument: - * - * sprintf(cmd, "foobar %s %s", sq_quote(arg0), sq_quote(arg1)) - * - * would be appropriate. If the system() is going to call ssh to - * run the command on the other side: - * - * sprintf(cmd, "git-diff-tree %s %s", sq_quote(arg0), sq_quote(arg1)); - * sprintf(rcmd, "ssh %s %s", sq_util/quote.host), sq_quote(cmd)); - * - * Note that the above examples leak memory! Remember to free result from - * sq_quote() in a real application. - */ - -struct strbuf; - -int sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen); - -#endif /* __PERF_QUOTE_H */ diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 6f09e4962dad..9cfc7bf16531 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -5,6 +5,7 @@ #include "parse-events.h" #include <errno.h> #include <api/fs/fs.h> +#include <subcmd/parse-options.h> #include "util.h" #include "cloexec.h" @@ -219,11 +220,21 @@ static int record_opts__config_freq(struct record_opts *opts) * User specified frequency is over current maximum. */ if (user_freq && (max_rate < opts->freq)) { - pr_err("Maximum frequency rate (%u) reached.\n" - "Please use -F freq option with lower value or consider\n" - "tweaking /proc/sys/kernel/perf_event_max_sample_rate.\n", - max_rate); - return -1; + if (opts->strict_freq) { + pr_err("error: Maximum frequency rate (%'u Hz) exceeded.\n" + " Please use -F freq option with a lower value or consider\n" + " tweaking /proc/sys/kernel/perf_event_max_sample_rate.\n", + max_rate); + return -1; + } else { + pr_warning("warning: Maximum frequency rate (%'u Hz) exceeded, throttling from %'u Hz to %'u Hz.\n" + " The limit can be raised via /proc/sys/kernel/perf_event_max_sample_rate.\n" + " The kernel will lower it when perf's interrupts take too long.\n" + " Use --strict-freq to disable this throttling, refusing to record.\n", + max_rate, opts->freq, max_rate); + + opts->freq = max_rate; + } } /* @@ -291,3 +302,25 @@ out_delete: perf_evlist__delete(temp_evlist); return ret; } + +int record__parse_freq(const struct option *opt, const char *str, int unset __maybe_unused) +{ + unsigned int freq; + struct record_opts *opts = opt->value; + + if (!str) + return -EINVAL; + + if (strcasecmp(str, "max") == 0) { + if (get_max_rate(&freq)) { + pr_err("couldn't read /proc/sys/kernel/perf_event_max_sample_rate\n"); + return -1; + } + pr_info("info: Using a maximum frequency rate of %'d Hz\n", freq); + } else { + freq = atoi(str); + } + + opts->user_freq = freq; + return 0; +} diff --git a/tools/perf/util/s390-cpumsf-kernel.h b/tools/perf/util/s390-cpumsf-kernel.h new file mode 100644 index 000000000000..de8c7ad0eca8 --- /dev/null +++ b/tools/perf/util/s390-cpumsf-kernel.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Auxtrace support for s390 CPU measurement sampling facility + * + * Copyright IBM Corp. 2018 + * Author(s): Hendrik Brueckner <brueckner@linux.ibm.com> + * Thomas Richter <tmricht@linux.ibm.com> + */ +#ifndef S390_CPUMSF_KERNEL_H +#define S390_CPUMSF_KERNEL_H + +#define S390_CPUMSF_PAGESZ 4096 /* Size of sample block units */ +#define S390_CPUMSF_DIAG_DEF_FIRST 0x8001 /* Diagnostic entry lowest id */ + +struct hws_basic_entry { + unsigned int def:16; /* 0-15 Data Entry Format */ + unsigned int R:4; /* 16-19 reserved */ + unsigned int U:4; /* 20-23 Number of unique instruct. */ + unsigned int z:2; /* zeros */ + unsigned int T:1; /* 26 PSW DAT mode */ + unsigned int W:1; /* 27 PSW wait state */ + unsigned int P:1; /* 28 PSW Problem state */ + unsigned int AS:2; /* 29-30 PSW address-space control */ + unsigned int I:1; /* 31 entry valid or invalid */ + unsigned int CL:2; /* 32-33 Configuration Level */ + unsigned int:14; + unsigned int prim_asn:16; /* primary ASN */ + unsigned long long ia; /* Instruction Address */ + unsigned long long gpp; /* Guest Program Parameter */ + unsigned long long hpp; /* Host Program Parameter */ +}; + +struct hws_diag_entry { + unsigned int def:16; /* 0-15 Data Entry Format */ + unsigned int R:15; /* 16-19 and 20-30 reserved */ + unsigned int I:1; /* 31 entry valid or invalid */ + u8 data[]; /* Machine-dependent sample data */ +}; + +struct hws_combined_entry { + struct hws_basic_entry basic; /* Basic-sampling data entry */ + struct hws_diag_entry diag; /* Diagnostic-sampling data entry */ +}; + +struct hws_trailer_entry { + union { + struct { + unsigned int f:1; /* 0 - Block Full Indicator */ + unsigned int a:1; /* 1 - Alert request control */ + unsigned int t:1; /* 2 - Timestamp format */ + unsigned int:29; /* 3 - 31: Reserved */ + unsigned int bsdes:16; /* 32-47: size of basic SDE */ + unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ + }; + unsigned long long flags; /* 0 - 64: All indicators */ + }; + unsigned long long overflow; /* 64 - sample Overflow count */ + unsigned char timestamp[16]; /* 16 - 31 timestamp */ + unsigned long long reserved1; /* 32 -Reserved */ + unsigned long long reserved2; /* */ + union { /* 48 - reserved for programming use */ + struct { + unsigned long long clock_base:1; /* in progusage2 */ + unsigned long long progusage1:63; + unsigned long long progusage2; + }; + unsigned long long progusage[2]; + }; +}; + +#endif diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c new file mode 100644 index 000000000000..d2c78ffd9fee --- /dev/null +++ b/tools/perf/util/s390-cpumsf.c @@ -0,0 +1,945 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright IBM Corp. 2018 + * Auxtrace support for s390 CPU-Measurement Sampling Facility + * + * Author(s): Thomas Richter <tmricht@linux.ibm.com> + * + * Auxiliary traces are collected during 'perf record' using rbd000 event. + * Several PERF_RECORD_XXX are generated during recording: + * + * PERF_RECORD_AUX: + * Records that new data landed in the AUX buffer part. + * PERF_RECORD_AUXTRACE: + * Defines auxtrace data. Followed by the actual data. The contents of + * the auxtrace data is dependent on the event and the CPU. + * This record is generated by perf record command. For details + * see Documentation/perf.data-file-format.txt. + * PERF_RECORD_AUXTRACE_INFO: + * Defines a table of contains for PERF_RECORD_AUXTRACE records. This + * record is generated during 'perf record' command. Each record contains up + * to 256 entries describing offset and size of the AUXTRACE data in the + * perf.data file. + * PERF_RECORD_AUXTRACE_ERROR: + * Indicates an error during AUXTRACE collection such as buffer overflow. + * PERF_RECORD_FINISHED_ROUND: + * Perf events are not necessarily in time stamp order, as they can be + * collected in parallel on different CPUs. If the events should be + * processed in time order they need to be sorted first. + * Perf report guarantees that there is no reordering over a + * PERF_RECORD_FINISHED_ROUND boundary event. All perf records with a + * time stamp lower than this record are processed (and displayed) before + * the succeeding perf record are processed. + * + * These records are evaluated during perf report command. + * + * 1. PERF_RECORD_AUXTRACE_INFO is used to set up the infrastructure for + * auxiliary trace data processing. See s390_cpumsf_process_auxtrace_info() + * below. + * Auxiliary trace data is collected per CPU. To merge the data into the report + * an auxtrace_queue is created for each CPU. It is assumed that the auxtrace + * data is in ascending order. + * + * Each queue has a double linked list of auxtrace_buffers. This list contains + * the offset and size of a CPU's auxtrace data. During auxtrace processing + * the data portion is mmap()'ed. + * + * To sort the queues in chronological order, all queue access is controlled + * by the auxtrace_heap. This is basicly a stack, each stack element has two + * entries, the queue number and a time stamp. However the stack is sorted by + * the time stamps. The highest time stamp is at the bottom the lowest + * (nearest) time stamp is at the top. That sort order is maintained at all + * times! + * + * After the auxtrace infrastructure has been setup, the auxtrace queues are + * filled with data (offset/size pairs) and the auxtrace_heap is populated. + * + * 2. PERF_RECORD_XXX processing triggers access to the auxtrace_queues. + * Each record is handled by s390_cpumsf_process_event(). The time stamp of + * the perf record is compared with the time stamp located on the auxtrace_heap + * top element. If that time stamp is lower than the time stamp from the + * record sample, the auxtrace queues will be processed. As auxtrace queues + * control many auxtrace_buffers and each buffer can be quite large, the + * auxtrace buffer might be processed only partially. In this case the + * position in the auxtrace_buffer of that queue is remembered and the time + * stamp of the last processed entry of the auxtrace_buffer replaces the + * current auxtrace_heap top. + * + * 3. Auxtrace_queues might run of out data and are feeded by the + * PERF_RECORD_AUXTRACE handling, see s390_cpumsf_process_auxtrace_event(). + * + * Event Generation + * Each sampling-data entry in the auxilary trace data generates a perf sample. + * This sample is filled + * with data from the auxtrace such as PID/TID, instruction address, CPU state, + * etc. This sample is processed with perf_session__deliver_synth_event() to + * be included into the GUI. + * + * 4. PERF_RECORD_FINISHED_ROUND event is used to process all the remaining + * auxiliary traces entries until the time stamp of this record is reached + * auxtrace_heap top. This is triggered by ordered_event->deliver(). + * + * + * Perf event processing. + * Event processing of PERF_RECORD_XXX entries relies on time stamp entries. + * This is the function call sequence: + * + * __cmd_report() + * | + * perf_session__process_events() + * | + * __perf_session__process_events() + * | + * perf_session__process_event() + * | This functions splits the PERF_RECORD_XXX records. + * | - Those generated by perf record command (type number equal or higher + * | than PERF_RECORD_USER_TYPE_START) are handled by + * | perf_session__process_user_event(see below) + * | - Those generated by the kernel are handled by + * | perf_evlist__parse_sample_timestamp() + * | + * perf_evlist__parse_sample_timestamp() + * | Extract time stamp from sample data. + * | + * perf_session__queue_event() + * | If timestamp is positive the sample is entered into an ordered_event + * | list, sort order is the timestamp. The event processing is deferred until + * | later (see perf_session__process_user_event()). + * | Other timestamps (0 or -1) are handled immediately by + * | perf_session__deliver_event(). These are events generated at start up + * | of command perf record. They create PERF_RECORD_COMM and PERF_RECORD_MMAP* + * | records. They are needed to create a list of running processes and its + * | memory mappings and layout. They are needed at the beginning to enable + * | command perf report to create process trees and memory mappings. + * | + * perf_session__deliver_event() + * | Delivers a PERF_RECORD_XXX entry for handling. + * | + * auxtrace__process_event() + * | The timestamp of the PERF_RECORD_XXX entry is taken to correlate with + * | time stamps from the auxiliary trace buffers. This enables + * | synchronization between auxiliary trace data and the events on the + * | perf.data file. + * | + * machine__deliver_event() + * | Handles the PERF_RECORD_XXX event. This depends on the record type. + * It might update the process tree, update a process memory map or enter + * a sample with IP and call back chain data into GUI data pool. + * + * + * Deferred processing determined by perf_session__process_user_event() is + * finally processed when a PERF_RECORD_FINISHED_ROUND is encountered. These + * are generated during command perf record. + * The timestamp of PERF_RECORD_FINISHED_ROUND event is taken to process all + * PERF_RECORD_XXX entries stored in the ordered_event list. This list was + * built up while reading the perf.data file. + * Each event is now processed by calling perf_session__deliver_event(). + * This enables time synchronization between the data in the perf.data file and + * the data in the auxiliary trace buffers. + */ + +#include <endian.h> +#include <errno.h> +#include <byteswap.h> +#include <inttypes.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/bitops.h> +#include <linux/log2.h> + +#include "cpumap.h" +#include "color.h" +#include "evsel.h" +#include "evlist.h" +#include "machine.h" +#include "session.h" +#include "util.h" +#include "thread.h" +#include "debug.h" +#include "auxtrace.h" +#include "s390-cpumsf.h" +#include "s390-cpumsf-kernel.h" + +struct s390_cpumsf { + struct auxtrace auxtrace; + struct auxtrace_queues queues; + struct auxtrace_heap heap; + struct perf_session *session; + struct machine *machine; + u32 auxtrace_type; + u32 pmu_type; + u16 machine_type; + bool data_queued; +}; + +struct s390_cpumsf_queue { + struct s390_cpumsf *sf; + unsigned int queue_nr; + struct auxtrace_buffer *buffer; + int cpu; +}; + +/* Display s390 CPU measurement facility basic-sampling data entry */ +static bool s390_cpumsf_basic_show(const char *color, size_t pos, + struct hws_basic_entry *basic) +{ + if (basic->def != 1) { + pr_err("Invalid AUX trace basic entry [%#08zx]\n", pos); + return false; + } + color_fprintf(stdout, color, " [%#08zx] Basic Def:%04x Inst:%#04x" + " %c%c%c%c AS:%d ASN:%#04x IA:%#018llx\n" + "\t\tCL:%d HPP:%#018llx GPP:%#018llx\n", + pos, basic->def, basic->U, + basic->T ? 'T' : ' ', + basic->W ? 'W' : ' ', + basic->P ? 'P' : ' ', + basic->I ? 'I' : ' ', + basic->AS, basic->prim_asn, basic->ia, basic->CL, + basic->hpp, basic->gpp); + return true; +} + +/* Display s390 CPU measurement facility diagnostic-sampling data entry */ +static bool s390_cpumsf_diag_show(const char *color, size_t pos, + struct hws_diag_entry *diag) +{ + if (diag->def < S390_CPUMSF_DIAG_DEF_FIRST) { + pr_err("Invalid AUX trace diagnostic entry [%#08zx]\n", pos); + return false; + } + color_fprintf(stdout, color, " [%#08zx] Diag Def:%04x %c\n", + pos, diag->def, diag->I ? 'I' : ' '); + return true; +} + +/* Return TOD timestamp contained in an trailer entry */ +static unsigned long long trailer_timestamp(struct hws_trailer_entry *te) +{ + /* te->t set: TOD in STCKE format, bytes 8-15 + * to->t not set: TOD in STCK format, bytes 0-7 + */ + unsigned long long ts; + + memcpy(&ts, &te->timestamp[te->t], sizeof(ts)); + return ts; +} + +/* Display s390 CPU measurement facility trailer entry */ +static bool s390_cpumsf_trailer_show(const char *color, size_t pos, + struct hws_trailer_entry *te) +{ + if (te->bsdes != sizeof(struct hws_basic_entry)) { + pr_err("Invalid AUX trace trailer entry [%#08zx]\n", pos); + return false; + } + color_fprintf(stdout, color, " [%#08zx] Trailer %c%c%c bsdes:%d" + " dsdes:%d Overflow:%lld Time:%#llx\n" + "\t\tC:%d TOD:%#lx 1:%#llx 2:%#llx\n", + pos, + te->f ? 'F' : ' ', + te->a ? 'A' : ' ', + te->t ? 'T' : ' ', + te->bsdes, te->dsdes, te->overflow, + trailer_timestamp(te), te->clock_base, te->progusage2, + te->progusage[0], te->progusage[1]); + return true; +} + +/* Test a sample data block. It must be 4KB or a multiple thereof in size and + * 4KB page aligned. Each sample data page has a trailer entry at the + * end which contains the sample entry data sizes. + * + * Return true if the sample data block passes the checks and set the + * basic set entry size and diagnostic set entry size. + * + * Return false on failure. + * + * Note: Old hardware does not set the basic or diagnostic entry sizes + * in the trailer entry. Use the type number instead. + */ +static bool s390_cpumsf_validate(int machine_type, + unsigned char *buf, size_t len, + unsigned short *bsdes, + unsigned short *dsdes) +{ + struct hws_basic_entry *basic = (struct hws_basic_entry *)buf; + struct hws_trailer_entry *te; + + *dsdes = *bsdes = 0; + if (len & (S390_CPUMSF_PAGESZ - 1)) /* Illegal size */ + return false; + if (basic->def != 1) /* No basic set entry, must be first */ + return false; + /* Check for trailer entry at end of SDB */ + te = (struct hws_trailer_entry *)(buf + S390_CPUMSF_PAGESZ + - sizeof(*te)); + *bsdes = te->bsdes; + *dsdes = te->dsdes; + if (!te->bsdes && !te->dsdes) { + /* Very old hardware, use CPUID */ + switch (machine_type) { + case 2097: + case 2098: + *dsdes = 64; + *bsdes = 32; + break; + case 2817: + case 2818: + *dsdes = 74; + *bsdes = 32; + break; + case 2827: + case 2828: + *dsdes = 85; + *bsdes = 32; + break; + default: + /* Illegal trailer entry */ + return false; + } + } + return true; +} + +/* Return true if there is room for another entry */ +static bool s390_cpumsf_reached_trailer(size_t entry_sz, size_t pos) +{ + size_t payload = S390_CPUMSF_PAGESZ - sizeof(struct hws_trailer_entry); + + if (payload - (pos & (S390_CPUMSF_PAGESZ - 1)) < entry_sz) + return false; + return true; +} + +/* Dump an auxiliary buffer. These buffers are multiple of + * 4KB SDB pages. + */ +static void s390_cpumsf_dump(struct s390_cpumsf *sf, + unsigned char *buf, size_t len) +{ + const char *color = PERF_COLOR_BLUE; + struct hws_basic_entry *basic; + struct hws_diag_entry *diag; + unsigned short bsdes, dsdes; + size_t pos = 0; + + color_fprintf(stdout, color, + ". ... s390 AUX data: size %zu bytes\n", + len); + + if (!s390_cpumsf_validate(sf->machine_type, buf, len, &bsdes, + &dsdes)) { + pr_err("Invalid AUX trace data block size:%zu" + " (type:%d bsdes:%hd dsdes:%hd)\n", + len, sf->machine_type, bsdes, dsdes); + return; + } + + /* s390 kernel always returns 4KB blocks fully occupied, + * no partially filled SDBs. + */ + while (pos < len) { + /* Handle Basic entry */ + basic = (struct hws_basic_entry *)(buf + pos); + if (s390_cpumsf_basic_show(color, pos, basic)) + pos += bsdes; + else + return; + + /* Handle Diagnostic entry */ + diag = (struct hws_diag_entry *)(buf + pos); + if (s390_cpumsf_diag_show(color, pos, diag)) + pos += dsdes; + else + return; + + /* Check for trailer entry */ + if (!s390_cpumsf_reached_trailer(bsdes + dsdes, pos)) { + /* Show trailer entry */ + struct hws_trailer_entry te; + + pos = (pos + S390_CPUMSF_PAGESZ) + & ~(S390_CPUMSF_PAGESZ - 1); + pos -= sizeof(te); + memcpy(&te, buf + pos, sizeof(te)); + /* Set descriptor sizes in case of old hardware + * where these values are not set. + */ + te.bsdes = bsdes; + te.dsdes = dsdes; + if (s390_cpumsf_trailer_show(color, pos, &te)) + pos += sizeof(te); + else + return; + } + } +} + +static void s390_cpumsf_dump_event(struct s390_cpumsf *sf, unsigned char *buf, + size_t len) +{ + printf(".\n"); + s390_cpumsf_dump(sf, buf, len); +} + +#define S390_LPP_PID_MASK 0xffffffff + +static bool s390_cpumsf_make_event(size_t pos, + struct hws_basic_entry *basic, + struct s390_cpumsf_queue *sfq) +{ + struct perf_sample sample = { + .ip = basic->ia, + .pid = basic->hpp & S390_LPP_PID_MASK, + .tid = basic->hpp & S390_LPP_PID_MASK, + .cpumode = PERF_RECORD_MISC_CPUMODE_UNKNOWN, + .cpu = sfq->cpu, + .period = 1 + }; + union perf_event event; + + memset(&event, 0, sizeof(event)); + if (basic->CL == 1) /* Native LPAR mode */ + sample.cpumode = basic->P ? PERF_RECORD_MISC_USER + : PERF_RECORD_MISC_KERNEL; + else if (basic->CL == 2) /* Guest kernel/user space */ + sample.cpumode = basic->P ? PERF_RECORD_MISC_GUEST_USER + : PERF_RECORD_MISC_GUEST_KERNEL; + else if (basic->gpp || basic->prim_asn != 0xffff) + /* Use heuristics on old hardware */ + sample.cpumode = basic->P ? PERF_RECORD_MISC_GUEST_USER + : PERF_RECORD_MISC_GUEST_KERNEL; + else + sample.cpumode = basic->P ? PERF_RECORD_MISC_USER + : PERF_RECORD_MISC_KERNEL; + + event.sample.header.type = PERF_RECORD_SAMPLE; + event.sample.header.misc = sample.cpumode; + event.sample.header.size = sizeof(struct perf_event_header); + + pr_debug4("%s pos:%#zx ip:%#" PRIx64 " P:%d CL:%d pid:%d.%d cpumode:%d cpu:%d\n", + __func__, pos, sample.ip, basic->P, basic->CL, sample.pid, + sample.tid, sample.cpumode, sample.cpu); + if (perf_session__deliver_synth_event(sfq->sf->session, &event, + &sample)) { + pr_err("s390 Auxiliary Trace: failed to deliver event\n"); + return false; + } + return true; +} + +static unsigned long long get_trailer_time(const unsigned char *buf) +{ + struct hws_trailer_entry *te; + unsigned long long aux_time; + + te = (struct hws_trailer_entry *)(buf + S390_CPUMSF_PAGESZ + - sizeof(*te)); + + if (!te->clock_base) /* TOD_CLOCK_BASE value missing */ + return 0; + + /* Correct calculation to convert time stamp in trailer entry to + * nano seconds (taken from arch/s390 function tod_to_ns()). + * TOD_CLOCK_BASE is stored in trailer entry member progusage2. + */ + aux_time = trailer_timestamp(te) - te->progusage2; + aux_time = (aux_time >> 9) * 125 + (((aux_time & 0x1ff) * 125) >> 9); + return aux_time; +} + +/* Process the data samples of a single queue. The first parameter is a + * pointer to the queue, the second parameter is the time stamp. This + * is the time stamp: + * - of the event that triggered this processing. + * - or the time stamp when the last proccesing of this queue stopped. + * In this case it stopped at a 4KB page boundary and record the + * position on where to continue processing on the next invocation + * (see buffer->use_data and buffer->use_size). + * + * When this function returns the second parameter is updated to + * reflect the time stamp of the last processed auxiliary data entry + * (taken from the trailer entry of that page). The caller uses this + * returned time stamp to record the last processed entry in this + * queue. + * + * The function returns: + * 0: Processing successful. The second parameter returns the + * time stamp from the trailer entry until which position + * processing took place. Subsequent calls resume from this + * position. + * <0: An error occurred during processing. The second parameter + * returns the maximum time stamp. + * >0: Done on this queue. The second parameter returns the + * maximum time stamp. + */ +static int s390_cpumsf_samples(struct s390_cpumsf_queue *sfq, u64 *ts) +{ + struct s390_cpumsf *sf = sfq->sf; + unsigned char *buf = sfq->buffer->use_data; + size_t len = sfq->buffer->use_size; + struct hws_basic_entry *basic; + unsigned short bsdes, dsdes; + size_t pos = 0; + int err = 1; + u64 aux_ts; + + if (!s390_cpumsf_validate(sf->machine_type, buf, len, &bsdes, + &dsdes)) { + *ts = ~0ULL; + return -1; + } + + /* Get trailer entry time stamp and check if entries in + * this auxiliary page are ready for processing. If the + * time stamp of the first entry is too high, whole buffer + * can be skipped. In this case return time stamp. + */ + aux_ts = get_trailer_time(buf); + if (!aux_ts) { + pr_err("[%#08" PRIx64 "] Invalid AUX trailer entry TOD clock base\n", + sfq->buffer->data_offset); + aux_ts = ~0ULL; + goto out; + } + if (aux_ts > *ts) { + *ts = aux_ts; + return 0; + } + + while (pos < len) { + /* Handle Basic entry */ + basic = (struct hws_basic_entry *)(buf + pos); + if (s390_cpumsf_make_event(pos, basic, sfq)) + pos += bsdes; + else { + err = -EBADF; + goto out; + } + + pos += dsdes; /* Skip diagnositic entry */ + + /* Check for trailer entry */ + if (!s390_cpumsf_reached_trailer(bsdes + dsdes, pos)) { + pos = (pos + S390_CPUMSF_PAGESZ) + & ~(S390_CPUMSF_PAGESZ - 1); + /* Check existence of next page */ + if (pos >= len) + break; + aux_ts = get_trailer_time(buf + pos); + if (!aux_ts) { + aux_ts = ~0ULL; + goto out; + } + if (aux_ts > *ts) { + *ts = aux_ts; + sfq->buffer->use_data += pos; + sfq->buffer->use_size -= pos; + return 0; + } + } + } +out: + *ts = aux_ts; + sfq->buffer->use_size = 0; + sfq->buffer->use_data = NULL; + return err; /* Buffer completely scanned or error */ +} + +/* Run the s390 auxiliary trace decoder. + * Select the queue buffer to operate on, the caller already selected + * the proper queue, depending on second parameter 'ts'. + * This is the time stamp until which the auxiliary entries should + * be processed. This value is updated by called functions and + * returned to the caller. + * + * Resume processing in the current buffer. If there is no buffer + * get a new buffer from the queue and setup start position for + * processing. + * When a buffer is completely processed remove it from the queue + * before returning. + * + * This function returns + * 1: When the queue is empty. Second parameter will be set to + * maximum time stamp. + * 0: Normal processing done. + * <0: Error during queue buffer setup. This causes the caller + * to stop processing completely. + */ +static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq, + u64 *ts) +{ + + struct auxtrace_buffer *buffer; + struct auxtrace_queue *queue; + int err; + + queue = &sfq->sf->queues.queue_array[sfq->queue_nr]; + + /* Get buffer and last position in buffer to resume + * decoding the auxiliary entries. One buffer might be large + * and decoding might stop in between. This depends on the time + * stamp of the trailer entry in each page of the auxiliary + * data and the time stamp of the event triggering the decoding. + */ + if (sfq->buffer == NULL) { + sfq->buffer = buffer = auxtrace_buffer__next(queue, + sfq->buffer); + if (!buffer) { + *ts = ~0ULL; + return 1; /* Processing done on this queue */ + } + /* Start with a new buffer on this queue */ + if (buffer->data) { + buffer->use_size = buffer->size; + buffer->use_data = buffer->data; + } + } else + buffer = sfq->buffer; + + if (!buffer->data) { + int fd = perf_data__fd(sfq->sf->session->data); + + buffer->data = auxtrace_buffer__get_data(buffer, fd); + if (!buffer->data) + return -ENOMEM; + buffer->use_size = buffer->size; + buffer->use_data = buffer->data; + } + pr_debug4("%s queue_nr:%d buffer:%" PRId64 " offset:%#" PRIx64 " size:%#zx rest:%#zx\n", + __func__, sfq->queue_nr, buffer->buffer_nr, buffer->offset, + buffer->size, buffer->use_size); + err = s390_cpumsf_samples(sfq, ts); + + /* If non-zero, there is either an error (err < 0) or the buffer is + * completely done (err > 0). The error is unrecoverable, usually + * some descriptors could not be read successfully, so continue with + * the next buffer. + * In both cases the parameter 'ts' has been updated. + */ + if (err) { + sfq->buffer = NULL; + list_del(&buffer->list); + auxtrace_buffer__free(buffer); + if (err > 0) /* Buffer done, no error */ + err = 0; + } + return err; +} + +static struct s390_cpumsf_queue * +s390_cpumsf_alloc_queue(struct s390_cpumsf *sf, unsigned int queue_nr) +{ + struct s390_cpumsf_queue *sfq; + + sfq = zalloc(sizeof(struct s390_cpumsf_queue)); + if (sfq == NULL) + return NULL; + + sfq->sf = sf; + sfq->queue_nr = queue_nr; + sfq->cpu = -1; + return sfq; +} + +static int s390_cpumsf_setup_queue(struct s390_cpumsf *sf, + struct auxtrace_queue *queue, + unsigned int queue_nr, u64 ts) +{ + struct s390_cpumsf_queue *sfq = queue->priv; + + if (list_empty(&queue->head)) + return 0; + + if (sfq == NULL) { + sfq = s390_cpumsf_alloc_queue(sf, queue_nr); + if (!sfq) + return -ENOMEM; + queue->priv = sfq; + + if (queue->cpu != -1) + sfq->cpu = queue->cpu; + } + return auxtrace_heap__add(&sf->heap, queue_nr, ts); +} + +static int s390_cpumsf_setup_queues(struct s390_cpumsf *sf, u64 ts) +{ + unsigned int i; + int ret = 0; + + for (i = 0; i < sf->queues.nr_queues; i++) { + ret = s390_cpumsf_setup_queue(sf, &sf->queues.queue_array[i], + i, ts); + if (ret) + break; + } + return ret; +} + +static int s390_cpumsf_update_queues(struct s390_cpumsf *sf, u64 ts) +{ + if (!sf->queues.new_data) + return 0; + + sf->queues.new_data = false; + return s390_cpumsf_setup_queues(sf, ts); +} + +static int s390_cpumsf_process_queues(struct s390_cpumsf *sf, u64 timestamp) +{ + unsigned int queue_nr; + u64 ts; + int ret; + + while (1) { + struct auxtrace_queue *queue; + struct s390_cpumsf_queue *sfq; + + if (!sf->heap.heap_cnt) + return 0; + + if (sf->heap.heap_array[0].ordinal >= timestamp) + return 0; + + queue_nr = sf->heap.heap_array[0].queue_nr; + queue = &sf->queues.queue_array[queue_nr]; + sfq = queue->priv; + + auxtrace_heap__pop(&sf->heap); + if (sf->heap.heap_cnt) { + ts = sf->heap.heap_array[0].ordinal + 1; + if (ts > timestamp) + ts = timestamp; + } else { + ts = timestamp; + } + + ret = s390_cpumsf_run_decoder(sfq, &ts); + if (ret < 0) { + auxtrace_heap__add(&sf->heap, queue_nr, ts); + return ret; + } + if (!ret) { + ret = auxtrace_heap__add(&sf->heap, queue_nr, ts); + if (ret < 0) + return ret; + } + } + return 0; +} + +static int s390_cpumsf_synth_error(struct s390_cpumsf *sf, int code, int cpu, + pid_t pid, pid_t tid, u64 ip) +{ + char msg[MAX_AUXTRACE_ERROR_MSG]; + union perf_event event; + int err; + + strncpy(msg, "Lost Auxiliary Trace Buffer", sizeof(msg) - 1); + auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE, + code, cpu, pid, tid, ip, msg); + + err = perf_session__deliver_synth_event(sf->session, &event, NULL); + if (err) + pr_err("s390 Auxiliary Trace: failed to deliver error event," + "error %d\n", err); + return err; +} + +static int s390_cpumsf_lost(struct s390_cpumsf *sf, struct perf_sample *sample) +{ + return s390_cpumsf_synth_error(sf, 1, sample->cpu, + sample->pid, sample->tid, 0); +} + +static int +s390_cpumsf_process_event(struct perf_session *session __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool) +{ + struct s390_cpumsf *sf = container_of(session->auxtrace, + struct s390_cpumsf, + auxtrace); + u64 timestamp = sample->time; + int err = 0; + + if (dump_trace) + return 0; + + if (!tool->ordered_events) { + pr_err("s390 Auxiliary Trace requires ordered events\n"); + return -EINVAL; + } + + if (event->header.type == PERF_RECORD_AUX && + event->aux.flags & PERF_AUX_FLAG_TRUNCATED) + return s390_cpumsf_lost(sf, sample); + + if (timestamp) { + err = s390_cpumsf_update_queues(sf, timestamp); + if (!err) + err = s390_cpumsf_process_queues(sf, timestamp); + } + return err; +} + +struct s390_cpumsf_synth { + struct perf_tool cpumsf_tool; + struct perf_session *session; +}; + +static int +s390_cpumsf_process_auxtrace_event(struct perf_session *session, + union perf_event *event __maybe_unused, + struct perf_tool *tool __maybe_unused) +{ + struct s390_cpumsf *sf = container_of(session->auxtrace, + struct s390_cpumsf, + auxtrace); + + int fd = perf_data__fd(session->data); + struct auxtrace_buffer *buffer; + off_t data_offset; + int err; + + if (sf->data_queued) + return 0; + + if (perf_data__is_pipe(session->data)) { + data_offset = 0; + } else { + data_offset = lseek(fd, 0, SEEK_CUR); + if (data_offset == -1) + return -errno; + } + + err = auxtrace_queues__add_event(&sf->queues, session, event, + data_offset, &buffer); + if (err) + return err; + + /* Dump here after copying piped trace out of the pipe */ + if (dump_trace) { + if (auxtrace_buffer__get_data(buffer, fd)) { + s390_cpumsf_dump_event(sf, buffer->data, + buffer->size); + auxtrace_buffer__put_data(buffer); + } + } + return 0; +} + +static void s390_cpumsf_free_events(struct perf_session *session __maybe_unused) +{ +} + +static int s390_cpumsf_flush(struct perf_session *session __maybe_unused, + struct perf_tool *tool __maybe_unused) +{ + return 0; +} + +static void s390_cpumsf_free_queues(struct perf_session *session) +{ + struct s390_cpumsf *sf = container_of(session->auxtrace, + struct s390_cpumsf, + auxtrace); + struct auxtrace_queues *queues = &sf->queues; + unsigned int i; + + for (i = 0; i < queues->nr_queues; i++) + zfree(&queues->queue_array[i].priv); + auxtrace_queues__free(queues); +} + +static void s390_cpumsf_free(struct perf_session *session) +{ + struct s390_cpumsf *sf = container_of(session->auxtrace, + struct s390_cpumsf, + auxtrace); + + auxtrace_heap__free(&sf->heap); + s390_cpumsf_free_queues(session); + session->auxtrace = NULL; + free(sf); +} + +static int s390_cpumsf_get_type(const char *cpuid) +{ + int ret, family = 0; + + ret = sscanf(cpuid, "%*[^,],%u", &family); + return (ret == 1) ? family : 0; +} + +/* Check itrace options set on perf report command. + * Return true, if none are set or all options specified can be + * handled on s390. + * Return false otherwise. + */ +static bool check_auxtrace_itrace(struct itrace_synth_opts *itops) +{ + if (!itops || !itops->set) + return true; + pr_err("No --itrace options supported\n"); + return false; +} + +int s390_cpumsf_process_auxtrace_info(union perf_event *event, + struct perf_session *session) +{ + struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info; + struct s390_cpumsf *sf; + int err; + + if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event)) + return -EINVAL; + + sf = zalloc(sizeof(struct s390_cpumsf)); + if (sf == NULL) + return -ENOMEM; + + if (!check_auxtrace_itrace(session->itrace_synth_opts)) { + err = -EINVAL; + goto err_free; + } + + err = auxtrace_queues__init(&sf->queues); + if (err) + goto err_free; + + sf->session = session; + sf->machine = &session->machines.host; /* No kvm support */ + sf->auxtrace_type = auxtrace_info->type; + sf->pmu_type = PERF_TYPE_RAW; + sf->machine_type = s390_cpumsf_get_type(session->evlist->env->cpuid); + + sf->auxtrace.process_event = s390_cpumsf_process_event; + sf->auxtrace.process_auxtrace_event = s390_cpumsf_process_auxtrace_event; + sf->auxtrace.flush_events = s390_cpumsf_flush; + sf->auxtrace.free_events = s390_cpumsf_free_events; + sf->auxtrace.free = s390_cpumsf_free; + session->auxtrace = &sf->auxtrace; + + if (dump_trace) + return 0; + + err = auxtrace_queues__process_index(&sf->queues, session); + if (err) + goto err_free_queues; + + if (sf->queues.populated) + sf->data_queued = true; + + return 0; + +err_free_queues: + auxtrace_queues__free(&sf->queues); + session->auxtrace = NULL; +err_free: + free(sf); + return err; +} diff --git a/tools/perf/util/s390-cpumsf.h b/tools/perf/util/s390-cpumsf.h new file mode 100644 index 000000000000..fb64d100555c --- /dev/null +++ b/tools/perf/util/s390-cpumsf.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright IBM Corp. 2018 + * Auxtrace support for s390 CPU-Measurement Sampling Facility + * + * Author(s): Thomas Richter <tmricht@linux.ibm.com> + */ + +#ifndef INCLUDE__PERF_S390_CPUMSF_H +#define INCLUDE__PERF_S390_CPUMSF_H + +union perf_event; +struct perf_session; +struct perf_pmu; + +struct auxtrace_record * +s390_cpumsf_recording_init(int *err, struct perf_pmu *s390_cpumsf_pmu); + +int s390_cpumsf_process_auxtrace_info(union perf_event *event, + struct perf_session *session); +#endif diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 7b79c413486b..45484f0f7292 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -535,7 +535,7 @@ static int perl_stop_script(void) return 0; } -static int perl_generate_script(struct pevent *pevent, const char *outfile) +static int perl_generate_script(struct tep_handle *pevent, const char *outfile) { struct event_format *event = NULL; struct format_field *f; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index ea070883c593..dfc6093f118c 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -48,8 +48,39 @@ #include "cpumap.h" #include "print_binary.h" #include "stat.h" +#include "mem-events.h" + +#if PY_MAJOR_VERSION < 3 +#define _PyUnicode_FromString(arg) \ + PyString_FromString(arg) +#define _PyUnicode_FromStringAndSize(arg1, arg2) \ + PyString_FromStringAndSize((arg1), (arg2)) +#define _PyBytes_FromStringAndSize(arg1, arg2) \ + PyString_FromStringAndSize((arg1), (arg2)) +#define _PyLong_FromLong(arg) \ + PyInt_FromLong(arg) +#define _PyLong_AsLong(arg) \ + PyInt_AsLong(arg) +#define _PyCapsule_New(arg1, arg2, arg3) \ + PyCObject_FromVoidPtr((arg1), (arg2)) PyMODINIT_FUNC initperf_trace_context(void); +#else +#define _PyUnicode_FromString(arg) \ + PyUnicode_FromString(arg) +#define _PyUnicode_FromStringAndSize(arg1, arg2) \ + PyUnicode_FromStringAndSize((arg1), (arg2)) +#define _PyBytes_FromStringAndSize(arg1, arg2) \ + PyBytes_FromStringAndSize((arg1), (arg2)) +#define _PyLong_FromLong(arg) \ + PyLong_FromLong(arg) +#define _PyLong_AsLong(arg) \ + PyLong_AsLong(arg) +#define _PyCapsule_New(arg1, arg2, arg3) \ + PyCapsule_New((arg1), (arg2), (arg3)) + +PyMODINIT_FUNC PyInit_perf_trace_context(void); +#endif #define TRACE_EVENT_TYPE_MAX \ ((1 << (sizeof(unsigned short) * 8)) - 1) @@ -135,7 +166,7 @@ static int get_argument_count(PyObject *handler) PyObject *arg_count_obj = PyObject_GetAttrString(code_obj, "co_argcount"); if (arg_count_obj) { - arg_count = (int) PyInt_AsLong(arg_count_obj); + arg_count = (int) _PyLong_AsLong(arg_count_obj); Py_DECREF(arg_count_obj); } Py_DECREF(code_obj); @@ -182,10 +213,10 @@ static void define_value(enum print_arg_type field_type, value = eval_flag(field_value); - PyTuple_SetItem(t, n++, PyString_FromString(ev_name)); - PyTuple_SetItem(t, n++, PyString_FromString(field_name)); - PyTuple_SetItem(t, n++, PyInt_FromLong(value)); - PyTuple_SetItem(t, n++, PyString_FromString(field_str)); + PyTuple_SetItem(t, n++, _PyUnicode_FromString(ev_name)); + PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_name)); + PyTuple_SetItem(t, n++, _PyLong_FromLong(value)); + PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_str)); try_call_object(handler_name, t); @@ -223,10 +254,10 @@ static void define_field(enum print_arg_type field_type, if (!t) Py_FatalError("couldn't create Python tuple"); - PyTuple_SetItem(t, n++, PyString_FromString(ev_name)); - PyTuple_SetItem(t, n++, PyString_FromString(field_name)); + PyTuple_SetItem(t, n++, _PyUnicode_FromString(ev_name)); + PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_name)); if (field_type == PRINT_FLAGS) - PyTuple_SetItem(t, n++, PyString_FromString(delim)); + PyTuple_SetItem(t, n++, _PyUnicode_FromString(delim)); try_call_object(handler_name, t); @@ -325,12 +356,12 @@ static PyObject *get_field_numeric_entry(struct event_format *event, if (field->flags & FIELD_IS_SIGNED) { if ((long long)val >= LONG_MIN && (long long)val <= LONG_MAX) - obj = PyInt_FromLong(val); + obj = _PyLong_FromLong(val); else obj = PyLong_FromLongLong(val); } else { if (val <= LONG_MAX) - obj = PyInt_FromLong(val); + obj = _PyLong_FromLong(val); else obj = PyLong_FromUnsignedLongLong(val); } @@ -342,6 +373,19 @@ static PyObject *get_field_numeric_entry(struct event_format *event, return obj; } +static const char *get_dsoname(struct map *map) +{ + const char *dsoname = "[unknown]"; + + if (map && map->dso) { + if (symbol_conf.show_kernel_path && map->dso->long_name) + dsoname = map->dso->long_name; + else + dsoname = map->dso->name; + } + + return dsoname; +} static PyObject *python_process_callchain(struct perf_sample *sample, struct perf_evsel *evsel, @@ -389,24 +433,18 @@ static PyObject *python_process_callchain(struct perf_sample *sample, pydict_set_item_string_decref(pysym, "end", PyLong_FromUnsignedLongLong(node->sym->end)); pydict_set_item_string_decref(pysym, "binding", - PyInt_FromLong(node->sym->binding)); + _PyLong_FromLong(node->sym->binding)); pydict_set_item_string_decref(pysym, "name", - PyString_FromStringAndSize(node->sym->name, + _PyUnicode_FromStringAndSize(node->sym->name, node->sym->namelen)); pydict_set_item_string_decref(pyelem, "sym", pysym); } if (node->map) { - struct map *map = node->map; - const char *dsoname = "[unknown]"; - if (map && map->dso) { - if (symbol_conf.show_kernel_path && map->dso->long_name) - dsoname = map->dso->long_name; - else - dsoname = map->dso->name; - } + const char *dsoname = get_dsoname(node->map); + pydict_set_item_string_decref(pyelem, "dso", - PyString_FromString(dsoname)); + _PyUnicode_FromString(dsoname)); } callchain_cursor_advance(&callchain_cursor); @@ -418,6 +456,166 @@ exit: return pylist; } +static PyObject *python_process_brstack(struct perf_sample *sample, + struct thread *thread) +{ + struct branch_stack *br = sample->branch_stack; + PyObject *pylist; + u64 i; + + pylist = PyList_New(0); + if (!pylist) + Py_FatalError("couldn't create Python list"); + + if (!(br && br->nr)) + goto exit; + + for (i = 0; i < br->nr; i++) { + PyObject *pyelem; + struct addr_location al; + const char *dsoname; + + pyelem = PyDict_New(); + if (!pyelem) + Py_FatalError("couldn't create Python dictionary"); + + pydict_set_item_string_decref(pyelem, "from", + PyLong_FromUnsignedLongLong(br->entries[i].from)); + pydict_set_item_string_decref(pyelem, "to", + PyLong_FromUnsignedLongLong(br->entries[i].to)); + pydict_set_item_string_decref(pyelem, "mispred", + PyBool_FromLong(br->entries[i].flags.mispred)); + pydict_set_item_string_decref(pyelem, "predicted", + PyBool_FromLong(br->entries[i].flags.predicted)); + pydict_set_item_string_decref(pyelem, "in_tx", + PyBool_FromLong(br->entries[i].flags.in_tx)); + pydict_set_item_string_decref(pyelem, "abort", + PyBool_FromLong(br->entries[i].flags.abort)); + pydict_set_item_string_decref(pyelem, "cycles", + PyLong_FromUnsignedLongLong(br->entries[i].flags.cycles)); + + thread__find_map(thread, sample->cpumode, + br->entries[i].from, &al); + dsoname = get_dsoname(al.map); + pydict_set_item_string_decref(pyelem, "from_dsoname", + _PyUnicode_FromString(dsoname)); + + thread__find_map(thread, sample->cpumode, + br->entries[i].to, &al); + dsoname = get_dsoname(al.map); + pydict_set_item_string_decref(pyelem, "to_dsoname", + _PyUnicode_FromString(dsoname)); + + PyList_Append(pylist, pyelem); + Py_DECREF(pyelem); + } + +exit: + return pylist; +} + +static unsigned long get_offset(struct symbol *sym, struct addr_location *al) +{ + unsigned long offset; + + if (al->addr < sym->end) + offset = al->addr - sym->start; + else + offset = al->addr - al->map->start - sym->start; + + return offset; +} + +static int get_symoff(struct symbol *sym, struct addr_location *al, + bool print_off, char *bf, int size) +{ + unsigned long offset; + + if (!sym || !sym->name[0]) + return scnprintf(bf, size, "%s", "[unknown]"); + + if (!print_off) + return scnprintf(bf, size, "%s", sym->name); + + offset = get_offset(sym, al); + + return scnprintf(bf, size, "%s+0x%x", sym->name, offset); +} + +static int get_br_mspred(struct branch_flags *flags, char *bf, int size) +{ + if (!flags->mispred && !flags->predicted) + return scnprintf(bf, size, "%s", "-"); + + if (flags->mispred) + return scnprintf(bf, size, "%s", "M"); + + return scnprintf(bf, size, "%s", "P"); +} + +static PyObject *python_process_brstacksym(struct perf_sample *sample, + struct thread *thread) +{ + struct branch_stack *br = sample->branch_stack; + PyObject *pylist; + u64 i; + char bf[512]; + struct addr_location al; + + pylist = PyList_New(0); + if (!pylist) + Py_FatalError("couldn't create Python list"); + + if (!(br && br->nr)) + goto exit; + + for (i = 0; i < br->nr; i++) { + PyObject *pyelem; + + pyelem = PyDict_New(); + if (!pyelem) + Py_FatalError("couldn't create Python dictionary"); + + thread__find_symbol(thread, sample->cpumode, + br->entries[i].from, &al); + get_symoff(al.sym, &al, true, bf, sizeof(bf)); + pydict_set_item_string_decref(pyelem, "from", + _PyUnicode_FromString(bf)); + + thread__find_symbol(thread, sample->cpumode, + br->entries[i].to, &al); + get_symoff(al.sym, &al, true, bf, sizeof(bf)); + pydict_set_item_string_decref(pyelem, "to", + _PyUnicode_FromString(bf)); + + get_br_mspred(&br->entries[i].flags, bf, sizeof(bf)); + pydict_set_item_string_decref(pyelem, "pred", + _PyUnicode_FromString(bf)); + + if (br->entries[i].flags.in_tx) { + pydict_set_item_string_decref(pyelem, "in_tx", + _PyUnicode_FromString("X")); + } else { + pydict_set_item_string_decref(pyelem, "in_tx", + _PyUnicode_FromString("-")); + } + + if (br->entries[i].flags.abort) { + pydict_set_item_string_decref(pyelem, "abort", + _PyUnicode_FromString("A")); + } else { + pydict_set_item_string_decref(pyelem, "abort", + _PyUnicode_FromString("-")); + } + + PyList_Append(pylist, pyelem); + Py_DECREF(pyelem); + } + +exit: + return pylist; +} + static PyObject *get_sample_value_as_tuple(struct sample_read_value *value) { PyObject *t; @@ -468,12 +666,63 @@ static void set_sample_read_in_dict(PyObject *dict_sample, pydict_set_item_string_decref(dict_sample, "values", values); } +static void set_sample_datasrc_in_dict(PyObject *dict, + struct perf_sample *sample) +{ + struct mem_info mi = { .data_src.val = sample->data_src }; + char decode[100]; + + pydict_set_item_string_decref(dict, "datasrc", + PyLong_FromUnsignedLongLong(sample->data_src)); + + perf_script__meminfo_scnprintf(decode, 100, &mi); + + pydict_set_item_string_decref(dict, "datasrc_decode", + _PyUnicode_FromString(decode)); +} + +static int regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) +{ + unsigned int i = 0, r; + int printed = 0; + + bf[0] = 0; + + for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) { + u64 val = regs->regs[i++]; + + printed += scnprintf(bf + printed, size - printed, + "%5s:0x%" PRIx64 " ", + perf_reg_name(r), val); + } + + return printed; +} + +static void set_regs_in_dict(PyObject *dict, + struct perf_sample *sample, + struct perf_evsel *evsel) +{ + struct perf_event_attr *attr = &evsel->attr; + char bf[512]; + + regs_map(&sample->intr_regs, attr->sample_regs_intr, 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)); + + pydict_set_item_string_decref(dict, "uregs", + _PyUnicode_FromString(bf)); +} + static PyObject *get_perf_sample_dict(struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al, PyObject *callchain) { - PyObject *dict, *dict_sample; + PyObject *dict, *dict_sample, *brstack, *brstacksym; dict = PyDict_New(); if (!dict) @@ -483,16 +732,16 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, if (!dict_sample) Py_FatalError("couldn't create Python dictionary"); - pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); - pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(perf_evsel__name(evsel))); + pydict_set_item_string_decref(dict, "attr", _PyUnicode_FromStringAndSize( (const char *)&evsel->attr, sizeof(evsel->attr))); pydict_set_item_string_decref(dict_sample, "pid", - PyInt_FromLong(sample->pid)); + _PyLong_FromLong(sample->pid)); pydict_set_item_string_decref(dict_sample, "tid", - PyInt_FromLong(sample->tid)); + _PyLong_FromLong(sample->tid)); pydict_set_item_string_decref(dict_sample, "cpu", - PyInt_FromLong(sample->cpu)); + _PyLong_FromLong(sample->cpu)); pydict_set_item_string_decref(dict_sample, "ip", PyLong_FromUnsignedLongLong(sample->ip)); pydict_set_item_string_decref(dict_sample, "time", @@ -501,24 +750,39 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, PyLong_FromUnsignedLongLong(sample->period)); pydict_set_item_string_decref(dict_sample, "phys_addr", PyLong_FromUnsignedLongLong(sample->phys_addr)); + pydict_set_item_string_decref(dict_sample, "addr", + PyLong_FromUnsignedLongLong(sample->addr)); set_sample_read_in_dict(dict_sample, sample, evsel); + pydict_set_item_string_decref(dict_sample, "weight", + PyLong_FromUnsignedLongLong(sample->weight)); + pydict_set_item_string_decref(dict_sample, "transaction", + PyLong_FromUnsignedLongLong(sample->transaction)); + set_sample_datasrc_in_dict(dict_sample, sample); pydict_set_item_string_decref(dict, "sample", dict_sample); - pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "raw_buf", _PyBytes_FromStringAndSize( (const char *)sample->raw_data, sample->raw_size)); pydict_set_item_string_decref(dict, "comm", - PyString_FromString(thread__comm_str(al->thread))); + _PyUnicode_FromString(thread__comm_str(al->thread))); if (al->map) { pydict_set_item_string_decref(dict, "dso", - PyString_FromString(al->map->dso->name)); + _PyUnicode_FromString(al->map->dso->name)); } if (al->sym) { pydict_set_item_string_decref(dict, "symbol", - PyString_FromString(al->sym->name)); + _PyUnicode_FromString(al->sym->name)); } pydict_set_item_string_decref(dict, "callchain", callchain); + brstack = python_process_brstack(sample, al->thread); + pydict_set_item_string_decref(dict, "brstack", brstack); + + brstacksym = python_process_brstacksym(sample, al->thread); + pydict_set_item_string_decref(dict, "brstacksym", brstacksym); + + set_regs_in_dict(dict, sample, evsel); + return dict; } @@ -574,9 +838,9 @@ static void python_process_tracepoint(struct perf_sample *sample, scripting_context->event_data = data; scripting_context->pevent = evsel->tp_format->pevent; - context = PyCObject_FromVoidPtr(scripting_context, NULL); + context = _PyCapsule_New(scripting_context, NULL, NULL); - PyTuple_SetItem(t, n++, PyString_FromString(handler_name)); + PyTuple_SetItem(t, n++, _PyUnicode_FromString(handler_name)); PyTuple_SetItem(t, n++, context); /* ip unwinding */ @@ -585,18 +849,18 @@ static void python_process_tracepoint(struct perf_sample *sample, Py_INCREF(callchain); if (!dict) { - PyTuple_SetItem(t, n++, PyInt_FromLong(cpu)); - PyTuple_SetItem(t, n++, PyInt_FromLong(s)); - PyTuple_SetItem(t, n++, PyInt_FromLong(ns)); - PyTuple_SetItem(t, n++, PyInt_FromLong(pid)); - PyTuple_SetItem(t, n++, PyString_FromString(comm)); + PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu)); + PyTuple_SetItem(t, n++, _PyLong_FromLong(s)); + PyTuple_SetItem(t, n++, _PyLong_FromLong(ns)); + PyTuple_SetItem(t, n++, _PyLong_FromLong(pid)); + PyTuple_SetItem(t, n++, _PyUnicode_FromString(comm)); PyTuple_SetItem(t, n++, callchain); } else { - pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu)); - pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s)); - pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns)); - pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid)); - pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm)); + pydict_set_item_string_decref(dict, "common_cpu", _PyLong_FromLong(cpu)); + pydict_set_item_string_decref(dict, "common_s", _PyLong_FromLong(s)); + pydict_set_item_string_decref(dict, "common_ns", _PyLong_FromLong(ns)); + pydict_set_item_string_decref(dict, "common_pid", _PyLong_FromLong(pid)); + pydict_set_item_string_decref(dict, "common_comm", _PyUnicode_FromString(comm)); pydict_set_item_string_decref(dict, "common_callchain", callchain); } for (field = event->format.fields; field; field = field->next) { @@ -607,15 +871,15 @@ static void python_process_tracepoint(struct perf_sample *sample, offset = field->offset; len = field->size; if (field->flags & FIELD_IS_DYNAMIC) { - val = pevent_read_number(scripting_context->pevent, - data + offset, len); + val = tep_read_number(scripting_context->pevent, + data + offset, len); offset = val; len = offset >> 16; offset &= 0xffff; } if (field->flags & FIELD_IS_STRING && is_printable_array(data + offset, len)) { - obj = PyString_FromString((char *) data + offset); + obj = _PyUnicode_FromString((char *) data + offset); } else { obj = PyByteArray_FromStringAndSize((const char *) data + offset, len); field->flags &= ~FIELD_IS_STRING; @@ -644,14 +908,11 @@ static void python_process_tracepoint(struct perf_sample *sample, if (_PyTuple_Resize(&t, n) == -1) Py_FatalError("error resizing Python tuple"); - if (!dict) { + if (!dict) call_object(handler, t, handler_name); - } else { + else call_object(handler, t, default_handler_name); - Py_DECREF(dict); - } - Py_XDECREF(all_entries_dict); Py_DECREF(t); } @@ -668,7 +929,7 @@ static PyObject *tuple_new(unsigned int sz) static int tuple_set_u64(PyObject *t, unsigned int pos, u64 val) { #if BITS_PER_LONG == 64 - return PyTuple_SetItem(t, pos, PyInt_FromLong(val)); + return PyTuple_SetItem(t, pos, _PyLong_FromLong(val)); #endif #if BITS_PER_LONG == 32 return PyTuple_SetItem(t, pos, PyLong_FromLongLong(val)); @@ -677,12 +938,12 @@ static int tuple_set_u64(PyObject *t, unsigned int pos, u64 val) static int tuple_set_s32(PyObject *t, unsigned int pos, s32 val) { - return PyTuple_SetItem(t, pos, PyInt_FromLong(val)); + return PyTuple_SetItem(t, pos, _PyLong_FromLong(val)); } static int tuple_set_string(PyObject *t, unsigned int pos, const char *s) { - return PyTuple_SetItem(t, pos, PyString_FromString(s)); + return PyTuple_SetItem(t, pos, _PyUnicode_FromString(s)); } static int python_export_evsel(struct db_export *dbe, struct perf_evsel *evsel) @@ -971,7 +1232,6 @@ static void python_process_general_event(struct perf_sample *sample, call_object(handler, t, handler_name); - Py_DECREF(dict); Py_DECREF(t); } @@ -1029,8 +1289,8 @@ process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp, return; } - PyTuple_SetItem(t, n++, PyInt_FromLong(cpu)); - PyTuple_SetItem(t, n++, PyInt_FromLong(thread)); + PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu)); + PyTuple_SetItem(t, n++, _PyLong_FromLong(thread)); tuple_set_u64(t, n++, tstamp); tuple_set_u64(t, n++, count->val); @@ -1212,27 +1472,58 @@ static void set_table_handlers(struct tables *tables) SET_TABLE_HANDLER(call_return); } +#if PY_MAJOR_VERSION < 3 +static void _free_command_line(const char **command_line, int num) +{ + free(command_line); +} +#else +static void _free_command_line(wchar_t **command_line, int num) +{ + int i; + for (i = 0; i < num; i++) + PyMem_RawFree(command_line[i]); + free(command_line); +} +#endif + + /* * Start trace script */ static int python_start_script(const char *script, int argc, const char **argv) { struct tables *tables = &tables_global; +#if PY_MAJOR_VERSION < 3 const char **command_line; +#else + wchar_t **command_line; +#endif char buf[PATH_MAX]; int i, err = 0; FILE *fp; +#if PY_MAJOR_VERSION < 3 command_line = malloc((argc + 1) * sizeof(const char *)); command_line[0] = script; for (i = 1; i < argc + 1; i++) command_line[i] = argv[i - 1]; +#else + command_line = malloc((argc + 1) * sizeof(wchar_t *)); + command_line[0] = Py_DecodeLocale(script, NULL); + for (i = 1; i < argc + 1; i++) + command_line[i] = Py_DecodeLocale(argv[i - 1], NULL); +#endif Py_Initialize(); +#if PY_MAJOR_VERSION < 3 initperf_trace_context(); - PySys_SetArgv(argc + 1, (char **)command_line); +#else + PyInit_perf_trace_context(); + PySys_SetArgv(argc + 1, command_line); +#endif fp = fopen(script, "r"); if (!fp) { @@ -1262,12 +1553,12 @@ static int python_start_script(const char *script, int argc, const char **argv) goto error; } - free(command_line); + _free_command_line(command_line, argc + 1); return err; error: Py_Finalize(); - free(command_line); + _free_command_line(command_line, argc + 1); return err; } @@ -1297,7 +1588,7 @@ static int python_stop_script(void) return 0; } -static int python_generate_script(struct pevent *pevent, const char *outfile) +static int python_generate_script(struct tep_handle *pevent, const char *outfile) { struct event_format *event = NULL; struct format_field *f; @@ -1332,6 +1623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "# See the perf-script-python Documentation for the list " "of available functions.\n\n"); + fprintf(ofp, "from __future__ import print_function\n\n"); fprintf(ofp, "import os\n"); fprintf(ofp, "import sys\n\n"); @@ -1341,10 +1633,10 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "from Core import *\n\n\n"); fprintf(ofp, "def trace_begin():\n"); - fprintf(ofp, "\tprint \"in trace_begin\"\n\n"); + fprintf(ofp, "\tprint(\"in trace_begin\")\n\n"); fprintf(ofp, "def trace_end():\n"); - fprintf(ofp, "\tprint \"in trace_end\"\n\n"); + fprintf(ofp, "\tprint(\"in trace_end\")\n\n"); while ((event = trace_find_next_event(pevent, event))) { fprintf(ofp, "def %s__%s(", event->system, event->name); @@ -1380,7 +1672,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) "common_secs, common_nsecs,\n\t\t\t" "common_pid, common_comm)\n\n"); - fprintf(ofp, "\t\tprint \""); + fprintf(ofp, "\t\tprint(\""); not_first = 0; count = 0; @@ -1441,31 +1733,31 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%s", f->name); } - fprintf(ofp, ")\n\n"); + fprintf(ofp, "))\n\n"); - fprintf(ofp, "\t\tprint 'Sample: {'+" - "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n"); + fprintf(ofp, "\t\tprint('Sample: {'+" + "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n"); fprintf(ofp, "\t\tfor node in common_callchain:"); fprintf(ofp, "\n\t\t\tif 'sym' in node:"); - fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])"); + fprintf(ofp, "\n\t\t\t\tprint(\"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name']))"); fprintf(ofp, "\n\t\t\telse:"); - fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n"); - fprintf(ofp, "\t\tprint \"\\n\"\n\n"); + fprintf(ofp, "\n\t\t\t\tprint(\"\t[%%x]\" %% (node['ip']))\n\n"); + fprintf(ofp, "\t\tprint()\n\n"); } fprintf(ofp, "def trace_unhandled(event_name, context, " "event_fields_dict, perf_sample_dict):\n"); - fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n"); - fprintf(ofp, "\t\tprint 'Sample: {'+" - "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n"); + fprintf(ofp, "\t\tprint(get_dict_as_string(event_fields_dict))\n"); + fprintf(ofp, "\t\tprint('Sample: {'+" + "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n"); fprintf(ofp, "def print_header(" "event_name, cpu, secs, nsecs, pid, comm):\n" - "\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t" - "(event_name, cpu, secs, nsecs, pid, comm),\n\n"); + "\tprint(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t" + "(event_name, cpu, secs, nsecs, pid, comm), end=\"\")\n\n"); fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n" "\treturn delimiter.join" diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c71ced7db152..8b9369303561 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1094,7 +1094,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, sample_type = evsel->attr.sample_type; - if (sample_type & PERF_SAMPLE_CALLCHAIN) + if (evsel__has_callchain(evsel)) callchain__printf(evsel, sample); if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !perf_evsel__has_branch_callstack(evsel)) @@ -1591,7 +1591,7 @@ static void perf_session__warn_about_errors(const struct perf_session *session) drop_rate = (double)stats->total_lost_samples / (double) (stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples); if (drop_rate > 0.05) { - ui__warning("Processed %" PRIu64 " samples and lost %3.2f%% samples!\n\n", + ui__warning("Processed %" PRIu64 " samples and lost %3.2f%%!\n\n", stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples, drop_rate * 100.0); } @@ -1973,12 +1973,11 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg) return false; } -int maps__set_kallsyms_ref_reloc_sym(struct map **maps, - const char *symbol_name, u64 addr) +int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, u64 addr) { char *bracket; - int i; struct ref_reloc_sym *ref; + struct kmap *kmap; ref = zalloc(sizeof(struct ref_reloc_sym)); if (ref == NULL) @@ -1996,13 +1995,9 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps, ref->addr = addr; - for (i = 0; i < MAP__NR_TYPES; ++i) { - struct kmap *kmap = map__kmap(maps[i]); - - if (!kmap) - continue; + kmap = map__kmap(map); + if (kmap) kmap->ref_reloc_sym = ref; - } return 0; } diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index af415febbc46..97efbcad076e 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,12 +1,20 @@ -#!/usr/bin/python2 +#!/usr/bin/python from os import getenv +from subprocess import Popen, PIPE +from re import sub + +def clang_has_option(option): + return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if "unknown argument" in o] == [ ] cc = getenv("CC") if cc == "clang": from _sysconfigdata import build_time_vars - from re import sub build_time_vars["CFLAGS"] = sub("-specs=[^ ]+", "", build_time_vars["CFLAGS"]) + if not clang_has_option("-mcet"): + build_time_vars["CFLAGS"] = sub("-mcet", "", build_time_vars["CFLAGS"]) + if not clang_has_option("-fcf-protection"): + build_time_vars["CFLAGS"] = sub("-fcf-protection", "", build_time_vars["CFLAGS"]) from distutils.core import setup, Extension @@ -28,6 +36,8 @@ class install_lib(_install_lib): cflags = getenv('CFLAGS', '').split() # switch off several checks (need to be at the end of cflags list) cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ] +if cc != "clang": + cflags += ['-Wno-cast-function-type' ] src_perf = getenv('srctree') + '/tools/perf' build_lib = getenv('PYTHON_EXTBUILD_LIB') @@ -35,11 +45,11 @@ build_tmp = getenv('PYTHON_EXTBUILD_TMP') libtraceevent = getenv('LIBTRACEEVENT') libapikfs = getenv('LIBAPI') -ext_sources = [f.strip() for f in file('util/python-ext-sources') +ext_sources = [f.strip() for f in open('util/python-ext-sources') if len(f.strip()) > 0 and f[0] != '#'] # use full paths with source files -ext_sources = map(lambda x: '%s/%s' % (src_perf, x) , ext_sources) +ext_sources = list(map(lambda x: '%s/%s' % (src_perf, x) , ext_sources)) perf = Extension('perf', sources = ext_sources, diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 2da4d0456a03..b284276ec963 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2,7 +2,7 @@ #include <errno.h> #include <inttypes.h> #include <regex.h> -#include <sys/mman.h> +#include <linux/mman.h> #include "sort.h" #include "hist.h" #include "comm.h" @@ -111,17 +111,20 @@ struct sort_entry sort_thread = { /* --sort comm */ +/* + * We can't use pointer comparison in functions below, + * because it gives different results based on pointer + * values, which could break some sorting assumptions. + */ static int64_t sort__comm_cmp(struct hist_entry *left, struct hist_entry *right) { - /* Compare the addr that should be unique among comm */ return strcmp(comm__str(right->comm), comm__str(left->comm)); } static int64_t sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) { - /* Compare the addr that should be unique among comm */ return strcmp(comm__str(right->comm), comm__str(left->comm)); } @@ -279,7 +282,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level); if (sym && map) { - if (map->type == MAP__VARIABLE) { + if (sym->type == STT_OBJECT) { ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name); ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx", ip - map->unmap_ip(map, sym->start)); @@ -328,24 +331,18 @@ struct sort_entry sort_sym = { /* --sort srcline */ -char *hist_entry__get_srcline(struct hist_entry *he) +char *hist_entry__srcline(struct hist_entry *he) { - struct map *map = he->ms.map; - - if (!map) - return SRCLINE_UNKNOWN; - - return get_srcline(map->dso, map__rip_2objdump(map, he->ip), - he->ms.sym, true, true, he->ip); + return map__srcline(he->ms.map, he->ip, he->ms.sym); } static int64_t sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) { if (!left->srcline) - left->srcline = hist_entry__get_srcline(left); + left->srcline = hist_entry__srcline(left); if (!right->srcline) - right->srcline = hist_entry__get_srcline(right); + right->srcline = hist_entry__srcline(right); return strcmp(right->srcline, left->srcline); } @@ -354,7 +351,7 @@ static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { if (!he->srcline) - he->srcline = hist_entry__get_srcline(he); + he->srcline = hist_entry__srcline(he); return repsep_snprintf(bf, size, "%-.*s", width, he->srcline); } @@ -368,33 +365,20 @@ struct sort_entry sort_srcline = { /* --sort srcline_from */ +static char *addr_map_symbol__srcline(struct addr_map_symbol *ams) +{ + return map__srcline(ams->map, ams->al_addr, ams->sym); +} + static int64_t sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right) { - if (!left->branch_info->srcline_from) { - struct map *map = left->branch_info->from.map; - if (!map) - left->branch_info->srcline_from = SRCLINE_UNKNOWN; - else - left->branch_info->srcline_from = get_srcline(map->dso, - map__rip_2objdump(map, - left->branch_info->from.al_addr), - left->branch_info->from.sym, - true, true, - left->branch_info->from.al_addr); - } - if (!right->branch_info->srcline_from) { - struct map *map = right->branch_info->from.map; - if (!map) - right->branch_info->srcline_from = SRCLINE_UNKNOWN; - else - right->branch_info->srcline_from = get_srcline(map->dso, - map__rip_2objdump(map, - right->branch_info->from.al_addr), - right->branch_info->from.sym, - true, true, - right->branch_info->from.al_addr); - } + if (!left->branch_info->srcline_from) + left->branch_info->srcline_from = addr_map_symbol__srcline(&left->branch_info->from); + + if (!right->branch_info->srcline_from) + right->branch_info->srcline_from = addr_map_symbol__srcline(&right->branch_info->from); + return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from); } @@ -416,30 +400,12 @@ struct sort_entry sort_srcline_from = { static int64_t sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right) { - if (!left->branch_info->srcline_to) { - struct map *map = left->branch_info->to.map; - if (!map) - left->branch_info->srcline_to = SRCLINE_UNKNOWN; - else - left->branch_info->srcline_to = get_srcline(map->dso, - map__rip_2objdump(map, - left->branch_info->to.al_addr), - left->branch_info->from.sym, - true, true, - left->branch_info->to.al_addr); - } - if (!right->branch_info->srcline_to) { - struct map *map = right->branch_info->to.map; - if (!map) - right->branch_info->srcline_to = SRCLINE_UNKNOWN; - else - right->branch_info->srcline_to = get_srcline(map->dso, - map__rip_2objdump(map, - right->branch_info->to.al_addr), - right->branch_info->to.sym, - true, true, - right->branch_info->to.al_addr); - } + if (!left->branch_info->srcline_to) + left->branch_info->srcline_to = addr_map_symbol__srcline(&left->branch_info->to); + + if (!right->branch_info->srcline_to) + right->branch_info->srcline_to = addr_map_symbol__srcline(&right->branch_info->to); + return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to); } @@ -635,7 +601,7 @@ static char *get_trace_output(struct hist_entry *he) { struct trace_seq seq; struct perf_evsel *evsel; - struct pevent_record rec = { + struct tep_record rec = { .data = he->raw_data, .size = he->raw_size, }; @@ -644,10 +610,10 @@ static char *get_trace_output(struct hist_entry *he) trace_seq_init(&seq); if (symbol_conf.raw_trace) { - pevent_print_fields(&seq, he->raw_data, he->raw_size, - evsel->tp_format); + tep_print_fields(&seq, he->raw_data, he->raw_size, + evsel->tp_format); } else { - pevent_event_info(&seq, evsel->tp_format, &rec); + tep_event_info(&seq, evsel->tp_format, &rec); } /* * Trim the buffer, it starts at 4KB and we're not going to @@ -1208,7 +1174,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, /* print [s] for shared data mmaps */ if ((he->cpumode != PERF_RECORD_MISC_KERNEL) && - map && (map->type == MAP__VARIABLE) && + map && !(map->prot & PROT_EXEC) && (map->flags & MAP_SHARED) && (map->maj || map->min || map->ino || map->ino_generation)) @@ -1542,6 +1508,46 @@ struct sort_entry sort_sym_size = { .se_width_idx = HISTC_SYM_SIZE, }; +/* --sort dso_size */ + +static int64_t _sort__dso_size_cmp(struct map *map_l, struct map *map_r) +{ + int64_t size_l = map_l != NULL ? map__size(map_l) : 0; + int64_t size_r = map_r != NULL ? map__size(map_r) : 0; + + return size_l < size_r ? -1 : + size_l == size_r ? 0 : 1; +} + +static int64_t +sort__dso_size_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return _sort__dso_size_cmp(right->ms.map, left->ms.map); +} + +static int _hist_entry__dso_size_snprintf(struct map *map, char *bf, + size_t bf_size, unsigned int width) +{ + if (map && map->dso) + return repsep_snprintf(bf, bf_size, "%*d", width, + map__size(map)); + + return repsep_snprintf(bf, bf_size, "%*s", width, "unknown"); +} + +static int hist_entry__dso_size_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return _hist_entry__dso_size_snprintf(he->ms.map, bf, size, width); +} + +struct sort_entry sort_dso_size = { + .se_header = "DSO size", + .se_cmp = sort__dso_size_cmp, + .se_snprintf = hist_entry__dso_size_snprintf, + .se_width_idx = HISTC_DSO_SIZE, +}; + struct sort_dimension { const char *name; @@ -1566,6 +1572,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_TRANSACTION, "transaction", sort_transaction), DIM(SORT_TRACE, "trace", sort_trace), DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size), + DIM(SORT_DSO_SIZE, "dso_size", sort_dso_size), DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id), }; @@ -2040,7 +2047,7 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct trace_seq seq; raw_field: trace_seq_init(&seq); - pevent_print_field(&seq, he->raw_data, hde->field); + tep_print_field(&seq, he->raw_data, hde->field); str = seq.buffer; } @@ -2067,7 +2074,7 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, if (field->flags & FIELD_IS_DYNAMIC) { unsigned long long dyn; - pevent_read_number_field(field, a->raw_data, &dyn); + tep_read_number_field(field, a->raw_data, &dyn); offset = dyn & 0xffff; size = (dyn >> 16) & 0xffff; @@ -2304,7 +2311,7 @@ static int add_all_matching_fields(struct perf_evlist *evlist, if (evsel->attr.type != PERF_TYPE_TRACEPOINT) continue; - field = pevent_find_any_field(evsel->tp_format, field_name); + field = tep_find_any_field(evsel->tp_format, field_name); if (field == NULL) continue; @@ -2371,7 +2378,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok, if (!strcmp(field_name, "*")) { ret = add_evsel_fields(evsel, raw_trace, level); } else { - field = pevent_find_any_field(evsel->tp_format, field_name); + field = tep_find_any_field(evsel->tp_format, field_name); if (field == NULL) { pr_debug("Cannot find event field for %s.%s\n", event_name, field_name); @@ -2538,7 +2545,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok, if (sort__mode != SORT_MODE__MEMORY) return -EINVAL; - if (sd->entry == &sort_mem_dcacheline && cacheline_size == 0) + if (sd->entry == &sort_mem_dcacheline && cacheline_size() == 0) return -EINVAL; if (sd->entry == &sort_mem_daddr_sym) @@ -2584,7 +2591,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, if (*tok) { ret = sort_dimension__add(list, tok, evlist, level); if (ret == -EINVAL) { - if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok))) + if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok))) pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); else pr_err("Invalid --sort key: `%s'", tok); diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index f5901c10a563..a97cf8e6be86 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -112,6 +112,8 @@ struct hist_entry { char level; u8 filtered; + + u16 callchain_size; union { /* * Since perf diff only supports the stdio output, TUI @@ -151,6 +153,11 @@ struct hist_entry { struct callchain_root callchain[0]; /* must be last member */ }; +static __pure inline bool hist_entry__has_callchains(struct hist_entry *he) +{ + return he->callchain_size != 0; +} + static inline bool hist_entry__has_pairs(struct hist_entry *he) { return !list_empty(&he->pairs.node); @@ -186,13 +193,13 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he) static inline u64 cl_address(u64 address) { /* return the cacheline of the address */ - return (address & ~(cacheline_size - 1)); + return (address & ~(cacheline_size() - 1)); } static inline u64 cl_offset(u64 address) { /* return the cacheline of the address */ - return (address & (cacheline_size - 1)); + return (address & (cacheline_size() - 1)); } enum sort_mode { @@ -220,6 +227,7 @@ enum sort_type { SORT_TRANSACTION, SORT_TRACE, SORT_SYM_SIZE, + SORT_DSO_SIZE, SORT_CGROUP_ID, /* branch stack specific sort keys */ @@ -268,7 +276,7 @@ extern struct sort_entry sort_thread; extern struct list_head hist_entry__sort_list; struct perf_evlist; -struct pevent; +struct tep_handle; int setup_sorting(struct perf_evlist *evlist); int setup_output_field(void); void reset_output_field(void); @@ -291,5 +299,5 @@ int64_t sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right); int64_t sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right); -char *hist_entry__get_srcline(struct hist_entry *he); +char *hist_entry__srcline(struct hist_entry *he); #endif /* __PERF_SORT_H */ diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 3c21fd059b64..09d6746e6ec8 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -103,6 +103,7 @@ static struct symbol *new_inline_sym(struct dso *dso, inline_sym = symbol__new(base_sym ? base_sym->start : 0, base_sym ? base_sym->end : 0, base_sym ? base_sym->binding : 0, + base_sym ? base_sym->type : 0, funcname); if (inline_sym) inline_sym->inlined = 1; diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 594d14a02b67..99990f5f2512 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -913,11 +913,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, ratio = total / avg; print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio); - } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) || - perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) { + } else if (perf_evsel__is_clock(evsel)) { if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0) print_metric(ctxp, NULL, "%8.3f", "CPUs utilized", - avg / ratio); + avg / (ratio * evsel->scale)); else print_metric(ctxp, NULL, NULL, "CPUs utilized", 0); } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) { diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 32235657c1ac..a0061e0b0fad 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -92,7 +92,7 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { }; #undef ID -void perf_stat_evsel_id_init(struct perf_evsel *evsel) +static void perf_stat_evsel_id_init(struct perf_evsel *evsel) { struct perf_stat_evsel *ps = evsel->stats; int i; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index dbc6f7134f61..36efb986f7fc 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -7,8 +7,7 @@ #include "xyarray.h" #include "rblist.h" -struct stats -{ +struct stats { double n, mean, M2; u64 max, min; }; @@ -90,6 +89,8 @@ struct perf_stat_config { bool scale; FILE *output; unsigned int interval; + unsigned int timeout; + int times; struct runtime_stat *stats; int stats_num; }; @@ -126,8 +127,6 @@ bool __perf_evsel_stat__is(struct perf_evsel *evsel, #define perf_stat_evsel__is(evsel, id) \ __perf_evsel_stat__is(evsel, PERF_STAT_EVSEL_ID__ ## id) -void perf_stat_evsel_id_init(struct perf_evsel *evsel); - extern struct runtime_stat rt_stat; extern struct stats walltime_nsecs_stats; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 2de770511e70..29770ea61768 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -114,16 +114,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym) sym->st_shndx != SHN_ABS; } -static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type) +static bool elf_sym__filter(GElf_Sym *sym) { - switch (type) { - case MAP__FUNCTION: - return elf_sym__is_function(sym); - case MAP__VARIABLE: - return elf_sym__is_object(sym); - default: - return false; - } + return elf_sym__is_function(sym) || elf_sym__is_object(sym); } static inline const char *elf_sym__name(const GElf_Sym *sym, @@ -150,17 +143,10 @@ static inline bool elf_sec__is_data(const GElf_Shdr *shdr, return strstr(elf_sec__name(shdr, secstrs), "data") != NULL; } -static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs, - enum map_type type) +static bool elf_sec__filter(GElf_Shdr *shdr, Elf_Data *secstrs) { - switch (type) { - case MAP__FUNCTION: - return elf_sec__is_text(shdr, secstrs); - case MAP__VARIABLE: - return elf_sec__is_data(shdr, secstrs); - default: - return false; - } + return elf_sec__is_text(shdr, secstrs) || + elf_sec__is_data(shdr, secstrs); } static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr) @@ -256,7 +242,7 @@ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) * And always look at the original dso, not at debuginfo packages, that * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS). */ -int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map) +int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss) { uint32_t nr_rel_entries, idx; GElf_Sym sym; @@ -364,12 +350,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * free(demangled); f = symbol__new(plt_offset, plt_entry_size, - STB_GLOBAL, sympltname); + STB_GLOBAL, STT_FUNC, sympltname); if (!f) goto out_elf_end; plt_offset += plt_entry_size; - symbols__insert(&dso->symbols[map->type], f); + symbols__insert(&dso->symbols, f); ++nr; } } else if (shdr_rel_plt.sh_type == SHT_REL) { @@ -390,12 +376,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map * free(demangled); f = symbol__new(plt_offset, plt_entry_size, - STB_GLOBAL, sympltname); + STB_GLOBAL, STT_FUNC, sympltname); if (!f) goto out_elf_end; plt_offset += plt_entry_size; - symbols__insert(&dso->symbols[map->type], f); + symbols__insert(&dso->symbols, f); ++nr; } } @@ -811,6 +797,110 @@ static u64 ref_reloc(struct kmap *kmap) void __weak arch__sym_update(struct symbol *s __maybe_unused, GElf_Sym *sym __maybe_unused) { } +static int dso__process_kernel_symbol(struct dso *dso, struct map *map, + GElf_Sym *sym, GElf_Shdr *shdr, + struct map_groups *kmaps, struct kmap *kmap, + struct dso **curr_dsop, struct map **curr_mapp, + const char *section_name, + bool adjust_kernel_syms, bool kmodule, bool *remap_kernel) +{ + struct dso *curr_dso = *curr_dsop; + struct map *curr_map; + char dso_name[PATH_MAX]; + + /* Adjust symbol to map to file offset */ + if (adjust_kernel_syms) + sym->st_value -= shdr->sh_addr - shdr->sh_offset; + + if (strcmp(section_name, (curr_dso->short_name + dso->short_name_len)) == 0) + return 0; + + if (strcmp(section_name, ".text") == 0) { + /* + * The initial kernel mapping is based on + * kallsyms and identity maps. Overwrite it to + * map to the kernel dso. + */ + if (*remap_kernel && dso->kernel) { + *remap_kernel = false; + map->start = shdr->sh_addr + ref_reloc(kmap); + map->end = map->start + shdr->sh_size; + map->pgoff = shdr->sh_offset; + map->map_ip = map__map_ip; + map->unmap_ip = map__unmap_ip; + /* Ensure maps are correctly ordered */ + if (kmaps) { + map__get(map); + map_groups__remove(kmaps, map); + map_groups__insert(kmaps, map); + map__put(map); + } + } + + /* + * The initial module mapping is based on + * /proc/modules mapped to offset zero. + * Overwrite it to map to the module dso. + */ + if (*remap_kernel && kmodule) { + *remap_kernel = false; + map->pgoff = shdr->sh_offset; + } + + *curr_mapp = map; + *curr_dsop = dso; + return 0; + } + + if (!kmap) + return 0; + + snprintf(dso_name, sizeof(dso_name), "%s%s", dso->short_name, section_name); + + curr_map = map_groups__find_by_name(kmaps, dso_name); + if (curr_map == NULL) { + u64 start = sym->st_value; + + if (kmodule) + start += map->start + shdr->sh_offset; + + curr_dso = dso__new(dso_name); + if (curr_dso == NULL) + return -1; + curr_dso->kernel = dso->kernel; + curr_dso->long_name = dso->long_name; + curr_dso->long_name_len = dso->long_name_len; + curr_map = map__new2(start, curr_dso); + dso__put(curr_dso); + if (curr_map == NULL) + return -1; + + if (adjust_kernel_syms) { + curr_map->start = shdr->sh_addr + ref_reloc(kmap); + curr_map->end = curr_map->start + shdr->sh_size; + curr_map->pgoff = shdr->sh_offset; + } else { + curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; + } + curr_dso->symtab_type = dso->symtab_type; + map_groups__insert(kmaps, curr_map); + /* + * Add it before we drop the referece to curr_map, i.e. while + * we still are sure to have a reference to this DSO via + * *curr_map->dso. + */ + dsos__add(&map->groups->machine->dsos, curr_dso); + /* kmaps already got it */ + map__put(curr_map); + dso__set_loaded(curr_dso); + *curr_mapp = curr_map; + *curr_dsop = curr_dso; + } else + *curr_dsop = curr_map->dso; + + return 0; +} + int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule) { @@ -844,7 +934,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, * have the wrong values for the dso maps, so remove them. */ if (kmodule && syms_ss->symtab) - symbols__delete(&dso->symbols[map->type]); + symbols__delete(&dso->symbols); if (!syms_ss->symtab) { /* @@ -921,10 +1011,10 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap); /* - * Initial kernel and module mappings do not map to the dso. For - * function mappings, flag the fixups. + * Initial kernel and module mappings do not map to the dso. + * Flag the fixups. */ - if (map->type == MAP__FUNCTION && (dso->kernel || kmodule)) { + if (dso->kernel || kmodule) { remap_kernel = true; adjust_kernel_syms = dso->adjust_symbols; } @@ -936,7 +1026,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, const char *section_name; bool used_opd = false; - if (!is_label && !elf_sym__is_a(&sym, map->type)) + if (!is_label && !elf_sym__filter(&sym)) continue; /* Reject ARM ELF "mapping symbols": these aren't unique and @@ -974,7 +1064,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, gelf_getshdr(sec, &shdr); - if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type)) + if (is_label && !elf_sec__filter(&shdr, secstrs)) continue; section_name = elf_sec__name(&shdr, secstrs); @@ -982,134 +1072,37 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, /* On ARM, symbols for thumb functions have 1 added to * the symbol address as a flag - remove it */ if ((ehdr.e_machine == EM_ARM) && - (map->type == MAP__FUNCTION) && + (GELF_ST_TYPE(sym.st_info) == STT_FUNC) && (sym.st_value & 1)) --sym.st_value; if (dso->kernel || kmodule) { - char dso_name[PATH_MAX]; - - /* Adjust symbol to map to file offset */ - if (adjust_kernel_syms) - sym.st_value -= shdr.sh_addr - shdr.sh_offset; - - if (strcmp(section_name, - (curr_dso->short_name + - dso->short_name_len)) == 0) - goto new_symbol; - - if (strcmp(section_name, ".text") == 0) { - /* - * The initial kernel mapping is based on - * kallsyms and identity maps. Overwrite it to - * map to the kernel dso. - */ - if (remap_kernel && dso->kernel) { - remap_kernel = false; - map->start = shdr.sh_addr + - ref_reloc(kmap); - map->end = map->start + shdr.sh_size; - map->pgoff = shdr.sh_offset; - map->map_ip = map__map_ip; - map->unmap_ip = map__unmap_ip; - /* Ensure maps are correctly ordered */ - if (kmaps) { - map__get(map); - map_groups__remove(kmaps, map); - map_groups__insert(kmaps, map); - map__put(map); - } - } - - /* - * The initial module mapping is based on - * /proc/modules mapped to offset zero. - * Overwrite it to map to the module dso. - */ - if (remap_kernel && kmodule) { - remap_kernel = false; - map->pgoff = shdr.sh_offset; - } - - curr_map = map; - curr_dso = dso; - goto new_symbol; - } - - if (!kmap) - goto new_symbol; - - snprintf(dso_name, sizeof(dso_name), - "%s%s", dso->short_name, section_name); - - curr_map = map_groups__find_by_name(kmaps, map->type, dso_name); - if (curr_map == NULL) { - u64 start = sym.st_value; - - if (kmodule) - start += map->start + shdr.sh_offset; - - curr_dso = dso__new(dso_name); - if (curr_dso == NULL) - goto out_elf_end; - curr_dso->kernel = dso->kernel; - curr_dso->long_name = dso->long_name; - curr_dso->long_name_len = dso->long_name_len; - curr_map = map__new2(start, curr_dso, - map->type); - dso__put(curr_dso); - if (curr_map == NULL) { - goto out_elf_end; - } - if (adjust_kernel_syms) { - curr_map->start = shdr.sh_addr + - ref_reloc(kmap); - curr_map->end = curr_map->start + - shdr.sh_size; - curr_map->pgoff = shdr.sh_offset; - } else { - curr_map->map_ip = identity__map_ip; - curr_map->unmap_ip = identity__map_ip; - } - curr_dso->symtab_type = dso->symtab_type; - map_groups__insert(kmaps, curr_map); - /* - * Add it before we drop the referece to curr_map, - * i.e. while we still are sure to have a reference - * to this DSO via curr_map->dso. - */ - dsos__add(&map->groups->machine->dsos, curr_dso); - /* kmaps already got it */ - map__put(curr_map); - dso__set_loaded(curr_dso, map->type); - } else - curr_dso = curr_map->dso; - - goto new_symbol; - } - - if ((used_opd && runtime_ss->adjust_symbols) - || (!used_opd && syms_ss->adjust_symbols)) { + if (dso__process_kernel_symbol(dso, map, &sym, &shdr, kmaps, kmap, &curr_dso, &curr_map, + section_name, adjust_kernel_syms, kmodule, &remap_kernel)) + goto out_elf_end; + } else if ((used_opd && runtime_ss->adjust_symbols) || + (!used_opd && syms_ss->adjust_symbols)) { pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " " "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__, (u64)sym.st_value, (u64)shdr.sh_addr, (u64)shdr.sh_offset); sym.st_value -= shdr.sh_addr - shdr.sh_offset; } -new_symbol: + demangled = demangle_sym(dso, kmodule, elf_name); if (demangled != NULL) elf_name = demangled; f = symbol__new(sym.st_value, sym.st_size, - GELF_ST_BIND(sym.st_info), elf_name); + GELF_ST_BIND(sym.st_info), + GELF_ST_TYPE(sym.st_info), elf_name); free(demangled); if (!f) goto out_elf_end; arch__sym_update(f, &sym); - __symbols__insert(&curr_dso->symbols[curr_map->type], f, dso->kernel); + __symbols__insert(&curr_dso->symbols, f, dso->kernel); nr++; } @@ -1117,14 +1110,14 @@ new_symbol: * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { - symbols__fixup_end(&dso->symbols[map->type]); - symbols__fixup_duplicate(&dso->symbols[map->type]); + symbols__fixup_end(&dso->symbols); + symbols__fixup_duplicate(&dso->symbols); if (kmap) { /* * We need to fixup this here too because we create new * maps here, for things like vsyscall sections. */ - __map_groups__fixup_end(kmaps, map->type); + map_groups__fixup_end(kmaps); } } err = nr; @@ -1393,8 +1386,16 @@ static off_t kcore__write(struct kcore *kcore) struct phdr_data { off_t offset; + off_t rel; u64 addr; u64 len; + struct list_head node; + struct phdr_data *remaps; +}; + +struct sym_data { + u64 addr; + struct list_head node; }; struct kcore_copy_info { @@ -1404,16 +1405,78 @@ struct kcore_copy_info { u64 last_symbol; u64 first_module; u64 last_module_symbol; - struct phdr_data kernel_map; - struct phdr_data modules_map; + size_t phnum; + struct list_head phdrs; + struct list_head syms; }; +#define kcore_copy__for_each_phdr(k, p) \ + list_for_each_entry((p), &(k)->phdrs, node) + +static struct phdr_data *phdr_data__new(u64 addr, u64 len, off_t offset) +{ + struct phdr_data *p = zalloc(sizeof(*p)); + + if (p) { + p->addr = addr; + p->len = len; + p->offset = offset; + } + + return p; +} + +static struct phdr_data *kcore_copy_info__addnew(struct kcore_copy_info *kci, + u64 addr, u64 len, + off_t offset) +{ + struct phdr_data *p = phdr_data__new(addr, len, offset); + + if (p) + list_add_tail(&p->node, &kci->phdrs); + + return p; +} + +static void kcore_copy__free_phdrs(struct kcore_copy_info *kci) +{ + struct phdr_data *p, *tmp; + + list_for_each_entry_safe(p, tmp, &kci->phdrs, node) { + list_del(&p->node); + free(p); + } +} + +static struct sym_data *kcore_copy__new_sym(struct kcore_copy_info *kci, + u64 addr) +{ + struct sym_data *s = zalloc(sizeof(*s)); + + if (s) { + s->addr = addr; + list_add_tail(&s->node, &kci->syms); + } + + return s; +} + +static void kcore_copy__free_syms(struct kcore_copy_info *kci) +{ + struct sym_data *s, *tmp; + + list_for_each_entry_safe(s, tmp, &kci->syms, node) { + list_del(&s->node); + free(s); + } +} + static int kcore_copy__process_kallsyms(void *arg, const char *name, char type, u64 start) { struct kcore_copy_info *kci = arg; - if (!symbol_type__is_a(type, MAP__FUNCTION)) + if (!kallsyms__is_function(type)) return 0; if (strchr(name, '[')) { @@ -1438,6 +1501,9 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type, return 0; } + if (is_entry_trampoline(name) && !kcore_copy__new_sym(kci, start)) + return -1; + return 0; } @@ -1487,27 +1553,39 @@ static int kcore_copy__parse_modules(struct kcore_copy_info *kci, return 0; } -static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff, - u64 s, u64 e) +static int kcore_copy__map(struct kcore_copy_info *kci, u64 start, u64 end, + u64 pgoff, u64 s, u64 e) { - if (p->addr || s < start || s >= end) - return; + u64 len, offset; + + if (s < start || s >= end) + return 0; - p->addr = s; - p->offset = (s - start) + pgoff; - p->len = e < end ? e - s : end - s; + offset = (s - start) + pgoff; + len = e < end ? e - s : end - s; + + return kcore_copy_info__addnew(kci, s, len, offset) ? 0 : -1; } static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data) { struct kcore_copy_info *kci = data; u64 end = start + len; + struct sym_data *sdat; - kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext, - kci->etext); + if (kcore_copy__map(kci, start, end, pgoff, kci->stext, kci->etext)) + return -1; - kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module, - kci->last_module_symbol); + if (kcore_copy__map(kci, start, end, pgoff, kci->first_module, + kci->last_module_symbol)) + return -1; + + list_for_each_entry(sdat, &kci->syms, node) { + u64 s = round_down(sdat->addr, page_size); + + if (kcore_copy__map(kci, start, end, pgoff, s, s + len)) + return -1; + } return 0; } @@ -1520,6 +1598,64 @@ static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf) return 0; } +static void kcore_copy__find_remaps(struct kcore_copy_info *kci) +{ + struct phdr_data *p, *k = NULL; + u64 kend; + + if (!kci->stext) + return; + + /* Find phdr that corresponds to the kernel map (contains stext) */ + kcore_copy__for_each_phdr(kci, p) { + u64 pend = p->addr + p->len - 1; + + if (p->addr <= kci->stext && pend >= kci->stext) { + k = p; + break; + } + } + + if (!k) + return; + + kend = k->offset + k->len; + + /* Find phdrs that remap the kernel */ + kcore_copy__for_each_phdr(kci, p) { + u64 pend = p->offset + p->len; + + if (p == k) + continue; + + if (p->offset >= k->offset && pend <= kend) + p->remaps = k; + } +} + +static void kcore_copy__layout(struct kcore_copy_info *kci) +{ + struct phdr_data *p; + off_t rel = 0; + + kcore_copy__find_remaps(kci); + + kcore_copy__for_each_phdr(kci, p) { + if (!p->remaps) { + p->rel = rel; + rel += p->len; + } + kci->phnum += 1; + } + + kcore_copy__for_each_phdr(kci, p) { + struct phdr_data *k = p->remaps; + + if (k) + p->rel = p->offset - k->offset + k->rel; + } +} + static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir, Elf *elf) { @@ -1555,7 +1691,12 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir, if (kci->first_module && !kci->last_module_symbol) return -1; - return kcore_copy__read_maps(kci, elf); + if (kcore_copy__read_maps(kci, elf)) + return -1; + + kcore_copy__layout(kci); + + return 0; } static int kcore_copy__copy_file(const char *from_dir, const char *to_dir, @@ -1678,12 +1819,15 @@ int kcore_copy(const char *from_dir, const char *to_dir) { struct kcore kcore; struct kcore extract; - size_t count = 2; int idx = 0, err = -1; - off_t offset = page_size, sz, modules_offset = 0; + off_t offset, sz; struct kcore_copy_info kci = { .stext = 0, }; char kcore_filename[PATH_MAX]; char extract_filename[PATH_MAX]; + struct phdr_data *p; + + INIT_LIST_HEAD(&kci.phdrs); + INIT_LIST_HEAD(&kci.syms); if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms")) return -1; @@ -1703,20 +1847,17 @@ int kcore_copy(const char *from_dir, const char *to_dir) if (kcore__init(&extract, extract_filename, kcore.elfclass, false)) goto out_kcore_close; - if (!kci.modules_map.addr) - count -= 1; - - if (kcore__copy_hdr(&kcore, &extract, count)) + if (kcore__copy_hdr(&kcore, &extract, kci.phnum)) goto out_extract_close; - if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr, - kci.kernel_map.len)) - goto out_extract_close; + offset = gelf_fsize(extract.elf, ELF_T_EHDR, 1, EV_CURRENT) + + gelf_fsize(extract.elf, ELF_T_PHDR, kci.phnum, EV_CURRENT); + offset = round_up(offset, page_size); + + kcore_copy__for_each_phdr(&kci, p) { + off_t offs = p->rel + offset; - if (kci.modules_map.addr) { - modules_offset = offset + kci.kernel_map.len; - if (kcore__add_phdr(&extract, idx, modules_offset, - kci.modules_map.addr, kci.modules_map.len)) + if (kcore__add_phdr(&extract, idx++, offs, p->addr, p->len)) goto out_extract_close; } @@ -1724,14 +1865,14 @@ int kcore_copy(const char *from_dir, const char *to_dir) if (sz < 0 || sz > offset) goto out_extract_close; - if (copy_bytes(kcore.fd, kci.kernel_map.offset, extract.fd, offset, - kci.kernel_map.len)) - goto out_extract_close; + kcore_copy__for_each_phdr(&kci, p) { + off_t offs = p->rel + offset; - if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset, - extract.fd, modules_offset, - kci.modules_map.len)) - goto out_extract_close; + if (p->remaps) + continue; + if (copy_bytes(kcore.fd, p->offset, extract.fd, offs, p->len)) + goto out_extract_close; + } if (kcore_copy__compare_file(from_dir, to_dir, "modules")) goto out_extract_close; @@ -1754,6 +1895,9 @@ out_unlink_kallsyms: if (err) kcore_copy__unlink(to_dir, "kallsyms"); + kcore_copy__free_phdrs(&kci); + kcore_copy__free_syms(&kci); + return err; } diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index ff48d0d49584..7119df77dc0b 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -288,8 +288,7 @@ void symsrc__destroy(struct symsrc *ss) } int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused, - struct symsrc *ss __maybe_unused, - struct map *map __maybe_unused) + struct symsrc *ss __maybe_unused) { return 0; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index cc065d4bfafc..d188b7588152 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -5,6 +5,7 @@ #include <stdio.h> #include <string.h> #include <linux/kernel.h> +#include <linux/mman.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/param.h> @@ -39,7 +40,6 @@ char **vmlinux_path; struct symbol_conf symbol_conf = { .use_modules = true, .try_vmlinux_path = true, - .annotate_src = true, .demangle = true, .demangle_kernel = false, .cumulate_callchain = true, @@ -70,18 +70,10 @@ static enum dso_binary_type binary_type_symtab[] = { #define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab) -bool symbol_type__is_a(char symbol_type, enum map_type map_type) +static bool symbol_type__filter(char symbol_type) { symbol_type = toupper(symbol_type); - - switch (map_type) { - case MAP__FUNCTION: - return symbol_type == 'T' || symbol_type == 'W'; - case MAP__VARIABLE: - return symbol_type == 'D'; - default: - return false; - } + return symbol_type == 'T' || symbol_type == 'W' || symbol_type == 'D' || symbol_type == 'B'; } static int prefix_underscores_count(const char *str) @@ -228,9 +220,9 @@ void symbols__fixup_end(struct rb_root *symbols) curr->end = roundup(curr->start, 4096) + 4096; } -void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) +void map_groups__fixup_end(struct map_groups *mg) { - struct maps *maps = &mg->maps[type]; + struct maps *maps = &mg->maps; struct map *next, *curr; down_write(&maps->lock); @@ -256,7 +248,7 @@ out_unlock: up_write(&maps->lock); } -struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name) +struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name) { size_t namelen = strlen(name) + 1; struct symbol *sym = calloc(1, (symbol_conf.priv_size + @@ -274,6 +266,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name) sym->start = start; sym->end = len ? start + len : start; + sym->type = type; sym->binding = binding; sym->namelen = namelen - 1; @@ -484,45 +477,40 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, void dso__reset_find_symbol_cache(struct dso *dso) { - enum map_type type; - - for (type = MAP__FUNCTION; type <= MAP__VARIABLE; ++type) { - dso->last_find_result[type].addr = 0; - dso->last_find_result[type].symbol = NULL; - } + dso->last_find_result.addr = 0; + dso->last_find_result.symbol = NULL; } -void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym) +void dso__insert_symbol(struct dso *dso, struct symbol *sym) { - __symbols__insert(&dso->symbols[type], sym, dso->kernel); + __symbols__insert(&dso->symbols, sym, dso->kernel); /* update the symbol cache if necessary */ - if (dso->last_find_result[type].addr >= sym->start && - (dso->last_find_result[type].addr < sym->end || + if (dso->last_find_result.addr >= sym->start && + (dso->last_find_result.addr < sym->end || sym->start == sym->end)) { - dso->last_find_result[type].symbol = sym; + dso->last_find_result.symbol = sym; } } -struct symbol *dso__find_symbol(struct dso *dso, - enum map_type type, u64 addr) +struct symbol *dso__find_symbol(struct dso *dso, u64 addr) { - if (dso->last_find_result[type].addr != addr || dso->last_find_result[type].symbol == NULL) { - dso->last_find_result[type].addr = addr; - dso->last_find_result[type].symbol = symbols__find(&dso->symbols[type], addr); + if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) { + dso->last_find_result.addr = addr; + dso->last_find_result.symbol = symbols__find(&dso->symbols, addr); } - return dso->last_find_result[type].symbol; + return dso->last_find_result.symbol; } -struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) +struct symbol *dso__first_symbol(struct dso *dso) { - return symbols__first(&dso->symbols[type]); + return symbols__first(&dso->symbols); } -struct symbol *dso__last_symbol(struct dso *dso, enum map_type type) +struct symbol *dso__last_symbol(struct dso *dso) { - return symbols__last(&dso->symbols[type]); + return symbols__last(&dso->symbols); } struct symbol *dso__next_symbol(struct symbol *sym) @@ -539,24 +527,22 @@ struct symbol *symbol__next_by_name(struct symbol *sym) } /* - * Teturns first symbol that matched with @name. + * Returns first symbol that matched with @name. */ -struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, - const char *name) +struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name) { - struct symbol *s = symbols__find_by_name(&dso->symbol_names[type], name, + struct symbol *s = symbols__find_by_name(&dso->symbol_names, name, SYMBOL_TAG_INCLUDE__NONE); if (!s) - s = symbols__find_by_name(&dso->symbol_names[type], name, + s = symbols__find_by_name(&dso->symbol_names, name, SYMBOL_TAG_INCLUDE__DEFAULT_ONLY); return s; } -void dso__sort_by_name(struct dso *dso, enum map_type type) +void dso__sort_by_name(struct dso *dso) { - dso__set_sorted_by_name(dso, type); - return symbols__sort_by_name(&dso->symbol_names[type], - &dso->symbols[type]); + dso__set_sorted_by_name(dso); + return symbols__sort_by_name(&dso->symbol_names, &dso->symbols); } int modules__parse(const char *filename, void *arg, @@ -621,11 +607,6 @@ out: return err; } -struct process_kallsyms_args { - struct map *map; - struct dso *dso; -}; - /* * These are symbols in the kernel image, so make sure that * sym is from a kernel DSO. @@ -661,10 +642,10 @@ static int map__process_kallsym_symbol(void *arg, const char *name, char type, u64 start) { struct symbol *sym; - struct process_kallsyms_args *a = arg; - struct rb_root *root = &a->dso->symbols[a->map->type]; + struct dso *dso = arg; + struct rb_root *root = &dso->symbols; - if (!symbol_type__is_a(type, a->map->type)) + if (!symbol_type__filter(type)) return 0; /* @@ -672,7 +653,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name, * symbols, setting length to 0, and rely on * symbols__fixup_end() to fix it up. */ - sym = symbol__new(start, 0, kallsyms2elf_binding(type), name); + sym = symbol__new(start, 0, kallsyms2elf_binding(type), kallsyms2elf_type(type), name); if (sym == NULL) return -ENOMEM; /* @@ -689,21 +670,18 @@ static int map__process_kallsym_symbol(void *arg, const char *name, * so that we can in the next step set the symbol ->end address and then * call kernel_maps__split_kallsyms. */ -static int dso__load_all_kallsyms(struct dso *dso, const char *filename, - struct map *map) +static int dso__load_all_kallsyms(struct dso *dso, const char *filename) { - struct process_kallsyms_args args = { .map = map, .dso = dso, }; - return kallsyms__parse(filename, &args, map__process_kallsym_symbol); + return kallsyms__parse(filename, dso, map__process_kallsym_symbol); } -static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map) +static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct dso *dso) { - struct map_groups *kmaps = map__kmaps(map); struct map *curr_map; struct symbol *pos; int count = 0; - struct rb_root old_root = dso->symbols[map->type]; - struct rb_root *root = &dso->symbols[map->type]; + struct rb_root old_root = dso->symbols; + struct rb_root *root = &dso->symbols; struct rb_node *next = rb_first(root); if (!kmaps) @@ -723,7 +701,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map) if (module) *module = '\0'; - curr_map = map_groups__find(kmaps, map->type, pos->start); + curr_map = map_groups__find(kmaps, pos->start); if (!curr_map) { symbol__delete(pos); @@ -733,7 +711,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map) pos->start -= curr_map->start - curr_map->pgoff; if (pos->end) pos->end -= curr_map->start - curr_map->pgoff; - symbols__insert(&curr_map->dso->symbols[curr_map->type], pos); + symbols__insert(&curr_map->dso->symbols, pos); ++count; } @@ -748,22 +726,25 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map) * kernel range is broken in several maps, named [kernel].N, as we don't have * the original ELF section names vmlinux have. */ -static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) +static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, u64 delta, + struct map *initial_map) { - struct map_groups *kmaps = map__kmaps(map); struct machine *machine; - struct map *curr_map = map; + struct map *curr_map = initial_map; struct symbol *pos; int count = 0, moved = 0; - struct rb_root *root = &dso->symbols[map->type]; + struct rb_root *root = &dso->symbols; struct rb_node *next = rb_first(root); int kernel_range = 0; + bool x86_64; if (!kmaps) return -1; machine = kmaps->machine; + x86_64 = machine__is(machine, "x86_64"); + while (next) { char *module; @@ -778,7 +759,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) *module++ = '\0'; if (strcmp(curr_map->dso->short_name, module)) { - if (curr_map != map && + if (curr_map != initial_map && dso->kernel == DSO_TYPE_GUEST_KERNEL && machine__is_default_guest(machine)) { /* @@ -788,18 +769,16 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) * symbols are in its kmap. Mark it as * loaded. */ - dso__set_loaded(curr_map->dso, - curr_map->type); + dso__set_loaded(curr_map->dso); } - curr_map = map_groups__find_by_name(kmaps, - map->type, module); + curr_map = map_groups__find_by_name(kmaps, module); if (curr_map == NULL) { pr_debug("%s/proc/{kallsyms,modules} " "inconsistency while looking " "for \"%s\" module!\n", machine->root_dir, module); - curr_map = map; + curr_map = initial_map; goto discard_symbol; } @@ -809,11 +788,21 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) } /* * So that we look just like we get from .ko files, - * i.e. not prelinked, relative to map->start. + * i.e. not prelinked, relative to initial_map->start. */ pos->start = curr_map->map_ip(curr_map, pos->start); pos->end = curr_map->map_ip(curr_map, pos->end); - } else if (curr_map != map) { + } else if (x86_64 && is_entry_trampoline(pos->name)) { + /* + * These symbols are not needed anymore since the + * trampoline maps refer to the text section and it's + * symbols instead. Avoid having to deal with + * relocations, and the assumption that the first symbol + * is the start of kernel text, by simply removing the + * symbols at this point. + */ + goto discard_symbol; + } else if (curr_map != initial_map) { char dso_name[PATH_MAX]; struct dso *ndso; @@ -824,7 +813,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) } if (count == 0) { - curr_map = map; + curr_map = initial_map; goto add_symbol; } @@ -843,7 +832,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) ndso->kernel = dso->kernel; - curr_map = map__new2(pos->start, ndso, map->type); + curr_map = map__new2(pos->start, ndso); if (curr_map == NULL) { dso__put(ndso); return -1; @@ -858,9 +847,9 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta) pos->end -= delta; } add_symbol: - if (curr_map != map) { + if (curr_map != initial_map) { rb_erase(&pos->rb_node, root); - symbols__insert(&curr_map->dso->symbols[curr_map->type], pos); + symbols__insert(&curr_map->dso->symbols, pos); ++moved; } else ++count; @@ -871,10 +860,10 @@ discard_symbol: symbol__delete(pos); } - if (curr_map != map && + if (curr_map != initial_map && dso->kernel == DSO_TYPE_GUEST_KERNEL && machine__is_default_guest(kmaps->machine)) { - dso__set_loaded(curr_map->dso, curr_map->type); + dso__set_loaded(curr_map->dso); } return count + moved; @@ -1035,7 +1024,12 @@ out_delete_from: return ret; } -static int do_validate_kcore_modules(const char *filename, struct map *map, +struct map *map_groups__first(struct map_groups *mg) +{ + return maps__first(&mg->maps); +} + +static int do_validate_kcore_modules(const char *filename, struct map_groups *kmaps) { struct rb_root modules = RB_ROOT; @@ -1046,13 +1040,12 @@ static int do_validate_kcore_modules(const char *filename, struct map *map, if (err) return err; - old_map = map_groups__first(kmaps, map->type); + old_map = map_groups__first(kmaps); while (old_map) { struct map *next = map_groups__next(old_map); struct module_info *mi; - if (old_map == map || old_map->start == map->start) { - /* The kernel map */ + if (!__map__is_kmodule(old_map)) { old_map = next; continue; } @@ -1109,7 +1102,7 @@ static int validate_kcore_modules(const char *kallsyms_filename, kallsyms_filename)) return -EINVAL; - if (do_validate_kcore_modules(modules_filename, map, kmaps)) + if (do_validate_kcore_modules(modules_filename, kmaps)) return -EINVAL; return 0; @@ -1138,7 +1131,6 @@ static int validate_kcore_addresses(const char *kallsyms_filename, struct kcore_mapfn_data { struct dso *dso; - enum map_type type; struct list_head maps; }; @@ -1147,7 +1139,7 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data) struct kcore_mapfn_data *md = data; struct map *map; - map = map__new2(start, md->dso, md->type); + map = map__new2(start, md->dso); if (map == NULL) return -ENOMEM; @@ -1163,13 +1155,13 @@ static int dso__load_kcore(struct dso *dso, struct map *map, const char *kallsyms_filename) { struct map_groups *kmaps = map__kmaps(map); - struct machine *machine; struct kcore_mapfn_data md; struct map *old_map, *new_map, *replacement_map = NULL; + struct machine *machine; bool is_64_bit; int err, fd; char kcore_filename[PATH_MAX]; - struct symbol *sym; + u64 stext; if (!kmaps) return -EINVAL; @@ -1177,7 +1169,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, machine = kmaps->machine; /* This function requires that the map is the kernel map */ - if (map != machine->vmlinux_maps[map->type]) + if (!__map__is_kernel(map)) return -EINVAL; if (!filename_from_kallsyms_filename(kcore_filename, "kcore", @@ -1189,7 +1181,6 @@ static int dso__load_kcore(struct dso *dso, struct map *map, return -EINVAL; md.dso = dso; - md.type = map->type; INIT_LIST_HEAD(&md.maps); fd = open(kcore_filename, O_RDONLY); @@ -1200,7 +1191,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, } /* Read new maps into temporary lists */ - err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md, + err = file__read_maps(fd, map->prot & PROT_EXEC, kcore_mapfn, &md, &is_64_bit); if (err) goto out_err; @@ -1212,7 +1203,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, } /* Remove old maps */ - old_map = map_groups__first(kmaps, map->type); + old_map = map_groups__first(kmaps); while (old_map) { struct map *next = map_groups__next(old_map); @@ -1220,14 +1211,15 @@ static int dso__load_kcore(struct dso *dso, struct map *map, map_groups__remove(kmaps, old_map); old_map = next; } + machine->trampolines_mapped = false; - /* Find the kernel map using the first symbol */ - sym = dso__first_symbol(dso, map->type); - list_for_each_entry(new_map, &md.maps, node) { - if (sym && sym->start >= new_map->start && - sym->start < new_map->end) { - replacement_map = new_map; - break; + /* Find the kernel map using the '_stext' symbol */ + if (!kallsyms__get_function_start(kallsyms_filename, "_stext", &stext)) { + list_for_each_entry(new_map, &md.maps, node) { + if (stext >= new_map->start && stext < new_map->end) { + replacement_map = new_map; + break; + } } } @@ -1256,6 +1248,19 @@ static int dso__load_kcore(struct dso *dso, struct map *map, map__put(new_map); } + if (machine__is(machine, "x86_64")) { + u64 addr; + + /* + * If one of the corresponding symbols is there, assume the + * entry trampoline maps are too. + */ + if (!kallsyms__get_function_start(kallsyms_filename, + ENTRY_TRAMPOLINE_NAME, + &addr)) + machine->trampolines_mapped = true; + } + /* * Set the data type and long name so that kcore can be read via * dso__data_read_addr(). @@ -1268,7 +1273,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, close(fd); - if (map->type == MAP__FUNCTION) + if (map->prot & PROT_EXEC) pr_debug("Using %s for kernel object code\n", kcore_filename); else pr_debug("Using %s for kernel data\n", kcore_filename); @@ -1289,14 +1294,10 @@ out_err: * If the kernel is relocated at boot time, kallsyms won't match. Compute the * delta based on the relocation reference symbol. */ -static int kallsyms__delta(struct map *map, const char *filename, u64 *delta) +static int kallsyms__delta(struct kmap *kmap, const char *filename, u64 *delta) { - struct kmap *kmap = map__kmap(map); u64 addr; - if (!kmap) - return -1; - if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name) return 0; @@ -1310,19 +1311,23 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta) int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, bool no_kcore) { + struct kmap *kmap = map__kmap(map); u64 delta = 0; if (symbol__restricted_filename(filename, "/proc/kallsyms")) return -1; - if (dso__load_all_kallsyms(dso, filename, map) < 0) + if (!kmap || !kmap->kmaps) + return -1; + + if (dso__load_all_kallsyms(dso, filename) < 0) return -1; - if (kallsyms__delta(map, filename, &delta)) + if (kallsyms__delta(kmap, filename, &delta)) return -1; - symbols__fixup_end(&dso->symbols[map->type]); - symbols__fixup_duplicate(&dso->symbols[map->type]); + symbols__fixup_end(&dso->symbols); + symbols__fixup_duplicate(&dso->symbols); if (dso->kernel == DSO_TYPE_GUEST_KERNEL) dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS; @@ -1330,9 +1335,9 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS; if (!no_kcore && !dso__load_kcore(dso, map, filename)) - return dso__split_kallsyms_for_kcore(dso, map); + return map_groups__split_kallsyms_for_kcore(kmap->kmaps, dso); else - return dso__split_kallsyms(dso, map, delta); + return map_groups__split_kallsyms(kmap->kmaps, dso, delta, map); } int dso__load_kallsyms(struct dso *dso, const char *filename, @@ -1341,8 +1346,7 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, return __dso__load_kallsyms(dso, filename, map, false); } -static int dso__load_perf_map(const char *map_path, struct dso *dso, - struct map *map) +static int dso__load_perf_map(const char *map_path, struct dso *dso) { char *line = NULL; size_t n; @@ -1379,12 +1383,12 @@ static int dso__load_perf_map(const char *map_path, struct dso *dso, if (len + 2 >= line_len) continue; - sym = symbol__new(start, size, STB_GLOBAL, line + len); + sym = symbol__new(start, size, STB_GLOBAL, STT_FUNC, line + len); if (sym == NULL) goto out_delete_line; - symbols__insert(&dso->symbols[map->type], sym); + symbols__insert(&dso->symbols, sym); nr_syms++; } @@ -1509,25 +1513,27 @@ int dso__load(struct dso *dso, struct map *map) pthread_mutex_lock(&dso->lock); /* check again under the dso->lock */ - if (dso__loaded(dso, map->type)) { + if (dso__loaded(dso)) { ret = 1; goto out; } + if (map->groups && map->groups->machine) + machine = map->groups->machine; + else + machine = NULL; + if (dso->kernel) { if (dso->kernel == DSO_TYPE_KERNEL) ret = dso__load_kernel_sym(dso, map); else if (dso->kernel == DSO_TYPE_GUEST_KERNEL) ret = dso__load_guest_kernel_sym(dso, map); + if (machine__is(machine, "x86_64")) + machine__map_x86_64_entry_trampolines(machine, dso); goto out; } - if (map->groups && map->groups->machine) - machine = map->groups->machine; - else - machine = NULL; - dso->adjust_symbols = 0; if (perfmap) { @@ -1542,7 +1548,7 @@ int dso__load(struct dso *dso, struct map *map) goto out; } - ret = dso__load_perf_map(map_path, dso, map); + ret = dso__load_perf_map(map_path, dso); dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT : DSO_BINARY_TYPE__NOT_FOUND; goto out; @@ -1582,7 +1588,7 @@ int dso__load(struct dso *dso, struct map *map) bool next_slot = false; bool is_reg; bool nsexit; - int sirc; + int sirc = -1; enum dso_binary_type symtab_type = binary_type_symtab[i]; @@ -1600,16 +1606,14 @@ int dso__load(struct dso *dso, struct map *map) nsinfo__mountns_exit(&nsc); is_reg = is_regular_file(name); - sirc = symsrc__init(ss, dso, name, symtab_type); + if (is_reg) + sirc = symsrc__init(ss, dso, name, symtab_type); if (nsexit) nsinfo__mountns_enter(dso->nsinfo, &nsc); - if (!is_reg || sirc < 0) { - if (sirc >= 0) - symsrc__destroy(ss); + if (!is_reg || sirc < 0) continue; - } if (!syms_ss && symsrc__has_symtab(ss)) { syms_ss = ss; @@ -1653,7 +1657,7 @@ int dso__load(struct dso *dso, struct map *map) if (ret > 0) { int nr_plt; - nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map); + nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss); if (nr_plt > 0) ret += nr_plt; } @@ -1665,17 +1669,16 @@ out_free: if (ret < 0 && strstr(dso->name, " (deleted)") != NULL) ret = 0; out: - dso__set_loaded(dso, map->type); + dso__set_loaded(dso); pthread_mutex_unlock(&dso->lock); nsinfo__mountns_exit(&nsc); return ret; } -struct map *map_groups__find_by_name(struct map_groups *mg, - enum map_type type, const char *name) +struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { - struct maps *maps = &mg->maps[type]; + struct maps *maps = &mg->maps; struct map *map; down_read(&maps->lock); @@ -1722,7 +1725,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, else dso->binary_type = DSO_BINARY_TYPE__VMLINUX; dso__set_long_name(dso, vmlinux, vmlinux_allocated); - dso__set_loaded(dso, map->type); + dso__set_loaded(dso); pr_debug("Using %s for symbols\n", symfs_vmlinux); } @@ -1960,8 +1963,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map) pr_debug("Using %s for symbols\n", kallsyms_filename); if (err > 0 && !dso__is_kcore(dso)) { dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS; - machine__mmap_name(machine, path, sizeof(path)); - dso__set_long_name(dso, strdup(path), true); + dso__set_long_name(dso, machine->mmap_name, false); map__fixup_start(map); map__fixup_end(map); } @@ -2094,16 +2096,14 @@ static bool symbol__read_kptr_restrict(void) int symbol__annotation_init(void) { + if (symbol_conf.init_annotation) + return 0; + if (symbol_conf.initialized) { pr_err("Annotation needs to be init before symbol__init()\n"); return -1; } - if (symbol_conf.init_annotation) { - pr_warning("Annotation being initialized multiple times\n"); - return 0; - } - symbol_conf.priv_size += sizeof(struct annotation); symbol_conf.init_annotation = true; return 0; @@ -2224,3 +2224,25 @@ int symbol__config_symfs(const struct option *opt __maybe_unused, free(bf); return 0; } + +struct mem_info *mem_info__get(struct mem_info *mi) +{ + if (mi) + refcount_inc(&mi->refcnt); + return mi; +} + +void mem_info__put(struct mem_info *mi) +{ + if (mi && refcount_dec_and_test(&mi->refcnt)) + free(mi); +} + +struct mem_info *mem_info__new(void) +{ + struct mem_info *mi = zalloc(sizeof(*mi)); + + if (mi) + refcount_set(&mi->refcnt, 1); + return mi; +} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 0563f33c1eb3..f25fae4b5743 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -57,7 +57,8 @@ struct symbol { u64 start; u64 end; u16 namelen; - u8 binding; + u8 type:4; + u8 binding:4; u8 idle:1; u8 ignore:1; u8 inlined:1; @@ -89,7 +90,6 @@ struct intlist; struct symbol_conf { unsigned short priv_size; - unsigned short nr_events; bool try_vmlinux_path, init_annotation, force, @@ -108,8 +108,6 @@ struct symbol_conf { show_cpu_utilization, initialized, kptr_restrict, - annotate_asm_raw, - annotate_src, event_group, demangle, demangle_kernel, @@ -200,9 +198,10 @@ struct branch_info { }; struct mem_info { - struct addr_map_symbol iaddr; - struct addr_map_symbol daddr; - union perf_mem_data_src data_src; + struct addr_map_symbol iaddr; + struct addr_map_symbol daddr; + union perf_mem_data_src data_src; + refcount_t refcnt; }; struct addr_location { @@ -258,17 +257,16 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, bool no_kcore); int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map); -void dso__insert_symbol(struct dso *dso, enum map_type type, +void dso__insert_symbol(struct dso *dso, struct symbol *sym); -struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, - u64 addr); -struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, - const char *name); +struct symbol *dso__find_symbol(struct dso *dso, u64 addr); +struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name); + struct symbol *symbol__next_by_name(struct symbol *sym); -struct symbol *dso__first_symbol(struct dso *dso, enum map_type type); -struct symbol *dso__last_symbol(struct dso *dso, enum map_type type); +struct symbol *dso__first_symbol(struct dso *dso); +struct symbol *dso__last_symbol(struct dso *dso); struct symbol *dso__next_symbol(struct symbol *sym); enum dso_type dso__type_fd(int fd); @@ -287,7 +285,7 @@ void symbol__exit(void); void symbol__elf_init(void); int symbol__annotation_init(void); -struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name); +struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name); size_t __symbol__fprintf_symname_offs(const struct symbol *sym, const struct addr_location *al, bool unknown_as_addr, @@ -299,7 +297,6 @@ size_t __symbol__fprintf_symname(const struct symbol *sym, bool unknown_as_addr, FILE *fp); size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp); size_t symbol__fprintf(struct symbol *sym, FILE *fp); -bool symbol_type__is_a(char symbol_type, enum map_type map_type); bool symbol__restricted_filename(const char *filename, const char *restricted_filename); int symbol__config_symfs(const struct option *opt __maybe_unused, @@ -307,8 +304,7 @@ int symbol__config_symfs(const struct option *opt __maybe_unused, int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule); -int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, - struct map *map); +int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss); char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name); @@ -316,7 +312,7 @@ void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel) void symbols__insert(struct rb_root *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root *symbols); void symbols__fixup_end(struct rb_root *symbols); -void __map_groups__fixup_end(struct map_groups *mg, enum map_type type); +void map_groups__fixup_end(struct map_groups *mg); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data); int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data, @@ -389,4 +385,16 @@ int sdt_notes__get_count(struct list_head *start); #define SDT_NOTE_NAME "stapsdt" #define NR_ADDR 3 +struct mem_info *mem_info__new(void); +struct mem_info *mem_info__get(struct mem_info *mi); +void mem_info__put(struct mem_info *mi); + +static inline void __mem_info__zput(struct mem_info **mi) +{ + mem_info__put(*mi); + *mi = NULL; +} + +#define mem_info__zput(mi) __mem_info__zput(&mi) + #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c index 6dd2cb88ccbe..ed0205cc7942 100644 --- a/tools/perf/util/symbol_fprintf.c +++ b/tools/perf/util/symbol_fprintf.c @@ -58,13 +58,13 @@ size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp) } size_t dso__fprintf_symbols_by_name(struct dso *dso, - enum map_type type, FILE *fp) + FILE *fp) { size_t ret = 0; struct rb_node *nd; struct symbol_name_rb_node *pos; - for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) { + for (nd = rb_first(&dso->symbol_names); nd; nd = rb_next(nd)) { pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); fprintf(fp, "%s\n", pos->sym.name); } diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 303bdb84ab5a..3393d7ee9401 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -17,7 +17,7 @@ #include <stdlib.h> #include <linux/compiler.h> -#ifdef HAVE_SYSCALL_TABLE +#ifdef HAVE_SYSCALL_TABLE_SUPPORT #include <string.h> #include "string2.h" #include "util.h" @@ -30,6 +30,18 @@ static const char **syscalltbl_native = syscalltbl_x86_64; #include <asm/syscalls_64.c> const int syscalltbl_native_max_id = SYSCALLTBL_S390_64_MAX_ID; static const char **syscalltbl_native = syscalltbl_s390_64; +#elif defined(__powerpc64__) +#include <asm/syscalls_64.c> +const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_64_MAX_ID; +static const char **syscalltbl_native = syscalltbl_powerpc_64; +#elif defined(__powerpc__) +#include <asm/syscalls_32.c> +const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID; +static const char **syscalltbl_native = syscalltbl_powerpc_32; +#elif defined(__aarch64__) +#include <asm/syscalls.c> +const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID; +static const char **syscalltbl_native = syscalltbl_arm64; #endif struct syscall { @@ -131,7 +143,7 @@ int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_g return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx); } -#else /* HAVE_SYSCALL_TABLE */ +#else /* HAVE_SYSCALL_TABLE_SUPPORT */ #include <libaudit.h> @@ -168,4 +180,4 @@ int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_g { return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx); } -#endif /* HAVE_SYSCALL_TABLE */ +#endif /* HAVE_SYSCALL_TABLE_SUPPORT */ diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 68b65b10579b..2048d393ece6 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -302,23 +302,20 @@ int thread__insert_map(struct thread *thread, struct map *map) static int __thread__prepare_access(struct thread *thread) { bool initialized = false; - int i, err = 0; - - for (i = 0; i < MAP__NR_TYPES; ++i) { - struct maps *maps = &thread->mg->maps[i]; - struct map *map; + int err = 0; + struct maps *maps = &thread->mg->maps; + struct map *map; - down_read(&maps->lock); + down_read(&maps->lock); - for (map = maps__first(maps); map; map = map__next(map)) { - err = unwind__prepare_access(thread, map, &initialized); - if (err || initialized) - break; - } - - up_read(&maps->lock); + for (map = maps__first(maps); map; map = map__next(map)) { + err = unwind__prepare_access(thread, map, &initialized); + if (err || initialized) + break; } + up_read(&maps->lock); + return err; } @@ -335,8 +332,6 @@ static int thread__prepare_access(struct thread *thread) static int thread__clone_map_groups(struct thread *thread, struct thread *parent) { - int i; - /* This is new thread, we share map groups for process. */ if (thread->pid_ == parent->pid_) return thread__prepare_access(thread); @@ -348,9 +343,8 @@ static int thread__clone_map_groups(struct thread *thread, } /* But this one is new process, copy maps. */ - for (i = 0; i < MAP__NR_TYPES; ++i) - if (map_groups__clone(thread, parent->mg, i) < 0) - return -ENOMEM; + if (map_groups__clone(thread, parent->mg) < 0) + return -ENOMEM; return 0; } @@ -371,8 +365,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) return thread__clone_map_groups(thread, parent); } -void thread__find_cpumode_addr_location(struct thread *thread, - enum map_type type, u64 addr, +void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, struct addr_location *al) { size_t i; @@ -384,7 +377,7 @@ void thread__find_cpumode_addr_location(struct thread *thread, }; for (i = 0; i < ARRAY_SIZE(cpumodes); i++) { - thread__find_addr_location(thread, cpumodes[i], type, addr, al); + thread__find_symbol(thread, cpumodes[i], addr, al); if (al->map) break; } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 40cfa36c022a..07606aa6998d 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -26,7 +26,6 @@ struct thread { pid_t ppid; int cpu; refcount_t refcnt; - char shortname[3]; bool comm_set; int comm_len; bool dead; /* if set thread has exited */ @@ -93,16 +92,13 @@ size_t thread__fprintf(struct thread *thread, FILE *fp); struct thread *thread__main_thread(struct machine *machine, struct thread *thread); -void thread__find_addr_map(struct thread *thread, - u8 cpumode, enum map_type type, u64 addr, - struct addr_location *al); +struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, + struct addr_location *al); -void thread__find_addr_location(struct thread *thread, - u8 cpumode, enum map_type type, u64 addr, - struct addr_location *al); +struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode, + u64 addr, struct addr_location *al); -void thread__find_cpumode_addr_location(struct thread *thread, - enum map_type type, u64 addr, +void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, struct addr_location *al); static inline void *thread__priv(struct thread *thread) diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 3e1038f6491c..5d467d8ae9ab 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -32,6 +32,7 @@ static void thread_map__reset(struct thread_map *map, int start, int nr) size_t size = (nr - start) * sizeof(map->map[0]); memset(&map->map[start], 0, size); + map->err_thread = -1; } static struct thread_map *thread_map__realloc(struct thread_map *map, int nr) @@ -323,7 +324,7 @@ out_free_threads: } struct thread_map *thread_map__new_str(const char *pid, const char *tid, - uid_t uid, bool per_thread) + uid_t uid, bool all_threads) { if (pid) return thread_map__new_by_pid_str(pid); @@ -331,7 +332,7 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid, if (!tid && uid != UINT_MAX) return thread_map__new_by_uid(uid); - if (per_thread) + if (all_threads) return thread_map__new_all_cpus(); return thread_map__new_by_tid_str(tid); diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index 0a806b99e73c..2f689c90a8c6 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -14,6 +14,7 @@ struct thread_map_data { struct thread_map { refcount_t refcnt; int nr; + int err_thread; struct thread_map_data map[]; }; @@ -31,7 +32,7 @@ struct thread_map *thread_map__get(struct thread_map *map); void thread_map__put(struct thread_map *map); struct thread_map *thread_map__new_str(const char *pid, - const char *tid, uid_t uid, bool per_thread); + const char *tid, uid_t uid, bool all_threads); struct thread_map *thread_map__new_by_tid_str(const char *tid_str); diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index 9892323cdd7c..9add1f72ce95 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -3,6 +3,7 @@ #define __PERF_TOP_H 1 #include "tool.h" +#include "annotate.h" #include <linux/types.h> #include <stddef.h> #include <stdbool.h> @@ -16,6 +17,7 @@ struct perf_top { struct perf_tool tool; struct perf_evlist *evlist; struct record_opts record_opts; + struct annotation_options annotation_opts; /* * Symbols will be added here in perf_event__process_sample and will * get out after decayed. @@ -35,7 +37,6 @@ struct perf_top { struct perf_session *session; struct winsize winsize; int realtime_prio; - int sym_pcnt_filter; const char *sym_filter; float min_percent; unsigned int nr_threads_synthesize; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index d7f2113462fb..7b0ca7cbb7de 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -103,11 +103,10 @@ out: static int record_header_files(void) { - char *path; + char *path = get_events_file("header_page"); struct stat st; int err = -EIO; - path = get_tracing_file("events/header_page"); if (!path) { pr_debug("can't get tracing/events/header_page"); return -ENOMEM; @@ -128,9 +127,9 @@ static int record_header_files(void) goto out; } - put_tracing_file(path); + put_events_file(path); - path = get_tracing_file("events/header_event"); + path = get_events_file("header_event"); if (!path) { pr_debug("can't get tracing/events/header_event"); err = -ENOMEM; @@ -154,7 +153,7 @@ static int record_header_files(void) err = 0; out: - put_tracing_file(path); + put_events_file(path); return err; } @@ -243,7 +242,7 @@ static int record_ftrace_files(struct tracepoint_path *tps) char *path; int ret; - path = get_tracing_file("events/ftrace"); + path = get_events_file("ftrace"); if (!path) { pr_debug("can't get tracing/events/ftrace"); return -ENOMEM; @@ -378,7 +377,7 @@ out: static int record_saved_cmdline(void) { - unsigned int size; + unsigned long long size; char *path; struct stat st; int ret, err = 0; diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index e0a6e9a6a053..e76214f8d596 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -32,7 +32,7 @@ static int get_common_field(struct scripting_context *context, int *offset, int *size, const char *type) { - struct pevent *pevent = context->pevent; + struct tep_handle *pevent = context->pevent; struct event_format *event; struct format_field *field; @@ -41,14 +41,14 @@ static int get_common_field(struct scripting_context *context, return 0; event = pevent->events[0]; - field = pevent_find_common_field(event, type); + field = tep_find_common_field(event, type); if (!field) return 0; *offset = field->offset; *size = field->size; } - return pevent_read_number(pevent, context->event_data + *offset, *size); + return tep_read_number(pevent, context->event_data + *offset, *size); } int common_lock_depth(struct scripting_context *context) @@ -99,24 +99,24 @@ raw_field_value(struct event_format *event, const char *name, void *data) struct format_field *field; unsigned long long val; - field = pevent_find_any_field(event, name); + field = tep_find_any_field(event, name); if (!field) return 0ULL; - pevent_read_number_field(field, data, &val); + tep_read_number_field(field, data, &val); return val; } unsigned long long read_size(struct event_format *event, void *ptr, int size) { - return pevent_read_number(event->pevent, ptr, size); + return tep_read_number(event->pevent, ptr, size); } void event_format__fprintf(struct event_format *event, int cpu, void *data, int size, FILE *fp) { - struct pevent_record record; + struct tep_record record; struct trace_seq s; memset(&record, 0, sizeof(record)); @@ -125,7 +125,7 @@ void event_format__fprintf(struct event_format *event, record.data = data; trace_seq_init(&s); - pevent_event_info(&s, event, &record); + tep_event_info(&s, event, &record); trace_seq_do_fprintf(&s, fp); trace_seq_destroy(&s); } @@ -136,7 +136,7 @@ void event_format__print(struct event_format *event, return event_format__fprintf(event, cpu, data, size, stdout); } -void parse_ftrace_printk(struct pevent *pevent, +void parse_ftrace_printk(struct tep_handle *pevent, char *file, unsigned int size __maybe_unused) { unsigned long long addr; @@ -157,39 +157,38 @@ void parse_ftrace_printk(struct pevent *pevent, /* fmt still has a space, skip it */ printk = strdup(fmt+1); line = strtok_r(NULL, "\n", &next); - pevent_register_print_string(pevent, printk, addr); + tep_register_print_string(pevent, printk, addr); } } -void parse_saved_cmdline(struct pevent *pevent, +void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int size __maybe_unused) { - char *comm; + char comm[17]; /* Max comm length in the kernel is 16. */ char *line; char *next = NULL; int pid; line = strtok_r(file, "\n", &next); while (line) { - sscanf(line, "%d %ms", &pid, &comm); - pevent_register_comm(pevent, comm, pid); - free(comm); + if (sscanf(line, "%d %16s", &pid, comm) == 2) + tep_register_comm(pevent, comm, pid); line = strtok_r(NULL, "\n", &next); } } -int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size) +int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size) { - return pevent_parse_event(pevent, buf, size, "ftrace"); + return tep_parse_event(pevent, buf, size, "ftrace"); } -int parse_event_file(struct pevent *pevent, +int parse_event_file(struct tep_handle *pevent, char *buf, unsigned long size, char *sys) { - return pevent_parse_event(pevent, buf, size, sys); + return tep_parse_event(pevent, buf, size, sys); } -struct event_format *trace_find_next_event(struct pevent *pevent, +struct event_format *trace_find_next_event(struct tep_handle *pevent, struct event_format *event) { static int idx; diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 40b425949aa3..3dfc1db6b25b 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -96,7 +96,7 @@ static void skip(int size) }; } -static unsigned int read4(struct pevent *pevent) +static unsigned int read4(struct tep_handle *pevent) { unsigned int data; @@ -105,7 +105,7 @@ static unsigned int read4(struct pevent *pevent) return __data2host4(pevent, data); } -static unsigned long long read8(struct pevent *pevent) +static unsigned long long read8(struct tep_handle *pevent) { unsigned long long data; @@ -158,7 +158,7 @@ out: return str; } -static int read_proc_kallsyms(struct pevent *pevent) +static int read_proc_kallsyms(struct tep_handle *pevent) { unsigned int size; @@ -181,7 +181,7 @@ static int read_proc_kallsyms(struct pevent *pevent) return 0; } -static int read_ftrace_printk(struct pevent *pevent) +static int read_ftrace_printk(struct tep_handle *pevent) { unsigned int size; char *buf; @@ -208,7 +208,7 @@ static int read_ftrace_printk(struct pevent *pevent) return 0; } -static int read_header_files(struct pevent *pevent) +static int read_header_files(struct tep_handle *pevent) { unsigned long long size; char *header_page; @@ -235,13 +235,13 @@ static int read_header_files(struct pevent *pevent) return -1; } - if (!pevent_parse_header_page(pevent, header_page, size, - pevent_get_long_size(pevent))) { + if (!tep_parse_header_page(pevent, header_page, size, + tep_get_long_size(pevent))) { /* * The commit field in the page is of type long, * use that instead, since it represents the kernel. */ - pevent_set_long_size(pevent, pevent->header_page_size_size); + tep_set_long_size(pevent, pevent->header_page_size_size); } free(header_page); @@ -259,7 +259,7 @@ static int read_header_files(struct pevent *pevent) return ret; } -static int read_ftrace_file(struct pevent *pevent, unsigned long long size) +static int read_ftrace_file(struct tep_handle *pevent, unsigned long long size) { int ret; char *buf; @@ -284,8 +284,8 @@ out: return ret; } -static int read_event_file(struct pevent *pevent, char *sys, - unsigned long long size) +static int read_event_file(struct tep_handle *pevent, char *sys, + unsigned long long size) { int ret; char *buf; @@ -310,7 +310,7 @@ out: return ret; } -static int read_ftrace_files(struct pevent *pevent) +static int read_ftrace_files(struct tep_handle *pevent) { unsigned long long size; int count; @@ -328,7 +328,7 @@ static int read_ftrace_files(struct pevent *pevent) return 0; } -static int read_event_files(struct pevent *pevent) +static int read_event_files(struct tep_handle *pevent) { unsigned long long size; char *sys; @@ -356,7 +356,7 @@ static int read_event_files(struct pevent *pevent) return 0; } -static int read_saved_cmdline(struct pevent *pevent) +static int read_saved_cmdline(struct tep_handle *pevent) { unsigned long long size; char *buf; @@ -399,7 +399,7 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) int host_bigendian; int file_long_size; int file_page_size; - struct pevent *pevent = NULL; + struct tep_handle *pevent = NULL; int err; repipe = __repipe; @@ -439,9 +439,9 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) pevent = tevent->pevent; - pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT); - pevent_set_file_bigendian(pevent, file_bigendian); - pevent_set_host_bigendian(pevent, host_bigendian); + tep_set_flag(pevent, TEP_NSEC_OUTPUT); + tep_set_file_bigendian(pevent, file_bigendian); + tep_set_host_bigendian(pevent, host_bigendian); if (do_read(buf, 1) < 0) goto out; @@ -451,8 +451,8 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) if (!file_page_size) goto out; - pevent_set_long_size(pevent, file_long_size); - pevent_set_page_size(pevent, file_page_size); + tep_set_long_size(pevent, file_long_size); + tep_set_page_size(pevent, file_page_size); err = read_header_files(pevent); if (err) @@ -479,9 +479,9 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) repipe = false; if (show_funcs) { - pevent_print_funcs(pevent); + tep_print_funcs(pevent); } else if (show_printk) { - pevent_print_printk(pevent); + tep_print_printk(pevent); } pevent = NULL; diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 0ac9077f62a2..b749f812ac70 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -66,7 +66,7 @@ static int python_start_script_unsupported(const char *script __maybe_unused, return -1; } -static int python_generate_script_unsupported(struct pevent *pevent +static int python_generate_script_unsupported(struct tep_handle *pevent __maybe_unused, const char *outfile __maybe_unused) @@ -98,7 +98,7 @@ static void register_python_scripting(struct scripting_ops *scripting_ops) } } -#ifdef NO_LIBPYTHON +#ifndef HAVE_LIBPYTHON_SUPPORT void setup_python_scripting(void) { register_python_scripting(&python_scripting_unsupported_ops); @@ -130,7 +130,7 @@ static int perl_start_script_unsupported(const char *script __maybe_unused, return -1; } -static int perl_generate_script_unsupported(struct pevent *pevent +static int perl_generate_script_unsupported(struct tep_handle *pevent __maybe_unused, const char *outfile __maybe_unused) { @@ -161,7 +161,7 @@ static void register_perl_scripting(struct scripting_ops *scripting_ops) } } -#ifdef NO_LIBPERL +#ifndef HAVE_LIBPERL_SUPPORT void setup_perl_scripting(void) { register_perl_scripting(&perl_scripting_unsupported_ops); diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c index 16a776371d03..58bb72f266f3 100644 --- a/tools/perf/util/trace-event.c +++ b/tools/perf/util/trace-event.c @@ -28,10 +28,10 @@ static bool tevent_initialized; int trace_event__init(struct trace_event *t) { - struct pevent *pevent = pevent_alloc(); + struct tep_handle *pevent = tep_alloc(); if (pevent) { - t->plugin_list = traceevent_load_plugins(pevent); + t->plugin_list = tep_load_plugins(pevent); t->pevent = pevent; } @@ -40,33 +40,33 @@ int trace_event__init(struct trace_event *t) static int trace_event__init2(void) { - int be = traceevent_host_bigendian(); - struct pevent *pevent; + int be = tep_host_bigendian(); + struct tep_handle *pevent; if (trace_event__init(&tevent)) return -1; pevent = tevent.pevent; - pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT); - pevent_set_file_bigendian(pevent, be); - pevent_set_host_bigendian(pevent, be); + tep_set_flag(pevent, TEP_NSEC_OUTPUT); + tep_set_file_bigendian(pevent, be); + tep_set_host_bigendian(pevent, be); tevent_initialized = true; return 0; } int trace_event__register_resolver(struct machine *machine, - pevent_func_resolver_t *func) + tep_func_resolver_t *func) { if (!tevent_initialized && trace_event__init2()) return -1; - return pevent_set_function_resolver(tevent.pevent, func, machine); + return tep_set_function_resolver(tevent.pevent, func, machine); } void trace_event__cleanup(struct trace_event *t) { - traceevent_unload_plugins(t->plugin_list, t->pevent); - pevent_free(t->pevent); + tep_unload_plugins(t->plugin_list, t->pevent); + tep_free(t->pevent); } /* @@ -75,21 +75,25 @@ void trace_event__cleanup(struct trace_event *t) static struct event_format* tp_format(const char *sys, const char *name) { - struct pevent *pevent = tevent.pevent; + char *tp_dir = get_events_file(sys); + struct tep_handle *pevent = tevent.pevent; struct event_format *event = NULL; char path[PATH_MAX]; size_t size; char *data; int err; - scnprintf(path, PATH_MAX, "%s/%s/%s/format", - tracing_events_path, sys, name); + if (!tp_dir) + return ERR_PTR(-errno); + + scnprintf(path, PATH_MAX, "%s/%s/format", tp_dir, name); + put_events_file(tp_dir); err = filename__read_str(path, &data, &size); if (err) return ERR_PTR(err); - pevent_parse_format(pevent, &event, data, size, sys); + tep_parse_format(pevent, &event, data, size, sys); free(data); return event; @@ -112,5 +116,5 @@ struct event_format *trace_event__tp_format_id(int id) if (!tevent_initialized && trace_event__init2()) return ERR_PTR(-ENOMEM); - return pevent_find_event(tevent.pevent, id); + return tep_find_event(tevent.pevent, id); } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index dcbdb53dc702..40204ec3a7a2 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -13,14 +13,14 @@ struct thread; struct plugin_list; struct trace_event { - struct pevent *pevent; + struct tep_handle *pevent; struct plugin_list *plugin_list; }; int trace_event__init(struct trace_event *t); void trace_event__cleanup(struct trace_event *t); int trace_event__register_resolver(struct machine *machine, - pevent_func_resolver_t *func); + tep_func_resolver_t *func); struct event_format* trace_event__tp_format(const char *sys, const char *name); @@ -34,20 +34,20 @@ void event_format__fprintf(struct event_format *event, void event_format__print(struct event_format *event, int cpu, void *data, int size); -int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size); -int parse_event_file(struct pevent *pevent, +int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size); +int parse_event_file(struct tep_handle *pevent, char *buf, unsigned long size, char *sys); unsigned long long raw_field_value(struct event_format *event, const char *name, void *data); -void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size); -void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size); -void parse_saved_cmdline(struct pevent *pevent, char *file, unsigned int size); +void parse_proc_kallsyms(struct tep_handle *pevent, char *file, unsigned int size); +void parse_ftrace_printk(struct tep_handle *pevent, char *file, unsigned int size); +void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int size); ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe); -struct event_format *trace_find_next_event(struct pevent *pevent, +struct event_format *trace_find_next_event(struct tep_handle *pevent, struct event_format *event); unsigned long long read_size(struct event_format *event, void *ptr, int size); unsigned long long eval_flag(const char *flag); @@ -83,7 +83,7 @@ struct scripting_ops { void (*process_stat)(struct perf_stat_config *config, struct perf_evsel *evsel, u64 tstamp); void (*process_stat_interval)(u64 tstamp); - int (*generate_script) (struct pevent *pevent, const char *outfile); + int (*generate_script) (struct tep_handle *pevent, const char *outfile); }; extern unsigned int scripting_max_stack; @@ -94,7 +94,7 @@ void setup_perl_scripting(void); void setup_python_scripting(void); struct scripting_context { - struct pevent *pevent; + struct tep_handle *pevent; void *event_data; }; diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 1e9c974faf67..6f318b15950e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -28,10 +28,11 @@ static int __report_module(struct addr_location *al, u64 ip, { Dwfl_Module *mod; struct dso *dso = NULL; - - thread__find_addr_location(ui->thread, - PERF_RECORD_MISC_USER, - MAP__FUNCTION, ip, al); + /* + * Some callers will use al->sym, so we can't just use the + * cheaper thread__find_map() here. + */ + thread__find_symbol(ui->thread, PERF_RECORD_MISC_USER, ip, al); if (al->map) dso = al->map->dso; @@ -50,7 +51,7 @@ static int __report_module(struct addr_location *al, u64 ip, if (!mod) mod = dwfl_report_elf(ui->dwfl, dso->short_name, - dso->long_name, -1, al->map->start, + (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start, false); return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1; @@ -76,7 +77,7 @@ static int entry(u64 ip, struct unwind_info *ui) if (__report_module(&al, ip, ui)) return -1; - e->ip = al.addr; + e->ip = ip; e->map = al.map; e->sym = al.sym; @@ -103,19 +104,7 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, struct addr_location al; ssize_t size; - thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__FUNCTION, addr, &al); - if (!al.map) { - /* - * We've seen cases (softice) where DWARF unwinder went - * through non executable mmaps, which we need to lookup - * in MAP__VARIABLE tree. - */ - thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__VARIABLE, addr, &al); - } - - if (!al.map) { + if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, addr, &al)) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); return -1; } @@ -236,7 +225,8 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, if (err) goto out; - if (!dwfl_attach_state(ui->dwfl, EM_NONE, thread->tid, &callbacks, ui)) + err = !dwfl_attach_state(ui->dwfl, EM_NONE, thread->tid, &callbacks, ui); + if (err) goto out; err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui); diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index af873044d33a..79f521a552cf 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -366,19 +366,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso, static struct map *find_map(unw_word_t ip, struct unwind_info *ui) { struct addr_location al; - - thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__FUNCTION, ip, &al); - if (!al.map) { - /* - * We've seen cases (softice) where DWARF unwinder went - * through non executable mmaps, which we need to lookup - * in MAP__VARIABLE tree. - */ - thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__VARIABLE, ip, &al); - } - return al.map; + return thread__find_map(ui->thread, PERF_RECORD_MISC_USER, ip, &al); } static int @@ -586,12 +574,9 @@ static int entry(u64 ip, struct thread *thread, struct unwind_entry e; struct addr_location al; - thread__find_addr_location(thread, PERF_RECORD_MISC_USER, - MAP__FUNCTION, ip, &al); - - e.ip = al.addr; + e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); + e.ip = ip; e.map = al.map; - e.sym = al.sym; pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", al.sym ? al.sym->name : "''", diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 1019bbc5dbd8..eac5b858a371 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -38,11 +38,43 @@ void perf_set_multithreaded(void) } unsigned int page_size; -int cacheline_size; + +#ifdef _SC_LEVEL1_DCACHE_LINESIZE +#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE) +#else +static void cache_line_size(int *cacheline_sizep) +{ + if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep)) + pr_debug("cannot determine cache line size"); +} +#endif + +int cacheline_size(void) +{ + static int size; + + if (!size) + cache_line_size(&size); + + return size; +} int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH; int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK; +int sysctl__max_stack(void) +{ + int value; + + if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0) + sysctl_perf_event_max_stack = value; + + if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0) + sysctl_perf_event_max_contexts_per_stack = value; + + return sysctl_perf_event_max_stack; +} + bool test_attr__enabled; bool perf_host = true; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 9496365da3d7..dc58254a2b69 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -11,8 +11,7 @@ #include <stdlib.h> #include <stdarg.h> #include <linux/compiler.h> -#include <linux/types.h> -#include "namespaces.h" +#include <sys/types.h> /* General helper functions */ void usage(const char *err) __noreturn; @@ -26,6 +25,7 @@ static inline void *zalloc(size_t size) #define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) struct dirent; +struct nsinfo; struct strlist; int mkdir_p(char *path, mode_t mode); @@ -43,7 +43,9 @@ size_t hex_width(u64 v); int hex2u64(const char *ptr, u64 *val); extern unsigned int page_size; -extern int cacheline_size; +int __pure cacheline_size(void); + +int sysctl__max_stack(void); int fetch_kernel_version(unsigned int *puint, char *str, size_t str_sz); diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 0acb1ec0e2f0..741af209b19d 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -139,12 +139,10 @@ static enum dso_type machine__thread_dso_type(struct machine *machine, struct thread *thread) { enum dso_type dso_type = DSO__TYPE_UNKNOWN; - struct map *map; - struct dso *dso; + struct map *map = map_groups__first(thread->mg); - map = map_groups__first(thread->mg, MAP__FUNCTION); for (; map ; map = map_groups__next(map)) { - dso = map->dso; + struct dso *dso = map->dso; if (!dso || dso->long_name[0] != '/') continue; dso_type = dso__type(dso, machine); diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c index a725b958cf31..902ce6384f57 100644 --- a/tools/perf/util/zlib.c +++ b/tools/perf/util/zlib.c @@ -5,6 +5,8 @@ #include <sys/stat.h> #include <sys/mman.h> #include <zlib.h> +#include <linux/compiler.h> +#include <unistd.h> #include "util/compress.h" #include "util/util.h" @@ -79,3 +81,19 @@ out_close: return ret == Z_STREAM_END ? 0 : -1; } + +bool gzip_is_compressed(const char *input) +{ + int fd = open(input, O_RDONLY); + const uint8_t magic[2] = { 0x1f, 0x8b }; + char buf[2] = { 0 }; + ssize_t rc; + + if (fd < 0) + return -1; + + rc = read(fd, buf, sizeof(buf)); + close(fd); + return rc == sizeof(buf) ? + memcmp(buf, magic, sizeof(buf)) == 0 : false; +} |
