diff options
Diffstat (limited to 'tools/perf')
221 files changed, 15392 insertions, 5048 deletions
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index 8f8fbc227a4..782d86e961b 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -13,6 +13,7 @@ perf*.html common-cmds.h perf.data perf.data.old +output.svg perf-archive tags TAGS diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index 5a37a7c84e6..3ba1c0b0990 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -145,16 +145,17 @@ endif ifneq ($(findstring $(MAKEFLAGS),s),s) ifneq ($(V),1) - QUIET_ASCIIDOC = @echo ' ' ASCIIDOC $@; - QUIET_XMLTO = @echo ' ' XMLTO $@; - QUIET_DB2TEXI = @echo ' ' DB2TEXI $@; - QUIET_MAKEINFO = @echo ' ' MAKEINFO $@; - QUIET_DBLATEX = @echo ' ' DBLATEX $@; - QUIET_XSLTPROC = @echo ' ' XSLTPROC $@; - QUIET_GEN = @echo ' ' GEN $@; + QUIET_ASCIIDOC = @echo ' ASCIIDOC '$@; + QUIET_XMLTO = @echo ' XMLTO '$@; + QUIET_DB2TEXI = @echo ' DB2TEXI '$@; + QUIET_MAKEINFO = @echo ' MAKEINFO '$@; + QUIET_DBLATEX = @echo ' DBLATEX '$@; + QUIET_XSLTPROC = @echo ' XSLTPROC '$@; + QUIET_GEN = @echo ' GEN '$@; QUIET_STDERR = 2> /dev/null QUIET_SUBDIR0 = +@subdir= - QUIET_SUBDIR1 = ;$(NO_SUBDIR) echo ' ' SUBDIR $$subdir; \ + QUIET_SUBDIR1 = ;$(NO_SUBDIR) \ + echo ' SUBDIR ' $$subdir; \ $(MAKE) $(PRINT_DIR) -C $$subdir export V endif @@ -183,47 +184,43 @@ ifdef missing_tools endif do-install-man: man - $(INSTALL) -d -m 755 $(DESTDIR)$(man1dir) -# $(INSTALL) -d -m 755 $(DESTDIR)$(man5dir) -# $(INSTALL) -d -m 755 $(DESTDIR)$(man7dir) - $(INSTALL) -m 644 $(DOC_MAN1) $(DESTDIR)$(man1dir) -# $(INSTALL) -m 644 $(DOC_MAN5) $(DESTDIR)$(man5dir) -# $(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir) + $(call QUIET_INSTALL, Documentation-man) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(man1dir); \ +# $(INSTALL) -d -m 755 $(DESTDIR)$(man5dir); \ +# $(INSTALL) -d -m 755 $(DESTDIR)$(man7dir); \ + $(INSTALL) -m 644 $(DOC_MAN1) $(DESTDIR)$(man1dir); \ +# $(INSTALL) -m 644 $(DOC_MAN5) $(DESTDIR)$(man5dir); \ +# $(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir) install-man: check-man-tools man -try-install-man: ifdef missing_tools - $(warning Please install $(missing_tools) to have the man pages installed) + DO_INSTALL_MAN = $(warning Please install $(missing_tools) to have the man pages installed) else - $(MAKE) do-install-man + DO_INSTALL_MAN = do-install-man endif +try-install-man: $(DO_INSTALL_MAN) + install-info: info - $(INSTALL) -d -m 755 $(DESTDIR)$(infodir) - $(INSTALL) -m 644 $(OUTPUT)perf.info $(OUTPUT)perfman.info $(DESTDIR)$(infodir) + $(call QUIET_INSTALL, Documentation-info) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(infodir); \ + $(INSTALL) -m 644 $(OUTPUT)perf.info $(OUTPUT)perfman.info $(DESTDIR)$(infodir); \ if test -r $(DESTDIR)$(infodir)/dir; then \ - $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perf.info ;\ - $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perfman.info ;\ + $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perf.info ;\ + $(INSTALL_INFO) --info-dir=$(DESTDIR)$(infodir) perfman.info ;\ else \ echo "No directory found in $(DESTDIR)$(infodir)" >&2 ; \ fi install-pdf: pdf - $(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir) - $(INSTALL) -m 644 $(OUTPUT)user-manual.pdf $(DESTDIR)$(pdfdir) + $(call QUIET_INSTALL, Documentation-pdf) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir); \ + $(INSTALL) -m 644 $(OUTPUT)user-manual.pdf $(DESTDIR)$(pdfdir) #install-html: html # '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir) -ifneq ($(MAKECMDGOALS),clean) -ifneq ($(MAKECMDGOALS),tags) -$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE - $(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) $(OUTPUT)PERF-VERSION-FILE - --include $(OUTPUT)PERF-VERSION-FILE -endif -endif # # Determine "include::" file references in asciidoc files. @@ -253,15 +250,17 @@ $(OUTPUT)cmd-list.made: cmd-list.perl ../command-list.txt $(MAN1_TXT) $(PERL_PATH) ./cmd-list.perl ../command-list.txt $(QUIET_STDERR) && \ date >$@ +CLEAN_FILES = \ + $(MAN_XML) $(addsuffix +,$(MAN_XML)) \ + $(MAN_HTML) $(addsuffix +,$(MAN_HTML)) \ + $(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7) \ + $(OUTPUT)*.texi $(OUTPUT)*.texi+ $(OUTPUT)*.texi++ \ + $(OUTPUT)perf.info $(OUTPUT)perfman.info \ + $(OUTPUT)howto-index.txt $(OUTPUT)howto/*.html $(OUTPUT)doc.dep \ + $(OUTPUT)technical/api-*.html $(OUTPUT)technical/api-index.txt \ + $(cmds_txt) $(OUTPUT)*.made clean: - $(RM) $(MAN_XML) $(addsuffix +,$(MAN_XML)) - $(RM) $(MAN_HTML) $(addsuffix +,$(MAN_HTML)) - $(RM) $(DOC_HTML) $(DOC_MAN1) $(DOC_MAN5) $(DOC_MAN7) - $(RM) $(OUTPUT)*.texi $(OUTPUT)*.texi+ $(OUTPUT)*.texi++ - $(RM) $(OUTPUT)perf.info $(OUTPUT)perfman.info - $(RM) $(OUTPUT)howto-index.txt $(OUTPUT)howto/*.html $(OUTPUT)doc.dep - $(RM) $(OUTPUT)technical/api-*.html $(OUTPUT)technical/api-index.txt - $(RM) $(cmds_txt) $(OUTPUT)*.made + $(call QUIET_CLEAN, Documentation) $(RM) $(CLEAN_FILES) $(MAN_HTML): $(OUTPUT)%.html : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ @@ -342,5 +341,3 @@ $(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt #quick-install-html: # '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir) - -.PHONY: .FORCE-PERF-VERSION-FILE diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index e9a8349a717..fd77d81ea74 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -21,6 +21,19 @@ OPTIONS -a:: --add=:: Add specified file to the cache. +-k:: +--kcore:: + Add specified kcore file to the cache. For the current host that is + /proc/kcore which requires root permissions to read. Be aware that + running 'perf buildid-cache' as root may update root's build-id cache + not the user's. Use the -v option to see where the file is created. + Note that the copied file contains only code sections not the whole core + image. Note also that files "kallsyms" and "modules" must also be in the + same directory and are also copied. All 3 files are created with read + permissions for root only. kcore will not be added if there is already a + kcore in the cache (with the same build-id) that has the same modules at + the same addresses. Use the -v option to see if a copy of kcore is + actually made. -r:: --remove=:: Remove specified file from the cache. diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index 5b3123d5721..fdfceee0ffd 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -3,17 +3,17 @@ perf-diff(1) NAME ---- -perf-diff - Read two perf.data files and display the differential profile +perf-diff - Read perf.data files and display the differential profile SYNOPSIS -------- [verse] -'perf diff' [oldfile] [newfile] +'perf diff' [baseline file] [data file1] [[data file2] ... ] DESCRIPTION ----------- -This command displays the performance difference amongst two perf.data files -captured via perf record. +This command displays the performance difference amongst two or more perf.data +files captured via perf record. If no parameters are passed it will assume perf.data.old and perf.data. @@ -75,8 +75,6 @@ OPTIONS -c:: --compute:: Differential computation selection - delta,ratio,wdiff (default is delta). - If '+' is specified as a first character, the output is sorted based - on the computation results. See COMPARISON METHODS section for more info. -p:: @@ -87,6 +85,63 @@ OPTIONS --formula:: Show formula for given computation. +-o:: +--order:: + Specify compute sorting column number. + +COMPARISON +---------- +The comparison is governed by the baseline file. The baseline perf.data +file is iterated for samples. All other perf.data files specified on +the command line are searched for the baseline sample pair. If the pair +is found, specified computation is made and result is displayed. + +All samples from non-baseline perf.data files, that do not match any +baseline entry, are displayed with empty space within baseline column +and possible computation results (delta) in their related column. + +Example files samples: +- file A with samples f1, f2, f3, f4, f6 +- file B with samples f2, f4, f5 +- file C with samples f1, f2, f5 + +Example output: + x - computation takes place for pair + b - baseline sample percentage + +- perf diff A B C + + baseline/A compute/B compute/C samples + --------------------------------------- + b x f1 + b x x f2 + b f3 + b x f4 + b f6 + x x f5 + +- perf diff B A C + + baseline/B compute/A compute/C samples + --------------------------------------- + b x x f2 + b x f4 + b x f5 + x x f1 + x f3 + x f6 + +- perf diff C B A + + baseline/C compute/B compute/A samples + --------------------------------------- + b x f1 + b x x f2 + b x f5 + x f3 + x x f4 + x f6 + COMPARISON METHODS ------------------ delta @@ -96,7 +151,7 @@ If specified the 'Delta' column is displayed with value 'd' computed as: d = A->period_percent - B->period_percent with: - - A/B being matching hist entry from first/second file specified + - A/B being matching hist entry from data/baseline file specified (or perf.data/perf.data.old) respectively. - period_percent being the % of the hist entry period value within @@ -109,24 +164,26 @@ If specified the 'Ratio' column is displayed with value 'r' computed as: r = A->period / B->period with: - - A/B being matching hist entry from first/second file specified + - A/B being matching hist entry from data/baseline file specified (or perf.data/perf.data.old) respectively. - period being the hist entry period value -wdiff -~~~~~ +wdiff:WEIGHT-B,WEIGHT-A +~~~~~~~~~~~~~~~~~~~~~~~ If specified the 'Weighted diff' column is displayed with value 'd' computed as: d = B->period * WEIGHT-A - A->period * WEIGHT-B - - A/B being matching hist entry from first/second file specified + - A/B being matching hist entry from data/baseline file specified (or perf.data/perf.data.old) respectively. - period being the hist entry period value - WEIGHT-A/WEIGHT-B being user suplied weights in the the '-c' option behind ':' separator like '-c wdiff:1,2'. + - WIEGHT-A being the weight of the data file + - WIEGHT-B being the weight of the baseline data file SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt index 326f2cb333c..6a06cefe964 100644 --- a/tools/perf/Documentation/perf-kvm.txt +++ b/tools/perf/Documentation/perf-kvm.txt @@ -13,6 +13,7 @@ SYNOPSIS {top|record|report|diff|buildid-list} 'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path> | --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat} +'perf kvm stat [record|report|live] [<options>] DESCRIPTION ----------- @@ -50,6 +51,10 @@ There are a couple of variants of perf kvm: 'perf kvm stat report' reports statistical data which includes events handled time, samples, and so on. + 'perf kvm stat live' reports statistical data in a live mode (similar to + record + report but with statistical data updated live at a given display + rate). + OPTIONS ------- -i:: @@ -85,13 +90,52 @@ STAT REPORT OPTIONS --vcpu=<value>:: analyze events which occures on this vcpu. (default: all vcpus) ---events=<value>:: - events to be analyzed. Possible values: vmexit, mmio, ioport. +--event=<value>:: + event to be analyzed. Possible values: vmexit, mmio, ioport. (default: vmexit) -k:: --key=<value>:: Sorting key. Possible values: sample (default, sort by samples number), time (sort by average time). +-p:: +--pid=:: + Analyze events only for given process ID(s) (comma separated list). + +STAT LIVE OPTIONS +----------------- +-d:: +--display:: + Time in seconds between display updates + +-m:: +--mmap-pages=:: + Number of mmap data pages (must be a power of two) or size + specification with appended unit character - B/K/M/G. The + size is rounded up to have nearest pages power of two value. + +-a:: +--all-cpus:: + System-wide collection from all CPUs. + +-p:: +--pid=:: + Analyze events only for given process ID(s) (comma separated list). + +--vcpu=<value>:: + analyze events which occures on this vcpu. (default: all vcpus) + + +--event=<value>:: + event to be analyzed. Possible values: vmexit, mmio, ioport. + (default: vmexit) + +-k:: +--key=<value>:: + Sorting key. Possible values: sample (default, sort by samples + number), time (sort by average time). + +--duration=<value>:: + Show events other than HLT that take longer than duration usecs. SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index d1e39dc8c81..6fce6a62220 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -8,7 +8,7 @@ perf-list - List all symbolic event types SYNOPSIS -------- [verse] -'perf list' [hw|sw|cache|tracepoint|event_glob] +'perf list' [hw|sw|cache|tracepoint|pmu|event_glob] DESCRIPTION ----------- @@ -29,6 +29,8 @@ counted. The following modifiers exist: G - guest counting (in KVM guests) H - host counting (not in KVM guests) p - precise level + S - read sample value (PERF_SAMPLE_READ) + D - pin the event to the PMU The 'p' modifier can be used for specifying how precise the instruction address should be. The 'p' modifier can be specified multiple times: @@ -104,6 +106,8 @@ To limit the list use: 'subsys_glob:event_glob' to filter by tracepoint subsystems such as sched, block, etc. +. 'pmu' to print the kernel supplied PMU events. + . If none of the above is matched, it will apply the supplied glob to all events, printing the ones that match. diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index c7f5f55634a..ab25be28c9d 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -48,7 +48,7 @@ REPORT OPTIONS -k:: --key=<value>:: Sorting key. Possible values: acquired (default), contended, - wait_total, wait_max, wait_min. + avg_wait, wait_total, wait_max, wait_min. INFO OPTIONS ------------ diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index e297b74471b..052f7c4dc00 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -87,11 +87,25 @@ OPTIONS -m:: --mmap-pages=:: - Number of mmap data pages. Must be a power of two. + Number of mmap data pages (must be a power of two) or size + specification with appended unit character - B/K/M/G. The + size is rounded up to have nearest pages power of two value. -g:: + Enables call-graph (stack chain/backtrace) recording. + --call-graph:: - Do call-graph (stack chain/backtrace) recording. + Setup and enable call-graph (stack chain/backtrace) recording, + implies -g. + + Allows specifying "fp" (frame pointer) or "dwarf" + (DWARF's CFI - Call Frame Information) as the method to collect + the information used to show the call graphs. + + In some systems, where binaries are build with gcc + --fomit-frame-pointer, using the "fp" method will produce bogus + call graphs, using "dwarf", if available (perf tools linked to + the libunwind library) should be used instead. -q:: --quiet:: @@ -166,6 +180,9 @@ following filters are defined: - u: only when the branch target is at the user level - k: only when the branch target is in the kernel - hv: only when the target is at the hypervisor level + - in_tx: only when the target is in a hardware transaction + - no_tx: only when the target is not in a hardware transaction + - abort_tx: only when the target is a hardware transaction abort + The option requires at least one branch type among any, any_call, any_ret, ind_call. @@ -176,12 +193,14 @@ is enabled for all the sampling events. The sampled branch type is the same for The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k Note that this feature may not be available on all processors. --W:: --weight:: Enable weightened sampling. An additional weight is recorded per sample and can be displayed with the weight and local_weight sort keys. This currently works for TSX abort events and some memory events in precise mode on modern Intel CPUs. +--transaction:: +Record transaction flags for transaction related events. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 66dab7410c1..10a27987125 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -71,7 +71,11 @@ OPTIONS entries are displayed as "[other]". - cpu: cpu number the task ran at the time of sample - srcline: filename and line number executed at the time of sample. The - DWARF debuggin info must be provided. + DWARF debugging info must be provided. + - weight: Event specific weight, e.g. memory latency or transaction + abort cost. This is the global weight. + - local_weight: Local weight version of the weight above. + - transaction: Transaction abort flags. By default, comm, dso and symbol keys are used. (i.e. --sort comm,dso,symbol) @@ -85,6 +89,8 @@ OPTIONS - symbol_from: name of function branched from - symbol_to: name of function branched to - mispredict: "N" for predicted branch, "Y" for mispredicted branch + - in_tx: branch in TSX transaction + - abort: TSX transaction abort. And default sort keys are changed to comm, dso_from, symbol_from, dso_to and symbol_to, see '--branch-stack'. @@ -115,7 +121,7 @@ OPTIONS --dump-raw-trace:: Dump raw trace in ASCII. --g [type,min[,limit],order]:: +-g [type,min[,limit],order[,key]]:: --call-graph:: Display call chains using type, min percent threshold, optional print limit and order. @@ -129,12 +135,29 @@ OPTIONS - callee: callee based call graph. - caller: inverted caller based call graph. - Default: fractal,0.5,callee. + key can be: + - function: compare on functions + - address: compare on individual code addresses + + Default: fractal,0.5,callee,function. + +--max-stack:: + Set the stack depth limit when parsing the callchain, anything + beyond the specified depth will be ignored. This is a trade-off + between information loss and faster processing especially for + workloads that can have a very long callchain stack. + + Default: 127 -G:: --inverted:: alias for inverted caller based call graph. +--ignore-callees=<regex>:: + Ignore callees of the function(s) matching the given regex. + This has the effect of collecting the callers of each such + function into one place in the call-graph tree. + --pretty=<key>:: Pretty printing style. key: normal, raw diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 2fe87fb558f..80c7da6732f 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -132,6 +132,16 @@ is a useful mode to detect imbalance between physical cores. To enable this mod use --per-core in addition to -a. (system-wide). The output includes the core number and the number of online logical processors on that physical processor. +-D msecs:: +--initial-delay msecs:: +After starting the program, wait msecs before measuring. This is useful to +filter out the startup phase of the program, which is often very different. + +-T:: +--transaction:: + +Print statistics of transactional execution if supported. + EXAMPLES -------- diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt index 1632b0efc75..3ff8bd4f0b4 100644 --- a/tools/perf/Documentation/perf-timechart.txt +++ b/tools/perf/Documentation/perf-timechart.txt @@ -8,7 +8,8 @@ perf-timechart - Tool to visualize total system behavior during a workload SYNOPSIS -------- [verse] -'perf timechart' {record} +'perf timechart' record <command> +'perf timechart' [<options>] DESCRIPTION ----------- @@ -41,6 +42,18 @@ OPTIONS --symfs=<directory>:: Look for files with symbols relative to this directory. +EXAMPLES +-------- + +$ perf timechart record git pull + + [ perf record: Woken up 13 times to write data ] + [ perf record: Captured and wrote 4.253 MB perf.data (~185801 samples) ] + +$ perf timechart + + Written 10.2 seconds of trace to output.svg. + SEE ALSO -------- linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 7fdd1909e37..7de01dd7968 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -68,7 +68,9 @@ Default is to monitor all CPUS. -m <pages>:: --mmap-pages=<pages>:: - Number of mmapped data pages. + Number of mmap data pages (must be a power of two) or size + specification with appended unit character - B/K/M/G. The + size is rounded up to have nearest pages power of two value. -p <pid>:: --pid=<pid>:: @@ -112,7 +114,8 @@ Default is to monitor all CPUS. -s:: --sort:: - Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight, local_weight. + Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight, + local_weight, abort, in_tx, transaction -n:: --show-nr-samples:: @@ -140,20 +143,25 @@ Default is to monitor all CPUS. --asm-raw:: Show raw instruction encoding of assembly instructions. --G [type,min,order]:: +-G:: + Enables call-graph (stack chain/backtrace) recording. + --call-graph:: - Display call chains using type, min percent threshold and order. - type can be either: - - flat: single column, linear exposure of call chains. - - graph: use a graph tree, displaying absolute overhead rates. - - fractal: like graph, but displays relative rates. Each branch of - the tree is considered as a new profiled object. - - order can be either: - - callee: callee based call graph. - - caller: inverted caller based call graph. - - Default: fractal,0.5,callee. + Setup and enable call-graph (stack chain/backtrace) recording, + implies -G. + +--max-stack:: + Set the stack depth limit when parsing the callchain, anything + beyond the specified depth will be ignored. This is a trade-off + between information loss and faster processing especially for + workloads that can have a very long callchain stack. + + Default: 127 + +--ignore-callees=<regex>:: + Ignore callees of the function(s) matching the given regex. + This has the effect of collecting the callers of each such + function into one place in the call-graph tree. --percent-limit:: Do not show entries which have an overhead under that percent. diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 68718ccdd17..7b0497f95a7 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -9,6 +9,7 @@ SYNOPSIS -------- [verse] 'perf trace' +'perf trace record' DESCRIPTION ----------- @@ -16,32 +17,59 @@ This command will show the events associated with the target, initially syscalls, but other system events like pagefaults, task lifetime events, scheduling events, etc. -Initially this is a live mode only tool, but eventually will work with -perf.data files like the other tools, allowing a detached 'record' from -analysis phases. +This is a live mode tool in addition to working with perf.data files like +the other perf tools. Files can be generated using the 'perf record' command +but the session needs to include the raw_syscalls events (-e 'raw_syscalls:*'). +Alernatively, the 'perf trace record' can be used as a shortcut to +automatically include the raw_syscalls events when writing events to a file. + +The following options apply to perf trace; options to perf trace record are +found in the perf record man page. OPTIONS ------- +-a:: --all-cpus:: System-wide collection from all CPUs. +-e:: +--expr:: + List of events to show, currently only syscall names. + Prefixing with ! shows all syscalls but the ones specified. You may + need to escape it. + +-o:: +--output=:: + Output file name. + -p:: --pid=:: Record events on existing process ID (comma separated list). +-t:: --tid=:: Record events on existing thread ID (comma separated list). +-u:: --uid=:: Record events in threads owned by uid. Name or number. +-v:: +--verbose=:: + Verbosity level. + +-i:: --no-inherit:: Child tasks do not inherit counters. +-m:: --mmap-pages=:: - Number of mmap data pages. Must be a power of two. + Number of mmap data pages (must be a power of two) or size + specification with appended unit character - B/K/M/G. The + size is rounded up to have nearest pages power of two value. +-C:: --cpu:: Collect samples 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. @@ -54,6 +82,25 @@ 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. +-i +--input + Process events from a given perf data file. + +-T +--time + Print full timestamp rather time relative to first sample. + +--comm:: + Show process COMM right beside its ID, on by default, disable with --no-comm. + +--summary:: + Show a summary of syscalls by thread with min, max, and average times (in + msec) and relative stddev. + +--tool_stats:: + Show tool stats such as number of times fd->pathname was discovered thru + hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script[1] diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 641fccddb24..4835618a560 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -1,806 +1,79 @@ -include ../scripts/Makefile.include - -# The default target of this Makefile is... -all: - -include config/utilities.mak - -# Define V to have a more verbose compile. -# -# Define O to save output files in a separate directory. -# -# Define ARCH as name of target architecture if you want cross-builds. -# -# Define CROSS_COMPILE as prefix name of compiler if you want cross-builds. -# -# Define NO_LIBPERL to disable perl script extension. -# -# Define NO_LIBPYTHON to disable python script extension. -# -# Define PYTHON to point to the python binary if the default -# `python' is not correct; for example: PYTHON=python2 -# -# Define PYTHON_CONFIG to point to the python-config binary if -# the default `$(PYTHON)-config' is not correct. # -# Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8 +# This is a simple wrapper Makefile that calls the main Makefile.perf +# with a -j option to do parallel builds # -# Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72. +# If you want to invoke the perf build in some non-standard way then +# you can use the 'make -f Makefile.perf' method to invoke it. # -# Define LDFLAGS=-static to build a static binary. -# -# Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds. -# -# Define NO_DWARF if you do not want debug-info analysis feature at all. -# -# Define WERROR=0 to disable treating any warnings as errors. -# -# Define NO_NEWT if you do not want TUI support. (deprecated) -# -# Define NO_SLANG if you do not want TUI support. -# -# Define NO_GTK2 if you do not want GTK+ GUI support. + # -# Define NO_DEMANGLE if you do not want C++ symbol demangling. +# Clear out the built-in rules GNU make defines by default (such as .o targets), +# so that we pass through all targets to Makefile.perf: # -# Define NO_LIBELF if you do not want libelf dependency (e.g. cross-builds) +.SUFFIXES: + # -# Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf -# backtrace post unwind. +# We don't want to pass along options like -j: # -# Define NO_BACKTRACE if you do not want stack backtrace debug feature +unexport MAKEFLAGS + # -# Define NO_LIBNUMA if you do not want numa perf benchmark +# Do a parallel build with multiple jobs, based on the number of CPUs online +# in this system: 'make -j8' on a 8-CPU system, etc. # -# Define NO_LIBAUDIT if you do not want libaudit support +# (To override it, run 'make JOBS=1' and similar.) # -# Define NO_LIBBIONIC if you do not want bionic support - -ifeq ($(srctree),) -srctree := $(patsubst %/,%,$(dir $(shell pwd))) -srctree := $(patsubst %/,%,$(dir $(srctree))) -#$(info Determined 'srctree' to be $(srctree)) -endif - -ifneq ($(objtree),) -#$(info Determined 'objtree' to be $(objtree)) -endif - -ifneq ($(OUTPUT),) -#$(info Determined 'OUTPUT' to be $(OUTPUT)) -endif - -$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE - @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) - -CC = $(CROSS_COMPILE)gcc -AR = $(CROSS_COMPILE)ar - -RM = rm -f -MKDIR = mkdir -FIND = find -INSTALL = install -FLEX = flex -BISON = bison -STRIP = strip - -LK_DIR = $(srctree)/tools/lib/lk/ -TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/ - -# include config/Makefile by default and rule out -# non-config cases -config := 1 - -NON_CONFIG_TARGETS := clean TAGS tags cscope help - -ifdef MAKECMDGOALS -ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),) - config := 0 -endif +ifeq ($(JOBS),) + JOBS := $(shell grep -c ^processor /proc/cpuinfo 2>/dev/null) + ifeq ($(JOBS),) + JOBS := 1 + endif endif -ifeq ($(config),1) -include config/Makefile +# +# Only pass canonical directory names as the output directory: +# +ifneq ($(O),) + FULL_O := $(shell readlink -f $(O) || echo $(O)) endif -export prefix bindir sharedir sysconfdir - -# sparse is architecture-neutral, which means that we need to tell it -# explicitly what architecture to check for. Fix this up for yours.. -SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ - -# Guard against environment variables -BUILTIN_OBJS = -LIB_H = -LIB_OBJS = -PYRF_OBJS = -SCRIPT_SH = - -SCRIPT_SH += perf-archive.sh - -grep-libs = $(filter -l%,$(1)) -strip-libs = $(filter-out -l%,$(1)) - -ifneq ($(OUTPUT),) - TE_PATH=$(OUTPUT) -ifneq ($(subdir),) - LK_PATH=$(objtree)/lib/lk/ -else - LK_PATH=$(OUTPUT) -endif +# +# Only accept the 'DEBUG' variable from the command line: +# +ifeq ("$(origin DEBUG)", "command line") + ifeq ($(DEBUG),) + override DEBUG = 0 + else + SET_DEBUG = "DEBUG=$(DEBUG)" + endif else - TE_PATH=$(TRACE_EVENT_DIR) - LK_PATH=$(LK_DIR) + override DEBUG = 0 endif -LIBTRACEEVENT = $(TE_PATH)libtraceevent.a -export LIBTRACEEVENT - -LIBLK = $(LK_PATH)liblk.a -export LIBLK +define print_msg + @printf ' BUILD: Doing '\''make \033[33m-j'$(JOBS)'\033[m'\'' parallel build\n' +endef -# python extension build directories -PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/ -PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/ -PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/ -export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP +define make + @$(MAKE) -f Makefile.perf --no-print-directory -j$(JOBS) O=$(FULL_O) $(SET_DEBUG) $@ +endef -python-clean := rm -rf $(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) $(LIBLK) - -$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) - $(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \ - --quiet build_ext; \ - mkdir -p $(OUTPUT)python && \ - cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/ # -# No Perl scripts right now: +# Needed if no target specified: # - -SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) +all: + $(print_msg) + $(make) # -# Single 'perf' binary right now: +# The clean target is not really parallel, don't print the jobs info: # -PROGRAMS += $(OUTPUT)perf - -# what 'all' will build and 'install' will install, in perfexecdir -ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS) - -# what 'all' will build but not install in perfexecdir -OTHER_PROGRAMS = $(OUTPUT)perf - -# Set paths to tools early so that they can be used for version tests. -ifndef SHELL_PATH - SHELL_PATH = /bin/sh -endif -ifndef PERL_PATH - PERL_PATH = /usr/bin/perl -endif - -export PERL_PATH - -$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c - $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c - -$(OUTPUT)util/parse-events-bison.c: util/parse-events.y - $(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c -p parse_events_ - -$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c - $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c - -$(OUTPUT)util/pmu-bison.c: util/pmu.y - $(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c -p perf_pmu_ - -$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c -$(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c - -LIB_FILE=$(OUTPUT)libperf.a +clean: + $(make) -LIB_H += ../../include/uapi/linux/perf_event.h -LIB_H += ../../include/linux/rbtree.h -LIB_H += ../../include/linux/list.h -LIB_H += ../../include/uapi/linux/const.h -LIB_H += ../../include/linux/hash.h -LIB_H += ../../include/linux/stringify.h -LIB_H += util/include/linux/bitmap.h -LIB_H += util/include/linux/bitops.h -LIB_H += util/include/linux/compiler.h -LIB_H += util/include/linux/const.h -LIB_H += util/include/linux/ctype.h -LIB_H += util/include/linux/kernel.h -LIB_H += util/include/linux/list.h -LIB_H += util/include/linux/export.h -LIB_H += util/include/linux/magic.h -LIB_H += util/include/linux/poison.h -LIB_H += util/include/linux/prefetch.h -LIB_H += util/include/linux/rbtree.h -LIB_H += util/include/linux/rbtree_augmented.h -LIB_H += util/include/linux/string.h -LIB_H += util/include/linux/types.h -LIB_H += util/include/linux/linkage.h -LIB_H += util/include/asm/asm-offsets.h -LIB_H += util/include/asm/bug.h -LIB_H += util/include/asm/byteorder.h -LIB_H += util/include/asm/hweight.h -LIB_H += util/include/asm/swab.h -LIB_H += util/include/asm/system.h -LIB_H += util/include/asm/uaccess.h -LIB_H += util/include/dwarf-regs.h -LIB_H += util/include/asm/dwarf2.h -LIB_H += util/include/asm/cpufeature.h -LIB_H += util/include/asm/unistd_32.h -LIB_H += util/include/asm/unistd_64.h -LIB_H += perf.h -LIB_H += util/annotate.h -LIB_H += util/cache.h -LIB_H += util/callchain.h -LIB_H += util/build-id.h -LIB_H += util/debug.h -LIB_H += util/sysfs.h -LIB_H += util/pmu.h -LIB_H += util/event.h -LIB_H += util/evsel.h -LIB_H += util/evlist.h -LIB_H += util/exec_cmd.h -LIB_H += util/types.h -LIB_H += util/levenshtein.h -LIB_H += util/machine.h -LIB_H += util/map.h -LIB_H += util/parse-options.h -LIB_H += util/parse-events.h -LIB_H += util/quote.h -LIB_H += util/util.h -LIB_H += util/xyarray.h -LIB_H += util/header.h -LIB_H += util/help.h -LIB_H += util/session.h -LIB_H += util/strbuf.h -LIB_H += util/strlist.h -LIB_H += util/strfilter.h -LIB_H += util/svghelper.h -LIB_H += util/tool.h -LIB_H += util/run-command.h -LIB_H += util/sigchain.h -LIB_H += util/dso.h -LIB_H += util/symbol.h -LIB_H += util/color.h -LIB_H += util/values.h -LIB_H += util/sort.h -LIB_H += util/hist.h -LIB_H += util/thread.h -LIB_H += util/thread_map.h -LIB_H += util/trace-event.h -LIB_H += util/probe-finder.h -LIB_H += util/dwarf-aux.h -LIB_H += util/probe-event.h -LIB_H += util/pstack.h -LIB_H += util/cpumap.h -LIB_H += util/top.h -LIB_H += $(ARCH_INCLUDE) -LIB_H += util/cgroup.h -LIB_H += $(TRACE_EVENT_DIR)event-parse.h -LIB_H += util/target.h -LIB_H += util/rblist.h -LIB_H += util/intlist.h -LIB_H += util/perf_regs.h -LIB_H += util/unwind.h -LIB_H += util/vdso.h -LIB_H += ui/helpline.h -LIB_H += ui/progress.h -LIB_H += ui/util.h -LIB_H += ui/ui.h - -LIB_OBJS += $(OUTPUT)util/abspath.o -LIB_OBJS += $(OUTPUT)util/alias.o -LIB_OBJS += $(OUTPUT)util/annotate.o -LIB_OBJS += $(OUTPUT)util/build-id.o -LIB_OBJS += $(OUTPUT)util/config.o -LIB_OBJS += $(OUTPUT)util/ctype.o -LIB_OBJS += $(OUTPUT)util/sysfs.o -LIB_OBJS += $(OUTPUT)util/pmu.o -LIB_OBJS += $(OUTPUT)util/environment.o -LIB_OBJS += $(OUTPUT)util/event.o -LIB_OBJS += $(OUTPUT)util/evlist.o -LIB_OBJS += $(OUTPUT)util/evsel.o -LIB_OBJS += $(OUTPUT)util/exec_cmd.o -LIB_OBJS += $(OUTPUT)util/help.o -LIB_OBJS += $(OUTPUT)util/levenshtein.o -LIB_OBJS += $(OUTPUT)util/parse-options.o -LIB_OBJS += $(OUTPUT)util/parse-events.o -LIB_OBJS += $(OUTPUT)util/path.o -LIB_OBJS += $(OUTPUT)util/rbtree.o -LIB_OBJS += $(OUTPUT)util/bitmap.o -LIB_OBJS += $(OUTPUT)util/hweight.o -LIB_OBJS += $(OUTPUT)util/run-command.o -LIB_OBJS += $(OUTPUT)util/quote.o -LIB_OBJS += $(OUTPUT)util/strbuf.o -LIB_OBJS += $(OUTPUT)util/string.o -LIB_OBJS += $(OUTPUT)util/strlist.o -LIB_OBJS += $(OUTPUT)util/strfilter.o -LIB_OBJS += $(OUTPUT)util/top.o -LIB_OBJS += $(OUTPUT)util/usage.o -LIB_OBJS += $(OUTPUT)util/wrapper.o -LIB_OBJS += $(OUTPUT)util/sigchain.o -LIB_OBJS += $(OUTPUT)util/dso.o -LIB_OBJS += $(OUTPUT)util/symbol.o -LIB_OBJS += $(OUTPUT)util/symbol-elf.o -LIB_OBJS += $(OUTPUT)util/color.o -LIB_OBJS += $(OUTPUT)util/pager.o -LIB_OBJS += $(OUTPUT)util/header.o -LIB_OBJS += $(OUTPUT)util/callchain.o -LIB_OBJS += $(OUTPUT)util/values.o -LIB_OBJS += $(OUTPUT)util/debug.o -LIB_OBJS += $(OUTPUT)util/machine.o -LIB_OBJS += $(OUTPUT)util/map.o -LIB_OBJS += $(OUTPUT)util/pstack.o -LIB_OBJS += $(OUTPUT)util/session.o -LIB_OBJS += $(OUTPUT)util/thread.o -LIB_OBJS += $(OUTPUT)util/thread_map.o -LIB_OBJS += $(OUTPUT)util/trace-event-parse.o -LIB_OBJS += $(OUTPUT)util/parse-events-flex.o -LIB_OBJS += $(OUTPUT)util/parse-events-bison.o -LIB_OBJS += $(OUTPUT)util/pmu-flex.o -LIB_OBJS += $(OUTPUT)util/pmu-bison.o -LIB_OBJS += $(OUTPUT)util/trace-event-read.o -LIB_OBJS += $(OUTPUT)util/trace-event-info.o -LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o -LIB_OBJS += $(OUTPUT)util/svghelper.o -LIB_OBJS += $(OUTPUT)util/sort.o -LIB_OBJS += $(OUTPUT)util/hist.o -LIB_OBJS += $(OUTPUT)util/probe-event.o -LIB_OBJS += $(OUTPUT)util/util.o -LIB_OBJS += $(OUTPUT)util/xyarray.o -LIB_OBJS += $(OUTPUT)util/cpumap.o -LIB_OBJS += $(OUTPUT)util/cgroup.o -LIB_OBJS += $(OUTPUT)util/target.o -LIB_OBJS += $(OUTPUT)util/rblist.o -LIB_OBJS += $(OUTPUT)util/intlist.o -LIB_OBJS += $(OUTPUT)util/vdso.o -LIB_OBJS += $(OUTPUT)util/stat.o - -LIB_OBJS += $(OUTPUT)ui/setup.o -LIB_OBJS += $(OUTPUT)ui/helpline.o -LIB_OBJS += $(OUTPUT)ui/progress.o -LIB_OBJS += $(OUTPUT)ui/util.o -LIB_OBJS += $(OUTPUT)ui/hist.o -LIB_OBJS += $(OUTPUT)ui/stdio/hist.o - -LIB_OBJS += $(OUTPUT)arch/common.o - -LIB_OBJS += $(OUTPUT)tests/parse-events.o -LIB_OBJS += $(OUTPUT)tests/dso-data.o -LIB_OBJS += $(OUTPUT)tests/attr.o -LIB_OBJS += $(OUTPUT)tests/vmlinux-kallsyms.o -LIB_OBJS += $(OUTPUT)tests/open-syscall.o -LIB_OBJS += $(OUTPUT)tests/open-syscall-all-cpus.o -LIB_OBJS += $(OUTPUT)tests/open-syscall-tp-fields.o -LIB_OBJS += $(OUTPUT)tests/mmap-basic.o -LIB_OBJS += $(OUTPUT)tests/perf-record.o -LIB_OBJS += $(OUTPUT)tests/rdpmc.o -LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o -LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o -LIB_OBJS += $(OUTPUT)tests/pmu.o -LIB_OBJS += $(OUTPUT)tests/hists_link.o -LIB_OBJS += $(OUTPUT)tests/python-use.o -LIB_OBJS += $(OUTPUT)tests/bp_signal.o -LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o -LIB_OBJS += $(OUTPUT)tests/task-exit.o -LIB_OBJS += $(OUTPUT)tests/sw-clock.o - -BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o -BUILTIN_OBJS += $(OUTPUT)builtin-bench.o -# Benchmark modules -BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o -BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o -ifeq ($(RAW_ARCH),x86_64) -BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o -BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o -endif -BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o -BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o - -BUILTIN_OBJS += $(OUTPUT)builtin-diff.o -BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o -BUILTIN_OBJS += $(OUTPUT)builtin-help.o -BUILTIN_OBJS += $(OUTPUT)builtin-sched.o -BUILTIN_OBJS += $(OUTPUT)builtin-buildid-list.o -BUILTIN_OBJS += $(OUTPUT)builtin-buildid-cache.o -BUILTIN_OBJS += $(OUTPUT)builtin-list.o -BUILTIN_OBJS += $(OUTPUT)builtin-record.o -BUILTIN_OBJS += $(OUTPUT)builtin-report.o -BUILTIN_OBJS += $(OUTPUT)builtin-stat.o -BUILTIN_OBJS += $(OUTPUT)builtin-timechart.o -BUILTIN_OBJS += $(OUTPUT)builtin-top.o -BUILTIN_OBJS += $(OUTPUT)builtin-script.o -BUILTIN_OBJS += $(OUTPUT)builtin-probe.o -BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o -BUILTIN_OBJS += $(OUTPUT)builtin-lock.o -BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o -BUILTIN_OBJS += $(OUTPUT)builtin-inject.o -BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o -BUILTIN_OBJS += $(OUTPUT)builtin-mem.o - -PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT) - -# We choose to avoid "if .. else if .. else .. endif endif" -# because maintaining the nesting to match is a pain. If -# we had "elif" things would have been much nicer... - --include arch/$(ARCH)/Makefile - -ifneq ($(OUTPUT),) - CFLAGS += -I$(OUTPUT) -endif - -ifdef NO_LIBELF -EXTLIBS := $(filter-out -lelf,$(EXTLIBS)) - -# Remove ELF/DWARF dependent codes -LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS)) -LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS)) -LIB_OBJS := $(filter-out $(OUTPUT)util/probe-event.o,$(LIB_OBJS)) -LIB_OBJS := $(filter-out $(OUTPUT)util/probe-finder.o,$(LIB_OBJS)) - -BUILTIN_OBJS := $(filter-out $(OUTPUT)builtin-probe.o,$(BUILTIN_OBJS)) - -# Use minimal symbol handling -LIB_OBJS += $(OUTPUT)util/symbol-minimal.o - -else # NO_LIBELF -ifndef NO_DWARF - LIB_OBJS += $(OUTPUT)util/probe-finder.o - LIB_OBJS += $(OUTPUT)util/dwarf-aux.o -endif # NO_DWARF -endif # NO_LIBELF - -ifndef NO_LIBUNWIND - LIB_OBJS += $(OUTPUT)util/unwind.o -endif - -ifndef NO_LIBAUDIT - BUILTIN_OBJS += $(OUTPUT)builtin-trace.o -endif - -ifndef NO_SLANG - LIB_OBJS += $(OUTPUT)ui/browser.o - LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o - LIB_OBJS += $(OUTPUT)ui/browsers/hists.o - LIB_OBJS += $(OUTPUT)ui/browsers/map.o - LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o - LIB_OBJS += $(OUTPUT)ui/tui/setup.o - LIB_OBJS += $(OUTPUT)ui/tui/util.o - LIB_OBJS += $(OUTPUT)ui/tui/helpline.o - LIB_OBJS += $(OUTPUT)ui/tui/progress.o - LIB_H += ui/browser.h - LIB_H += ui/browsers/map.h - LIB_H += ui/keysyms.h - LIB_H += ui/libslang.h -endif - -ifndef NO_GTK2 - LIB_OBJS += $(OUTPUT)ui/gtk/browser.o - LIB_OBJS += $(OUTPUT)ui/gtk/hists.o - LIB_OBJS += $(OUTPUT)ui/gtk/setup.o - LIB_OBJS += $(OUTPUT)ui/gtk/util.o - LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o - LIB_OBJS += $(OUTPUT)ui/gtk/progress.o - LIB_OBJS += $(OUTPUT)ui/gtk/annotate.o -endif - -ifndef NO_LIBPERL - LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o - LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o -endif - -ifndef NO_LIBPYTHON - LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o - LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o -endif - -ifeq ($(NO_PERF_REGS),0) - ifeq ($(ARCH),x86) - LIB_H += arch/x86/include/perf_regs.h - endif -endif - -ifndef NO_LIBNUMA - BUILTIN_OBJS += $(OUTPUT)bench/numa.o -endif - -ifdef ASCIIDOC8 - export ASCIIDOC8 -endif - -LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group - -export INSTALL SHELL_PATH - -### Build rules - -SHELL = $(SHELL_PATH) - -all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS) - -please_set_SHELL_PATH_to_a_more_modern_shell: - @$$(:) - -shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell - -strip: $(PROGRAMS) $(OUTPUT)perf - $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf - -$(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -include $(OUTPUT)PERF-VERSION-FILE \ - '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ - $(CFLAGS) -c $(filter %.c,$^) -o $@ - -$(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OUTPUT)perf.o \ - $(BUILTIN_OBJS) $(LIBS) -o $@ - -$(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ - '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ - '-DPERF_MAN_PATH="$(mandir_SQ)"' \ - '-DPERF_INFO_PATH="$(infodir_SQ)"' $< - -$(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ - '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ - '-DPERF_MAN_PATH="$(mandir_SQ)"' \ - '-DPERF_INFO_PATH="$(infodir_SQ)"' $< - -$(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt - -$(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt) - $(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@ - -$(SCRIPTS) : % : %.sh - $(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@' - -# These can record PERF_VERSION -$(OUTPUT)perf.o perf.spec \ - $(SCRIPTS) \ - : $(OUTPUT)PERF-VERSION-FILE - -.SUFFIXES: -.SUFFIXES: .o .c .S .s - -# These two need to be here so that when O= is not used they take precedence -# over the general rule for .o - -$(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -w $< - -$(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $< - -$(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $< -$(OUTPUT)%.i: %.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $< -$(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -S $(CFLAGS) $< -$(OUTPUT)%.o: %.S - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $< -$(OUTPUT)%.s: %.S - $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $< - -$(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ - '-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \ - '-DPREFIX="$(prefix_SQ)"' \ - $< - -$(OUTPUT)tests/attr.o: tests/attr.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ - '-DBINDIR="$(bindir_SQ)"' -DPYTHON='"$(PYTHON_WORD)"' \ - $< - -$(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ - -DPYTHONPATH='"$(OUTPUT)python"' \ - -DPYTHON='"$(PYTHON_WORD)"' \ - $< - -$(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< - -$(OUTPUT)ui/browser.o: ui/browser.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< - -$(OUTPUT)ui/browsers/annotate.o: ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< - -$(OUTPUT)ui/browsers/hists.o: ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< - -$(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< - -$(OUTPUT)ui/browsers/scripts.o: ui/browsers/scripts.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< - -$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< - -$(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $< - -$(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< - -$(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< - -$(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< - -$(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< - -$(OUTPUT)perf-%: %.o $(PERFLIBS) - $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS) - -$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H) -$(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h) - -# we compile into subdirectories. if the target directory is not the source directory, they might not exists. So -# we depend the various files onto their directories. -DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h -$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS))) -# In the second step, we make a rule to actually create these directories -$(sort $(dir $(DIRECTORY_DEPS))): - $(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null - -$(LIB_FILE): $(LIB_OBJS) - $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS) - -# libtraceevent.a -$(LIBTRACEEVENT): - $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) libtraceevent.a - -$(LIBTRACEEVENT)-clean: - $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) clean - -# if subdir is set, we've been called from above so target has been built -# already -$(LIBLK): -ifeq ($(subdir),) - $(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) liblk.a -endif - -$(LIBLK)-clean: -ifeq ($(subdir),) - $(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) clean -endif - -help: - @echo 'Perf make targets:' - @echo ' doc - make *all* documentation (see below)' - @echo ' man - make manpage documentation (access with man <foo>)' - @echo ' html - make html documentation' - @echo ' info - make GNU info documentation (access with info <foo>)' - @echo ' pdf - make pdf documentation' - @echo ' TAGS - use etags to make tag information for source browsing' - @echo ' tags - use ctags to make tag information for source browsing' - @echo ' cscope - use cscope to make interactive browsing database' - @echo '' - @echo 'Perf install targets:' - @echo ' NOTE: documentation build requires asciidoc, xmlto packages to be installed' - @echo ' HINT: use "make prefix=<path> <install target>" to install to a particular' - @echo ' path like make prefix=/usr/local install install-doc' - @echo ' install - install compiled binaries' - @echo ' install-doc - install *all* documentation' - @echo ' install-man - install manpage documentation' - @echo ' install-html - install html documentation' - @echo ' install-info - install GNU info documentation' - @echo ' install-pdf - install pdf documentation' - @echo '' - @echo ' quick-install-doc - alias for quick-install-man' - @echo ' quick-install-man - install the documentation quickly' - @echo ' quick-install-html - install the html documentation quickly' - @echo '' - @echo 'Perf maintainer targets:' - @echo ' clean - clean all binary objects and build output' - - -DOC_TARGETS := doc man html info pdf - -INSTALL_DOC_TARGETS := $(patsubst %,install-%,$(DOC_TARGETS)) try-install-man -INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html - -# 'make doc' should call 'make -C Documentation all' -$(DOC_TARGETS): - $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all) - -TAGS: - $(RM) TAGS - $(FIND) . -name '*.[hcS]' -print | xargs etags -a - -tags: - $(RM) tags - $(FIND) . -name '*.[hcS]' -print | xargs ctags -a - -cscope: - $(RM) cscope* - $(FIND) . -name '*.[hcS]' -print | xargs cscope -b - -### Detect prefix changes -TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\ - $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ) - -$(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS - @FLAGS='$(TRACK_CFLAGS)'; \ - if test x"$$FLAGS" != x"`cat $(OUTPUT)PERF-CFLAGS 2>/dev/null`" ; then \ - echo 1>&2 " * new build flags or prefix"; \ - echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \ - fi - -### Testing rules - -# GNU make supports exporting all variables by "export" without parameters. -# However, the environment gets quite big, and some programs have problems -# with that. - -check: $(OUTPUT)common-cmds.h - if sparse; \ - then \ - for i in *.c */*.c; \ - do \ - sparse $(CFLAGS) $(SPARSE_FLAGS) $$i || exit; \ - done; \ - else \ - exit 1; \ - fi - -### Installation rules - -install-bin: all - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)' - $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)' - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace' - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin' - $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' - $(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace' - $(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl' - $(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin' - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace' - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin' - $(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace' - $(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python' - $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin' - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d' - $(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf' - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests' - $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests' - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr' - $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr' - -install: install-bin try-install-man - -install-python_ext: - $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)' - -# 'make install-doc' should call 'make -C Documentation install' -$(INSTALL_DOC_TARGETS): - $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:-doc=) - -### Cleaning rules - -clean: $(LIBTRACEEVENT)-clean $(LIBLK)-clean - $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) - $(RM) $(ALL_PROGRAMS) perf - $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* - $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean - $(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS - $(RM) $(OUTPUT)util/*-bison* - $(RM) $(OUTPUT)util/*-flex* - $(python-clean) - -.PHONY: all install clean strip $(LIBTRACEEVENT) $(LIBLK) -.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell -.PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS +# +# All other targets get passed through: +# +%: + $(print_msg) + $(make) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf new file mode 100644 index 00000000000..7fc8f179cae --- /dev/null +++ b/tools/perf/Makefile.perf @@ -0,0 +1,892 @@ +include ../scripts/Makefile.include + +# The default target of this Makefile is... +all: + +include config/utilities.mak + +# Define V to have a more verbose compile. +# +# Define O to save output files in a separate directory. +# +# Define ARCH as name of target architecture if you want cross-builds. +# +# Define CROSS_COMPILE as prefix name of compiler if you want cross-builds. +# +# Define NO_LIBPERL to disable perl script extension. +# +# Define NO_LIBPYTHON to disable python script extension. +# +# Define PYTHON to point to the python binary if the default +# `python' is not correct; for example: PYTHON=python2 +# +# Define PYTHON_CONFIG to point to the python-config binary if +# the default `$(PYTHON)-config' is not correct. +# +# Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8 +# +# Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72. +# +# Define LDFLAGS=-static to build a static binary. +# +# Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds. +# +# Define NO_DWARF if you do not want debug-info analysis feature at all. +# +# Define WERROR=0 to disable treating any warnings as errors. +# +# Define NO_NEWT if you do not want TUI support. (deprecated) +# +# Define NO_SLANG if you do not want TUI support. +# +# Define NO_GTK2 if you do not want GTK+ GUI support. +# +# Define NO_DEMANGLE if you do not want C++ symbol demangling. +# +# Define NO_LIBELF if you do not want libelf dependency (e.g. cross-builds) +# +# Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf +# backtrace post unwind. +# +# Define NO_BACKTRACE if you do not want stack backtrace debug feature +# +# Define NO_LIBNUMA if you do not want numa perf benchmark +# +# Define NO_LIBAUDIT if you do not want libaudit support +# +# Define NO_LIBBIONIC if you do not want bionic support + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(shell pwd))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +ifneq ($(objtree),) +#$(info Determined 'objtree' to be $(objtree)) +endif + +ifneq ($(OUTPUT),) +#$(info Determined 'OUTPUT' to be $(OUTPUT)) +endif + +$(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD + @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) + @touch $(OUTPUT)PERF-VERSION-FILE + +CC = $(CROSS_COMPILE)gcc +AR = $(CROSS_COMPILE)ar + +RM = rm -f +LN = ln -f +MKDIR = mkdir +FIND = find +INSTALL = install +FLEX = flex +BISON = bison +STRIP = strip + +LK_DIR = $(srctree)/tools/lib/lk/ +TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/ + +# include config/Makefile by default and rule out +# non-config cases +config := 1 + +NON_CONFIG_TARGETS := clean TAGS tags cscope help + +ifdef MAKECMDGOALS +ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),) + config := 0 +endif +endif + +ifeq ($(config),1) +include config/Makefile +endif + +export prefix bindir sharedir sysconfdir + +# sparse is architecture-neutral, which means that we need to tell it +# explicitly what architecture to check for. Fix this up for yours.. +SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ + +# Guard against environment variables +BUILTIN_OBJS = +LIB_H = +LIB_OBJS = +GTK_OBJS = +PYRF_OBJS = +SCRIPT_SH = + +SCRIPT_SH += perf-archive.sh + +grep-libs = $(filter -l%,$(1)) +strip-libs = $(filter-out -l%,$(1)) + +ifneq ($(OUTPUT),) + TE_PATH=$(OUTPUT) +ifneq ($(subdir),) + LK_PATH=$(OUTPUT)/../lib/lk/ +else + LK_PATH=$(OUTPUT) +endif +else + TE_PATH=$(TRACE_EVENT_DIR) + LK_PATH=$(LK_DIR) +endif + +LIBTRACEEVENT = $(TE_PATH)libtraceevent.a +export LIBTRACEEVENT + +LIBLK = $(LK_PATH)liblk.a +export LIBLK + +# python extension build directories +PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/ +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_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources) +PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBLK) + +$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) + $(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \ + --quiet build_ext; \ + mkdir -p $(OUTPUT)python && \ + cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/ +# +# No Perl scripts right now: +# + +SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) + +# +# Single 'perf' binary right now: +# +PROGRAMS += $(OUTPUT)perf + +# what 'all' will build and 'install' will install, in perfexecdir +ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS) + +# what 'all' will build but not install in perfexecdir +OTHER_PROGRAMS = $(OUTPUT)perf + +# Set paths to tools early so that they can be used for version tests. +ifndef SHELL_PATH + SHELL_PATH = /bin/sh +endif +ifndef PERL_PATH + PERL_PATH = /usr/bin/perl +endif + +export PERL_PATH + +$(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c + $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c + +$(OUTPUT)util/parse-events-bison.c: util/parse-events.y + $(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c -p parse_events_ + +$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c + $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c + +$(OUTPUT)util/pmu-bison.c: util/pmu.y + $(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c -p perf_pmu_ + +$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c +$(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c + +LIB_FILE=$(OUTPUT)libperf.a + +LIB_H += ../../include/uapi/linux/perf_event.h +LIB_H += ../../include/linux/rbtree.h +LIB_H += ../../include/linux/list.h +LIB_H += ../../include/uapi/linux/const.h +LIB_H += ../../include/linux/hash.h +LIB_H += ../../include/linux/stringify.h +LIB_H += util/include/linux/bitmap.h +LIB_H += util/include/linux/bitops.h +LIB_H += util/include/linux/compiler.h +LIB_H += util/include/linux/const.h +LIB_H += util/include/linux/ctype.h +LIB_H += util/include/linux/kernel.h +LIB_H += util/include/linux/list.h +LIB_H += util/include/linux/export.h +LIB_H += util/include/linux/magic.h +LIB_H += util/include/linux/poison.h +LIB_H += util/include/linux/prefetch.h +LIB_H += util/include/linux/rbtree.h +LIB_H += util/include/linux/rbtree_augmented.h +LIB_H += util/include/linux/string.h +LIB_H += util/include/linux/types.h +LIB_H += util/include/linux/linkage.h +LIB_H += util/include/asm/asm-offsets.h +LIB_H += util/include/asm/bug.h +LIB_H += util/include/asm/byteorder.h +LIB_H += util/include/asm/hweight.h +LIB_H += util/include/asm/swab.h +LIB_H += util/include/asm/system.h +LIB_H += util/include/asm/uaccess.h +LIB_H += util/include/dwarf-regs.h +LIB_H += util/include/asm/dwarf2.h +LIB_H += util/include/asm/cpufeature.h +LIB_H += util/include/asm/unistd_32.h +LIB_H += util/include/asm/unistd_64.h +LIB_H += perf.h +LIB_H += util/annotate.h +LIB_H += util/cache.h +LIB_H += util/callchain.h +LIB_H += util/build-id.h +LIB_H += util/debug.h +LIB_H += util/fs.h +LIB_H += util/pmu.h +LIB_H += util/event.h +LIB_H += util/evsel.h +LIB_H += util/evlist.h +LIB_H += util/exec_cmd.h +LIB_H += util/types.h +LIB_H += util/levenshtein.h +LIB_H += util/machine.h +LIB_H += util/map.h +LIB_H += util/parse-options.h +LIB_H += util/parse-events.h +LIB_H += util/quote.h +LIB_H += util/util.h +LIB_H += util/xyarray.h +LIB_H += util/header.h +LIB_H += util/help.h +LIB_H += util/session.h +LIB_H += util/strbuf.h +LIB_H += util/strlist.h +LIB_H += util/strfilter.h +LIB_H += util/svghelper.h +LIB_H += util/tool.h +LIB_H += util/run-command.h +LIB_H += util/sigchain.h +LIB_H += util/dso.h +LIB_H += util/symbol.h +LIB_H += util/color.h +LIB_H += util/values.h +LIB_H += util/sort.h +LIB_H += util/hist.h +LIB_H += util/comm.h +LIB_H += util/thread.h +LIB_H += util/thread_map.h +LIB_H += util/trace-event.h +LIB_H += util/probe-finder.h +LIB_H += util/dwarf-aux.h +LIB_H += util/probe-event.h +LIB_H += util/pstack.h +LIB_H += util/cpumap.h +LIB_H += util/top.h +LIB_H += $(ARCH_INCLUDE) +LIB_H += util/cgroup.h +LIB_H += $(LIB_INCLUDE)traceevent/event-parse.h +LIB_H += util/target.h +LIB_H += util/rblist.h +LIB_H += util/intlist.h +LIB_H += util/perf_regs.h +LIB_H += util/unwind.h +LIB_H += util/vdso.h +LIB_H += ui/helpline.h +LIB_H += ui/progress.h +LIB_H += ui/util.h +LIB_H += ui/ui.h +LIB_H += util/data.h + +LIB_OBJS += $(OUTPUT)util/abspath.o +LIB_OBJS += $(OUTPUT)util/alias.o +LIB_OBJS += $(OUTPUT)util/annotate.o +LIB_OBJS += $(OUTPUT)util/build-id.o +LIB_OBJS += $(OUTPUT)util/config.o +LIB_OBJS += $(OUTPUT)util/ctype.o +LIB_OBJS += $(OUTPUT)util/fs.o +LIB_OBJS += $(OUTPUT)util/pmu.o +LIB_OBJS += $(OUTPUT)util/environment.o +LIB_OBJS += $(OUTPUT)util/event.o +LIB_OBJS += $(OUTPUT)util/evlist.o +LIB_OBJS += $(OUTPUT)util/evsel.o +LIB_OBJS += $(OUTPUT)util/exec_cmd.o +LIB_OBJS += $(OUTPUT)util/help.o +LIB_OBJS += $(OUTPUT)util/levenshtein.o +LIB_OBJS += $(OUTPUT)util/parse-options.o +LIB_OBJS += $(OUTPUT)util/parse-events.o +LIB_OBJS += $(OUTPUT)util/path.o +LIB_OBJS += $(OUTPUT)util/rbtree.o +LIB_OBJS += $(OUTPUT)util/bitmap.o +LIB_OBJS += $(OUTPUT)util/hweight.o +LIB_OBJS += $(OUTPUT)util/run-command.o +LIB_OBJS += $(OUTPUT)util/quote.o +LIB_OBJS += $(OUTPUT)util/strbuf.o +LIB_OBJS += $(OUTPUT)util/string.o +LIB_OBJS += $(OUTPUT)util/strlist.o +LIB_OBJS += $(OUTPUT)util/strfilter.o +LIB_OBJS += $(OUTPUT)util/top.o +LIB_OBJS += $(OUTPUT)util/usage.o +LIB_OBJS += $(OUTPUT)util/wrapper.o +LIB_OBJS += $(OUTPUT)util/sigchain.o +LIB_OBJS += $(OUTPUT)util/dso.o +LIB_OBJS += $(OUTPUT)util/symbol.o +LIB_OBJS += $(OUTPUT)util/symbol-elf.o +LIB_OBJS += $(OUTPUT)util/color.o +LIB_OBJS += $(OUTPUT)util/pager.o +LIB_OBJS += $(OUTPUT)util/header.o +LIB_OBJS += $(OUTPUT)util/callchain.o +LIB_OBJS += $(OUTPUT)util/values.o +LIB_OBJS += $(OUTPUT)util/debug.o +LIB_OBJS += $(OUTPUT)util/machine.o +LIB_OBJS += $(OUTPUT)util/map.o +LIB_OBJS += $(OUTPUT)util/pstack.o +LIB_OBJS += $(OUTPUT)util/session.o +LIB_OBJS += $(OUTPUT)util/comm.o +LIB_OBJS += $(OUTPUT)util/thread.o +LIB_OBJS += $(OUTPUT)util/thread_map.o +LIB_OBJS += $(OUTPUT)util/trace-event-parse.o +LIB_OBJS += $(OUTPUT)util/parse-events-flex.o +LIB_OBJS += $(OUTPUT)util/parse-events-bison.o +LIB_OBJS += $(OUTPUT)util/pmu-flex.o +LIB_OBJS += $(OUTPUT)util/pmu-bison.o +LIB_OBJS += $(OUTPUT)util/trace-event-read.o +LIB_OBJS += $(OUTPUT)util/trace-event-info.o +LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o +LIB_OBJS += $(OUTPUT)util/svghelper.o +LIB_OBJS += $(OUTPUT)util/sort.o +LIB_OBJS += $(OUTPUT)util/hist.o +LIB_OBJS += $(OUTPUT)util/probe-event.o +LIB_OBJS += $(OUTPUT)util/util.o +LIB_OBJS += $(OUTPUT)util/xyarray.o +LIB_OBJS += $(OUTPUT)util/cpumap.o +LIB_OBJS += $(OUTPUT)util/cgroup.o +LIB_OBJS += $(OUTPUT)util/target.o +LIB_OBJS += $(OUTPUT)util/rblist.o +LIB_OBJS += $(OUTPUT)util/intlist.o +LIB_OBJS += $(OUTPUT)util/vdso.o +LIB_OBJS += $(OUTPUT)util/stat.o +LIB_OBJS += $(OUTPUT)util/record.o +LIB_OBJS += $(OUTPUT)util/srcline.o +LIB_OBJS += $(OUTPUT)util/data.o + +LIB_OBJS += $(OUTPUT)ui/setup.o +LIB_OBJS += $(OUTPUT)ui/helpline.o +LIB_OBJS += $(OUTPUT)ui/progress.o +LIB_OBJS += $(OUTPUT)ui/util.o +LIB_OBJS += $(OUTPUT)ui/hist.o +LIB_OBJS += $(OUTPUT)ui/stdio/hist.o + +LIB_OBJS += $(OUTPUT)arch/common.o + +LIB_OBJS += $(OUTPUT)tests/parse-events.o +LIB_OBJS += $(OUTPUT)tests/dso-data.o +LIB_OBJS += $(OUTPUT)tests/attr.o +LIB_OBJS += $(OUTPUT)tests/vmlinux-kallsyms.o +LIB_OBJS += $(OUTPUT)tests/open-syscall.o +LIB_OBJS += $(OUTPUT)tests/open-syscall-all-cpus.o +LIB_OBJS += $(OUTPUT)tests/open-syscall-tp-fields.o +LIB_OBJS += $(OUTPUT)tests/mmap-basic.o +LIB_OBJS += $(OUTPUT)tests/perf-record.o +LIB_OBJS += $(OUTPUT)tests/rdpmc.o +LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o +LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o +LIB_OBJS += $(OUTPUT)tests/pmu.o +LIB_OBJS += $(OUTPUT)tests/hists_link.o +LIB_OBJS += $(OUTPUT)tests/python-use.o +LIB_OBJS += $(OUTPUT)tests/bp_signal.o +LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o +LIB_OBJS += $(OUTPUT)tests/task-exit.o +LIB_OBJS += $(OUTPUT)tests/sw-clock.o +ifeq ($(ARCH),x86) +LIB_OBJS += $(OUTPUT)tests/perf-time-to-tsc.o +endif +LIB_OBJS += $(OUTPUT)tests/code-reading.o +LIB_OBJS += $(OUTPUT)tests/sample-parsing.o +LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o + +BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o +BUILTIN_OBJS += $(OUTPUT)builtin-bench.o +# Benchmark modules +BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o +BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o +ifeq ($(RAW_ARCH),x86_64) +BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o +BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o +endif +BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o +BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o + +BUILTIN_OBJS += $(OUTPUT)builtin-diff.o +BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o +BUILTIN_OBJS += $(OUTPUT)builtin-help.o +BUILTIN_OBJS += $(OUTPUT)builtin-sched.o +BUILTIN_OBJS += $(OUTPUT)builtin-buildid-list.o +BUILTIN_OBJS += $(OUTPUT)builtin-buildid-cache.o +BUILTIN_OBJS += $(OUTPUT)builtin-list.o +BUILTIN_OBJS += $(OUTPUT)builtin-record.o +BUILTIN_OBJS += $(OUTPUT)builtin-report.o +BUILTIN_OBJS += $(OUTPUT)builtin-stat.o +BUILTIN_OBJS += $(OUTPUT)builtin-timechart.o +BUILTIN_OBJS += $(OUTPUT)builtin-top.o +BUILTIN_OBJS += $(OUTPUT)builtin-script.o +BUILTIN_OBJS += $(OUTPUT)builtin-probe.o +BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o +BUILTIN_OBJS += $(OUTPUT)builtin-lock.o +BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o +BUILTIN_OBJS += $(OUTPUT)builtin-inject.o +BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o +BUILTIN_OBJS += $(OUTPUT)builtin-mem.o + +PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT) + +# We choose to avoid "if .. else if .. else .. endif endif" +# because maintaining the nesting to match is a pain. If +# we had "elif" things would have been much nicer... + +-include arch/$(ARCH)/Makefile + +ifneq ($(OUTPUT),) + CFLAGS += -I$(OUTPUT) +endif + +ifdef NO_LIBELF +EXTLIBS := $(filter-out -lelf,$(EXTLIBS)) + +# Remove ELF/DWARF dependent codes +LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS)) +LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS)) +LIB_OBJS := $(filter-out $(OUTPUT)util/probe-event.o,$(LIB_OBJS)) +LIB_OBJS := $(filter-out $(OUTPUT)util/probe-finder.o,$(LIB_OBJS)) + +BUILTIN_OBJS := $(filter-out $(OUTPUT)builtin-probe.o,$(BUILTIN_OBJS)) + +# Use minimal symbol handling +LIB_OBJS += $(OUTPUT)util/symbol-minimal.o + +else # NO_LIBELF +ifndef NO_DWARF + LIB_OBJS += $(OUTPUT)util/probe-finder.o + LIB_OBJS += $(OUTPUT)util/dwarf-aux.o +endif # NO_DWARF +endif # NO_LIBELF + +ifndef NO_LIBUNWIND + LIB_OBJS += $(OUTPUT)util/unwind.o +endif +LIB_OBJS += $(OUTPUT)tests/keep-tracking.o + +ifndef NO_LIBAUDIT + BUILTIN_OBJS += $(OUTPUT)builtin-trace.o +endif + +ifndef NO_SLANG + LIB_OBJS += $(OUTPUT)ui/browser.o + LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o + LIB_OBJS += $(OUTPUT)ui/browsers/hists.o + LIB_OBJS += $(OUTPUT)ui/browsers/map.o + LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o + LIB_OBJS += $(OUTPUT)ui/tui/setup.o + LIB_OBJS += $(OUTPUT)ui/tui/util.o + LIB_OBJS += $(OUTPUT)ui/tui/helpline.o + LIB_OBJS += $(OUTPUT)ui/tui/progress.o + LIB_H += ui/tui/tui.h + LIB_H += ui/browser.h + LIB_H += ui/browsers/map.h + LIB_H += ui/keysyms.h + LIB_H += ui/libslang.h +endif + +ifndef NO_GTK2 + ALL_PROGRAMS += $(OUTPUT)libperf-gtk.so + + GTK_OBJS += $(OUTPUT)ui/gtk/browser.o + GTK_OBJS += $(OUTPUT)ui/gtk/hists.o + GTK_OBJS += $(OUTPUT)ui/gtk/setup.o + GTK_OBJS += $(OUTPUT)ui/gtk/util.o + GTK_OBJS += $(OUTPUT)ui/gtk/helpline.o + GTK_OBJS += $(OUTPUT)ui/gtk/progress.o + GTK_OBJS += $(OUTPUT)ui/gtk/annotate.o + +install-gtk: $(OUTPUT)libperf-gtk.so + $(call QUIET_INSTALL, 'GTK UI') \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \ + $(INSTALL) $(OUTPUT)libperf-gtk.so '$(DESTDIR_SQ)$(libdir_SQ)' +endif + +ifndef NO_LIBPERL + LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o + LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o +endif + +ifndef NO_LIBPYTHON + LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o + LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o +endif + +ifeq ($(NO_PERF_REGS),0) + ifeq ($(ARCH),x86) + LIB_H += arch/x86/include/perf_regs.h + endif +endif + +ifndef NO_LIBNUMA + BUILTIN_OBJS += $(OUTPUT)bench/numa.o +endif + +ifdef ASCIIDOC8 + export ASCIIDOC8 +endif + +LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group + +export INSTALL SHELL_PATH + +### Build rules + +SHELL = $(SHELL_PATH) + +all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS) + +please_set_SHELL_PATH_to_a_more_modern_shell: + @$$(:) + +shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell + +strip: $(PROGRAMS) $(OUTPUT)perf + $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf + +$(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -include $(OUTPUT)PERF-VERSION-FILE \ + '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ + $(CFLAGS) -c $(filter %.c,$^) -o $@ + +$(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OUTPUT)perf.o \ + $(BUILTIN_OBJS) $(LIBS) -o $@ + +$(GTK_OBJS): $(OUTPUT)%.o: %.c $(LIB_H) + $(QUIET_CC)$(CC) -o $@ -c -fPIC $(CFLAGS) $(GTK_CFLAGS) $< + +$(OUTPUT)libperf-gtk.so: $(GTK_OBJS) $(PERFLIBS) + $(QUIET_LINK)$(CC) -o $@ -shared $(ALL_LDFLAGS) $(filter %.o,$^) $(GTK_LIBS) + +$(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ + '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ + '-DPERF_MAN_PATH="$(mandir_SQ)"' \ + '-DPERF_INFO_PATH="$(infodir_SQ)"' $< + +$(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ + '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ + '-DPERF_MAN_PATH="$(mandir_SQ)"' \ + '-DPERF_INFO_PATH="$(infodir_SQ)"' $< + +$(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt + +$(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt) + $(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@ + +$(SCRIPTS) : % : %.sh + $(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@' + +# These can record PERF_VERSION +$(OUTPUT)perf.o perf.spec \ + $(SCRIPTS) \ + : $(OUTPUT)PERF-VERSION-FILE + +.SUFFIXES: + +# +# If a target does not match any of the later rules then prefix it by $(OUTPUT) +# This makes targets like 'make O=/tmp/perf perf.o' work in a natural way. +# +ifneq ($(OUTPUT),) +%.o: $(OUTPUT)%.o + @echo " # Redirected target $@ => $(OUTPUT)$@" +util/%.o: $(OUTPUT)util/%.o + @echo " # Redirected target $@ => $(OUTPUT)$@" +bench/%.o: $(OUTPUT)bench/%.o + @echo " # Redirected target $@ => $(OUTPUT)$@" +tests/%.o: $(OUTPUT)tests/%.o + @echo " # Redirected target $@ => $(OUTPUT)$@" +endif + +# These two need to be here so that when O= is not used they take precedence +# over the general rule for .o + +$(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -w $< + +$(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $< + +$(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $< +$(OUTPUT)%.i: %.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $< +$(OUTPUT)%.s: %.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -S $(CFLAGS) $< +$(OUTPUT)%.o: %.S + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $< +$(OUTPUT)%.s: %.S + $(QUIET_CC)$(CC) -o $@ -E $(CFLAGS) $< + +$(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ + '-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \ + '-DPREFIX="$(prefix_SQ)"' \ + $< + +$(OUTPUT)tests/attr.o: tests/attr.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ + '-DBINDIR="$(bindir_SQ)"' -DPYTHON='"$(PYTHON_WORD)"' \ + $< + +$(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \ + -DPYTHONPATH='"$(OUTPUT)python"' \ + -DPYTHON='"$(PYTHON_WORD)"' \ + $< + +$(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + +$(OUTPUT)ui/setup.o: ui/setup.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DLIBDIR='"$(libdir_SQ)"' $< + +$(OUTPUT)ui/browser.o: ui/browser.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< + +$(OUTPUT)ui/browsers/annotate.o: ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< + +$(OUTPUT)ui/browsers/hists.o: ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< + +$(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< + +$(OUTPUT)ui/browsers/scripts.o: ui/browsers/scripts.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $< + +$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< + +$(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $< + +$(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default $< + +$(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-undef -Wno-switch-default $< + +$(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $< + +$(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< + +$(OUTPUT)perf-%: %.o $(PERFLIBS) + $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS) + +$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H) +$(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h) + +# we compile into subdirectories. if the target directory is not the source directory, they might not exists. So +# we depend the various files onto their directories. +DIRECTORY_DEPS = $(LIB_OBJS) $(BUILTIN_OBJS) $(GTK_OBJS) +DIRECTORY_DEPS += $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h +$(DIRECTORY_DEPS): | $(sort $(dir $(DIRECTORY_DEPS))) +# In the second step, we make a rule to actually create these directories +$(sort $(dir $(DIRECTORY_DEPS))): + $(QUIET_MKDIR)$(MKDIR) -p $@ 2>/dev/null + +$(LIB_FILE): $(LIB_OBJS) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS) + +# libtraceevent.a +TE_SOURCES = $(wildcard $(TRACE_EVENT_DIR)*.[ch]) + +$(LIBTRACEEVENT): $(TE_SOURCES) + $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) CFLAGS="-g -Wall $(EXTRA_CFLAGS)" libtraceevent.a + +$(LIBTRACEEVENT)-clean: + $(call QUIET_CLEAN, libtraceevent) + @$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null + +LIBLK_SOURCES = $(wildcard $(LK_PATH)*.[ch]) + +# if subdir is set, we've been called from above so target has been built +# already +$(LIBLK): $(LIBLK_SOURCES) +ifeq ($(subdir),) + $(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) liblk.a +endif + +$(LIBLK)-clean: +ifeq ($(subdir),) + $(call QUIET_CLEAN, liblk) + @$(MAKE) -C $(LK_DIR) O=$(OUTPUT) clean >/dev/null +endif + +help: + @echo 'Perf make targets:' + @echo ' doc - make *all* documentation (see below)' + @echo ' man - make manpage documentation (access with man <foo>)' + @echo ' html - make html documentation' + @echo ' info - make GNU info documentation (access with info <foo>)' + @echo ' pdf - make pdf documentation' + @echo ' TAGS - use etags to make tag information for source browsing' + @echo ' tags - use ctags to make tag information for source browsing' + @echo ' cscope - use cscope to make interactive browsing database' + @echo '' + @echo 'Perf install targets:' + @echo ' NOTE: documentation build requires asciidoc, xmlto packages to be installed' + @echo ' HINT: use "make prefix=<path> <install target>" to install to a particular' + @echo ' path like make prefix=/usr/local install install-doc' + @echo ' install - install compiled binaries' + @echo ' install-doc - install *all* documentation' + @echo ' install-man - install manpage documentation' + @echo ' install-html - install html documentation' + @echo ' install-info - install GNU info documentation' + @echo ' install-pdf - install pdf documentation' + @echo '' + @echo ' quick-install-doc - alias for quick-install-man' + @echo ' quick-install-man - install the documentation quickly' + @echo ' quick-install-html - install the html documentation quickly' + @echo '' + @echo 'Perf maintainer targets:' + @echo ' clean - clean all binary objects and build output' + + +DOC_TARGETS := doc man html info pdf + +INSTALL_DOC_TARGETS := $(patsubst %,install-%,$(DOC_TARGETS)) try-install-man +INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html + +# 'make doc' should call 'make -C Documentation all' +$(DOC_TARGETS): + $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all) + +TAGS: + $(RM) TAGS + $(FIND) . -name '*.[hcS]' -print | xargs etags -a + +tags: + $(RM) tags + $(FIND) . -name '*.[hcS]' -print | xargs ctags -a + +cscope: + $(RM) cscope* + $(FIND) . -name '*.[hcS]' -print | xargs cscope -b + +### Detect prefix changes +TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\ + $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ) + +$(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS + @FLAGS='$(TRACK_CFLAGS)'; \ + if test x"$$FLAGS" != x"`cat $(OUTPUT)PERF-CFLAGS 2>/dev/null`" ; then \ + echo 1>&2 " FLAGS: * new build flags or prefix"; \ + echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \ + fi + +### Testing rules + +# GNU make supports exporting all variables by "export" without parameters. +# However, the environment gets quite big, and some programs have problems +# with that. + +check: $(OUTPUT)common-cmds.h + if sparse; \ + then \ + for i in *.c */*.c; \ + do \ + sparse $(CFLAGS) $(SPARSE_FLAGS) $$i || exit; \ + done; \ + else \ + exit 1; \ + fi + +### Installation rules + +install-gtk: + +install-bin: all install-gtk + $(call QUIET_INSTALL, binaries) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \ + $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \ + $(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(bindir_SQ)/trace' + $(call QUIET_INSTALL, libexec) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' + $(call QUIET_INSTALL, perf-archive) \ + $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' +ifndef NO_LIBPERL + $(call QUIET_INSTALL, perl-scripts) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \ + $(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \ + $(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'; \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'; \ + $(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin' +endif +ifndef NO_LIBPYTHON + $(call QUIET_INSTALL, python-scripts) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'; \ + $(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'; \ + $(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \ + $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin' +endif + $(call QUIET_INSTALL, bash_completion-script) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \ + $(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf' + $(call QUIET_INSTALL, tests) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \ + $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \ + $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr' + +install: install-bin try-install-man + +install-python_ext: + $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)' + +# 'make install-doc' should call 'make -C Documentation install' +$(INSTALL_DOC_TARGETS): + $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:-doc=) + +### Cleaning rules + +# +# This is here, not in config/Makefile, because config/Makefile does +# not get included for the clean target: +# +config-clean: + $(call QUIET_CLEAN, config) + @$(MAKE) -C config/feature-checks clean >/dev/null + +clean: $(LIBTRACEEVENT)-clean $(LIBLK)-clean config-clean + $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS) + $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf + $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* + $(call QUIET_CLEAN, Documentation) + @$(MAKE) -C Documentation O=$(OUTPUT) clean >/dev/null + $(python-clean) + +# +# Trick: if ../../.git does not exist - we are building out of tree for example, +# then force version regeneration: +# +ifeq ($(wildcard ../../.git/HEAD),) + GIT-HEAD-PHONY = ../../.git/HEAD +else + GIT-HEAD-PHONY = +endif + +.PHONY: all install clean config-clean strip install-gtk +.PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell +.PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope .FORCE-PERF-CFLAGS + diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 815841c04eb..8801fe02f20 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -6,3 +6,5 @@ ifndef NO_LIBUNWIND LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o endif LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o +LIB_H += arch/$(ARCH)/util/tsc.h diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index 7fcdcdbee91..e84ca76aae7 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -5,7 +5,7 @@ #include "../../util/types.h" #include <asm/perf_regs.h> -#ifndef ARCH_X86_64 +#ifndef HAVE_ARCH_X86_64_SUPPORT #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1) #else #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \ @@ -52,7 +52,7 @@ static inline const char *perf_reg_name(int id) return "FS"; case PERF_REG_X86_GS: return "GS"; -#ifdef ARCH_X86_64 +#ifdef HAVE_ARCH_X86_64_SUPPORT case PERF_REG_X86_R8: return "R8"; case PERF_REG_X86_R9: @@ -69,7 +69,7 @@ static inline const char *perf_reg_name(int id) return "R14"; case PERF_REG_X86_R15: return "R15"; -#endif /* ARCH_X86_64 */ +#endif /* HAVE_ARCH_X86_64_SUPPORT */ default: return NULL; } diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c new file mode 100644 index 00000000000..b2519e49424 --- /dev/null +++ b/tools/perf/arch/x86/util/tsc.c @@ -0,0 +1,59 @@ +#include <stdbool.h> +#include <errno.h> + +#include <linux/perf_event.h> + +#include "../../perf.h" +#include "../../util/types.h" +#include "../../util/debug.h" +#include "tsc.h" + +u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc) +{ + u64 t, quot, rem; + + t = ns - tc->time_zero; + quot = t / tc->time_mult; + rem = t % tc->time_mult; + return (quot << tc->time_shift) + + (rem << tc->time_shift) / tc->time_mult; +} + +u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc) +{ + u64 quot, rem; + + quot = cyc >> tc->time_shift; + rem = cyc & ((1 << tc->time_shift) - 1); + return tc->time_zero + quot * tc->time_mult + + ((rem * tc->time_mult) >> tc->time_shift); +} + +int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, + struct perf_tsc_conversion *tc) +{ + bool cap_user_time_zero; + u32 seq; + int i = 0; + + while (1) { + seq = pc->lock; + rmb(); + tc->time_mult = pc->time_mult; + tc->time_shift = pc->time_shift; + tc->time_zero = pc->time_zero; + cap_user_time_zero = pc->cap_user_time_zero; + rmb(); + if (pc->lock == seq && !(seq & 1)) + break; + if (++i > 10000) { + pr_debug("failed to get perf_event_mmap_page lock\n"); + return -EINVAL; + } + } + + if (!cap_user_time_zero) + return -EOPNOTSUPP; + + return 0; +} diff --git a/tools/perf/arch/x86/util/tsc.h b/tools/perf/arch/x86/util/tsc.h new file mode 100644 index 00000000000..a24dec81c79 --- /dev/null +++ b/tools/perf/arch/x86/util/tsc.h @@ -0,0 +1,20 @@ +#ifndef TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ +#define TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ + +#include "../../util/types.h" + +struct perf_tsc_conversion { + u16 time_shift; + u32 time_mult; + u64 time_zero; +}; + +struct perf_event_mmap_page; + +int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, + struct perf_tsc_conversion *tc); + +u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc); +u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc); + +#endif /* TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ */ diff --git a/tools/perf/arch/x86/util/unwind.c b/tools/perf/arch/x86/util/unwind.c index 78d956eff96..456a88cf5b3 100644 --- a/tools/perf/arch/x86/util/unwind.c +++ b/tools/perf/arch/x86/util/unwind.c @@ -4,7 +4,7 @@ #include "perf_regs.h" #include "../../util/unwind.h" -#ifdef ARCH_X86_64 +#ifdef HAVE_ARCH_X86_64_SUPPORT int unwind__arch_reg_id(int regnum) { int id; @@ -108,4 +108,4 @@ int unwind__arch_reg_id(int regnum) return id; } -#endif /* ARCH_X86_64 */ +#endif /* HAVE_ARCH_X86_64_SUPPORT */ diff --git a/tools/perf/bash_completion b/tools/perf/bash_completion index 56e6a12aab5..62e157db2e2 100644 --- a/tools/perf/bash_completion +++ b/tools/perf/bash_completion @@ -1,17 +1,87 @@ # perf completion -function_exists() +# Taken from git.git's completion script. +__my_reassemble_comp_words_by_ref() { - declare -F $1 > /dev/null - return $? + local exclude i j first + # Which word separators to exclude? + exclude="${1//[^$COMP_WORDBREAKS]}" + cword_=$COMP_CWORD + if [ -z "$exclude" ]; then + words_=("${COMP_WORDS[@]}") + return + fi + # List of word completion separators has shrunk; + # re-assemble words to complete. + for ((i=0, j=0; i < ${#COMP_WORDS[@]}; i++, j++)); do + # Append each nonempty word consisting of just + # word separator characters to the current word. + first=t + while + [ $i -gt 0 ] && + [ -n "${COMP_WORDS[$i]}" ] && + # word consists of excluded word separators + [ "${COMP_WORDS[$i]//[^$exclude]}" = "${COMP_WORDS[$i]}" ] + do + # Attach to the previous token, + # unless the previous token is the command name. + if [ $j -ge 2 ] && [ -n "$first" ]; then + ((j--)) + fi + first= + words_[$j]=${words_[j]}${COMP_WORDS[i]} + if [ $i = $COMP_CWORD ]; then + cword_=$j + fi + if (($i < ${#COMP_WORDS[@]} - 1)); then + ((i++)) + else + # Done. + return + fi + done + words_[$j]=${words_[j]}${COMP_WORDS[i]} + if [ $i = $COMP_CWORD ]; then + cword_=$j + fi + done } -function_exists __ltrim_colon_completions || +type _get_comp_words_by_ref &>/dev/null || +_get_comp_words_by_ref() +{ + local exclude cur_ words_ cword_ + if [ "$1" = "-n" ]; then + exclude=$2 + shift 2 + fi + __my_reassemble_comp_words_by_ref "$exclude" + cur_=${words_[cword_]} + while [ $# -gt 0 ]; do + case "$1" in + cur) + cur=$cur_ + ;; + prev) + prev=${words_[$cword_-1]} + ;; + words) + words=("${words_[@]}") + ;; + cword) + cword=$cword_ + ;; + esac + shift + done +} + +type __ltrim_colon_completions &>/dev/null || __ltrim_colon_completions() { if [[ "$1" == *:* && "$COMP_WORDBREAKS" == *:* ]]; then # Remove colon-word prefix from COMPREPLY items - local colon_word=${1%${1##*:}} + local colon_word=${1%"${1##*:}"} local i=${#COMPREPLY[*]} while [[ $((--i)) -ge 0 ]]; do COMPREPLY[$i]=${COMPREPLY[$i]#"$colon_word"} @@ -19,23 +89,18 @@ __ltrim_colon_completions() fi } -have perf && +type perf &>/dev/null && _perf() { - local cur prev cmd + local cur words cword prev cmd COMPREPLY=() - if function_exists _get_comp_words_by_ref; then - _get_comp_words_by_ref -n : cur prev - else - cur=$(_get_cword :) - prev=${COMP_WORDS[COMP_CWORD-1]} - fi + _get_comp_words_by_ref -n =: cur words cword prev - cmd=${COMP_WORDS[0]} + cmd=${words[0]} # List perf subcommands or long options - if [ $COMP_CWORD -eq 1 ]; then + if [ $cword -eq 1 ]; then if [[ $cur == --* ]]; then COMPREPLY=( $( compgen -W '--help --version \ --exec-path --html-path --paginate --no-pager \ @@ -45,18 +110,17 @@ _perf() COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) ) fi # List possible events for -e option - elif [[ $prev == "-e" && "${COMP_WORDS[1]}" == @(record|stat|top) ]]; then + elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then evts=$($cmd list --raw-dump) COMPREPLY=( $( compgen -W '$evts' -- "$cur" ) ) __ltrim_colon_completions $cur # List long option names elif [[ $cur == --* ]]; then - subcmd=${COMP_WORDS[1]} + subcmd=${words[1]} opts=$($cmd $subcmd --list-opts) COMPREPLY=( $( compgen -W '$opts' -- "$cur" ) ) - # Fall down to list regular files - else - _filedir fi } && -complete -F _perf perf + +complete -o bashdefault -o default -o nospace -F _perf perf 2>/dev/null \ + || complete -o default -o nospace -F _perf perf diff --git a/tools/perf/bench/mem-memcpy-arch.h b/tools/perf/bench/mem-memcpy-arch.h index a72e36cb539..57b4ed87145 100644 --- a/tools/perf/bench/mem-memcpy-arch.h +++ b/tools/perf/bench/mem-memcpy-arch.h @@ -1,5 +1,5 @@ -#ifdef ARCH_X86_64 +#ifdef HAVE_ARCH_X86_64_SUPPORT #define MEMCPY_FN(fn, name, desc) \ extern void *fn(void *, const void *, size_t); diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c index 25fd3f1966f..5ce71d3b72c 100644 --- a/tools/perf/bench/mem-memcpy.c +++ b/tools/perf/bench/mem-memcpy.c @@ -58,7 +58,7 @@ struct routine routines[] = { { "default", "Default memcpy() provided by glibc", memcpy }, -#ifdef ARCH_X86_64 +#ifdef HAVE_ARCH_X86_64_SUPPORT #define MEMCPY_FN(fn, name, desc) { name, desc, fn }, #include "mem-memcpy-x86-64-asm-def.h" @@ -117,6 +117,8 @@ static void alloc_mem(void **dst, void **src, size_t length) *src = zalloc(length); if (!*src) die("memory allocation failed - maybe length is too large?\n"); + /* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */ + memset(*src, 0, length); } static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault) diff --git a/tools/perf/bench/mem-memset-arch.h b/tools/perf/bench/mem-memset-arch.h index a040fa77665..633800cb0dc 100644 --- a/tools/perf/bench/mem-memset-arch.h +++ b/tools/perf/bench/mem-memset-arch.h @@ -1,5 +1,5 @@ -#ifdef ARCH_X86_64 +#ifdef HAVE_ARCH_X86_64_SUPPORT #define MEMSET_FN(fn, name, desc) \ extern void *fn(void *, int, size_t); diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c index 4a2f1208196..9af79d2b18e 100644 --- a/tools/perf/bench/mem-memset.c +++ b/tools/perf/bench/mem-memset.c @@ -58,7 +58,7 @@ static const struct routine routines[] = { { "default", "Default memset() provided by glibc", memset }, -#ifdef ARCH_X86_64 +#ifdef HAVE_ARCH_X86_64_SUPPORT #define MEMSET_FN(fn, name, desc) { name, desc, fn }, #include "mem-memset-x86-64-asm-def.h" diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 30d1c3225b4..d4c83c60b9b 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -429,14 +429,14 @@ static int parse_cpu_list(const char *arg) return 0; } -static void parse_setup_cpu_list(void) +static int parse_setup_cpu_list(void) { struct thread_data *td; char *str0, *str; int t; if (!g->p.cpu_list_str) - return; + return 0; dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks); @@ -500,8 +500,12 @@ static void parse_setup_cpu_list(void) dprintf("CPUs: %d_%d-%d#%dx%d\n", bind_cpu_0, bind_len, bind_cpu_1, step, mul); - BUG_ON(bind_cpu_0 < 0 || bind_cpu_0 >= g->p.nr_cpus); - BUG_ON(bind_cpu_1 < 0 || bind_cpu_1 >= g->p.nr_cpus); + if (bind_cpu_0 >= g->p.nr_cpus || bind_cpu_1 >= g->p.nr_cpus) { + printf("\nTest not applicable, system has only %d CPUs.\n", g->p.nr_cpus); + return -1; + } + + BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0); BUG_ON(bind_cpu_0 > bind_cpu_1); for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) { @@ -541,6 +545,7 @@ out: printf("# NOTE: %d tasks bound, %d tasks unbound\n", t, g->p.nr_tasks - t); free(str0); + return 0; } static int parse_cpus_opt(const struct option *opt __maybe_unused, @@ -561,14 +566,14 @@ static int parse_node_list(const char *arg) return 0; } -static void parse_setup_node_list(void) +static int parse_setup_node_list(void) { struct thread_data *td; char *str0, *str; int t; if (!g->p.node_list_str) - return; + return 0; dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks); @@ -619,8 +624,12 @@ static void parse_setup_node_list(void) dprintf("NODEs: %d-%d #%d\n", bind_node_0, bind_node_1, step); - BUG_ON(bind_node_0 < 0 || bind_node_0 >= g->p.nr_nodes); - BUG_ON(bind_node_1 < 0 || bind_node_1 >= g->p.nr_nodes); + if (bind_node_0 >= g->p.nr_nodes || bind_node_1 >= g->p.nr_nodes) { + printf("\nTest not applicable, system has only %d nodes.\n", g->p.nr_nodes); + return -1; + } + + BUG_ON(bind_node_0 < 0 || bind_node_1 < 0); BUG_ON(bind_node_0 > bind_node_1); for (bind_node = bind_node_0; bind_node <= bind_node_1; bind_node += step) { @@ -651,6 +660,7 @@ out: printf("# NOTE: %d tasks mem-bound, %d tasks unbound\n", t, g->p.nr_tasks - t); free(str0); + return 0; } static int parse_nodes_opt(const struct option *opt __maybe_unused, @@ -1110,7 +1120,7 @@ static void *worker_thread(void *__tdata) /* Check whether our max runtime timed out: */ if (g->p.nr_secs) { timersub(&stop, &start0, &diff); - if (diff.tv_sec >= g->p.nr_secs) { + if ((u32)diff.tv_sec >= g->p.nr_secs) { g->stop_work = true; break; } @@ -1157,7 +1167,7 @@ static void *worker_thread(void *__tdata) runtime_ns_max += diff.tv_usec * 1000; if (details >= 0) { - printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016lx]\n", + printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016"PRIx64"]\n", process_nr, thread_nr, runtime_ns_max / bytes_done, val); } fflush(stdout); @@ -1356,8 +1366,8 @@ static int init(void) init_thread_data(); tprintf("#\n"); - parse_setup_cpu_list(); - parse_setup_node_list(); + if (parse_setup_cpu_list() || parse_setup_node_list()) + return -1; tprintf("#\n"); print_summary(); @@ -1600,7 +1610,6 @@ static int run_bench_numa(const char *name, const char **argv) return 0; err: - usage_with_options(numa_usage, options); return -1; } @@ -1701,8 +1710,7 @@ static int bench_all(void) BUG_ON(ret < 0); for (i = 0; i < nr; i++) { - if (run_bench_numa(tests[i][0], tests[i] + 1)) - return -1; + run_bench_numa(tests[i][0], tests[i] + 1); } printf("\n"); diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index 69cfba8d4c6..07a8d7646a1 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -7,9 +7,7 @@ * Based on pipe-test-1m.c by Ingo Molnar <mingo@redhat.com> * http://people.redhat.com/mingo/cfs-scheduler/tools/pipe-test-1m.c * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> - * */ - #include "../perf.h" #include "../util/util.h" #include "../util/parse-options.h" @@ -28,12 +26,24 @@ #include <sys/time.h> #include <sys/types.h> +#include <pthread.h> + +struct thread_data { + int nr; + int pipe_read; + int pipe_write; + pthread_t pthread; +}; + #define LOOPS_DEFAULT 1000000 -static int loops = LOOPS_DEFAULT; +static int loops = LOOPS_DEFAULT; + +/* Use processes by default: */ +static bool threaded; static const struct option options[] = { - OPT_INTEGER('l', "loop", &loops, - "Specify number of loops"), + OPT_INTEGER('l', "loop", &loops, "Specify number of loops"), + OPT_BOOLEAN('T', "threaded", &threaded, "Specify threads/process based task setup"), OPT_END() }; @@ -42,13 +52,37 @@ static const char * const bench_sched_pipe_usage[] = { NULL }; -int bench_sched_pipe(int argc, const char **argv, - const char *prefix __maybe_unused) +static void *worker_thread(void *__tdata) { - int pipe_1[2], pipe_2[2]; + struct thread_data *td = __tdata; int m = 0, i; + int ret; + + for (i = 0; i < loops; i++) { + if (!td->nr) { + ret = read(td->pipe_read, &m, sizeof(int)); + BUG_ON(ret != sizeof(int)); + ret = write(td->pipe_write, &m, sizeof(int)); + BUG_ON(ret != sizeof(int)); + } else { + ret = write(td->pipe_write, &m, sizeof(int)); + BUG_ON(ret != sizeof(int)); + ret = read(td->pipe_read, &m, sizeof(int)); + BUG_ON(ret != sizeof(int)); + } + } + + return NULL; +} + +int bench_sched_pipe(int argc, const char **argv, const char *prefix __maybe_unused) +{ + struct thread_data threads[2], *td; + int pipe_1[2], pipe_2[2]; struct timeval start, stop, diff; unsigned long long result_usec = 0; + int nr_threads = 2; + int t; /* * why does "ret" exist? @@ -58,43 +92,66 @@ int bench_sched_pipe(int argc, const char **argv, int __maybe_unused ret, wait_stat; pid_t pid, retpid __maybe_unused; - argc = parse_options(argc, argv, options, - bench_sched_pipe_usage, 0); + argc = parse_options(argc, argv, options, bench_sched_pipe_usage, 0); BUG_ON(pipe(pipe_1)); BUG_ON(pipe(pipe_2)); - pid = fork(); - assert(pid >= 0); - gettimeofday(&start, NULL); - if (!pid) { - for (i = 0; i < loops; i++) { - ret = read(pipe_1[0], &m, sizeof(int)); - ret = write(pipe_2[1], &m, sizeof(int)); - } - } else { - for (i = 0; i < loops; i++) { - ret = write(pipe_1[1], &m, sizeof(int)); - ret = read(pipe_2[0], &m, sizeof(int)); + for (t = 0; t < nr_threads; t++) { + td = threads + t; + + td->nr = t; + + if (t == 0) { + td->pipe_read = pipe_1[0]; + td->pipe_write = pipe_2[1]; + } else { + td->pipe_write = pipe_1[1]; + td->pipe_read = pipe_2[0]; } } - gettimeofday(&stop, NULL); - timersub(&stop, &start, &diff); - if (pid) { + if (threaded) { + + for (t = 0; t < nr_threads; t++) { + td = threads + t; + + ret = pthread_create(&td->pthread, NULL, worker_thread, td); + BUG_ON(ret); + } + + for (t = 0; t < nr_threads; t++) { + td = threads + t; + + ret = pthread_join(td->pthread, NULL); + BUG_ON(ret); + } + + } else { + pid = fork(); + assert(pid >= 0); + + if (!pid) { + worker_thread(threads + 0); + exit(0); + } else { + worker_thread(threads + 1); + } + retpid = waitpid(pid, &wait_stat, 0); assert((retpid == pid) && WIFEXITED(wait_stat)); - } else { - exit(0); } + gettimeofday(&stop, NULL); + timersub(&stop, &start, &diff); + switch (bench_format) { case BENCH_FORMAT_DEFAULT: - printf("# Executed %d pipe operations between two tasks\n\n", - loops); + printf("# Executed %d pipe operations between two %s\n\n", + loops, threaded ? "threads" : "processes"); result_usec = diff.tv_sec * 1000000; result_usec += diff.tv_usec; diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index db491e9a812..4087ab19823 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -28,8 +28,10 @@ #include "util/hist.h" #include "util/session.h" #include "util/tool.h" +#include "util/data.h" #include "arch/common.h" +#include <dlfcn.h> #include <linux/bitmap.h> struct perf_annotate { @@ -63,7 +65,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, return 0; } - he = __hists__add_entry(&evsel->hists, al, NULL, 1, 1); + he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0); if (he == NULL) return -ENOMEM; @@ -90,8 +92,7 @@ static int process_sample_event(struct perf_tool *tool, struct perf_annotate *ann = container_of(tool, struct perf_annotate, tool); struct addr_location al; - if (perf_event__preprocess_sample(event, machine, &al, sample, - symbol__annotate_init) < 0) { + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { pr_warning("problem processing %d event, skipping it.\n", event->header.type); return -1; @@ -117,11 +118,11 @@ static int hist_entry__tty_annotate(struct hist_entry *he, ann->print_line, ann->full_paths, 0, 0); } -static void hists__find_annotations(struct hists *self, +static void hists__find_annotations(struct hists *hists, struct perf_evsel *evsel, struct perf_annotate *ann) { - struct rb_node *nd = rb_first(&self->entries), *next; + struct rb_node *nd = rb_first(&hists->entries), *next; int key = K_RIGHT; while (nd) { @@ -143,8 +144,18 @@ find_next: if (use_browser == 2) { int ret; + int (*annotate)(struct hist_entry *he, + struct perf_evsel *evsel, + struct hist_browser_timer *hbt); + + annotate = dlsym(perf_gtk_handle, + "hist_entry__gtk_annotate"); + if (annotate == NULL) { + ui__error("GTK browser not found!\n"); + return; + } - ret = hist_entry__gtk_annotate(he, evsel, NULL); + ret = annotate(he, evsel, NULL); if (!ret || !ann->skip_missing) return; @@ -189,12 +200,18 @@ static int __cmd_annotate(struct perf_annotate *ann) struct perf_session *session; struct perf_evsel *pos; u64 total_nr_samples; + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + .force = ann->force, + }; - session = perf_session__new(input_name, O_RDONLY, - ann->force, false, &ann->tool); + session = perf_session__new(&file, false, &ann->tool); if (session == NULL) return -ENOMEM; + machines__set_symbol_filter(&session->machines, symbol__annotate_init); + if (ann->cpu_list) { ret = perf_session__cpu_bitmap(session, ann->cpu_list, ann->cpu_bitmap); @@ -230,7 +247,7 @@ static int __cmd_annotate(struct perf_annotate *ann) if (nr_samples > 0) { total_nr_samples += nr_samples; - hists__collapse_resort(hists); + hists__collapse_resort(hists, NULL); hists__output_resort(hists); if (symbol_conf.event_group && @@ -242,12 +259,21 @@ static int __cmd_annotate(struct perf_annotate *ann) } if (total_nr_samples == 0) { - ui__error("The %s file has no samples!\n", session->filename); + ui__error("The %s file has no samples!\n", file.path); goto out_delete; } - if (use_browser == 2) - perf_gtk__show_annotations(); + if (use_browser == 2) { + void (*show_annotations)(void); + + show_annotations = dlsym(perf_gtk_handle, + "perf_gtk__show_annotations"); + if (show_annotations == NULL) { + ui__error("GTK browser not found!\n"); + goto out_delete; + } + show_annotations(); + } out_delete: /* @@ -276,6 +302,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) .tool = { .sample = process_sample_event, .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, .exit = perf_event__process_exit, .fork = perf_event__process_fork, diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index 77298bf892b..e47f90cc7b9 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -1,21 +1,18 @@ /* - * * builtin-bench.c * - * General benchmarking subsystem provided by perf + * General benchmarking collections provided by perf * * Copyright (C) 2009, Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> - * */ /* + * Available benchmark collection list: * - * Available subsystem list: - * sched ... scheduler and IPC mechanism + * sched ... scheduler and IPC performance * mem ... memory access performance - * + * numa ... NUMA scheduling and MM performance */ - #include "perf.h" #include "util/util.h" #include "util/parse-options.h" @@ -25,112 +22,92 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/prctl.h> -struct bench_suite { - const char *name; - const char *summary; - int (*fn)(int, const char **, const char *); +typedef int (*bench_fn_t)(int argc, const char **argv, const char *prefix); + +struct bench { + const char *name; + const char *summary; + bench_fn_t fn; }; - \ -/* sentinel: easy for help */ -#define suite_all { "all", "Test all benchmark suites", NULL } - -#ifdef LIBNUMA_SUPPORT -static struct bench_suite numa_suites[] = { - { "mem", - "Benchmark for NUMA workloads", - bench_numa }, - suite_all, - { NULL, - NULL, - NULL } + +#ifdef HAVE_LIBNUMA_SUPPORT +static struct bench numa_benchmarks[] = { + { "mem", "Benchmark for NUMA workloads", bench_numa }, + { "all", "Test all NUMA benchmarks", NULL }, + { NULL, NULL, NULL } }; #endif -static struct bench_suite sched_suites[] = { - { "messaging", - "Benchmark for scheduler and IPC mechanisms", - bench_sched_messaging }, - { "pipe", - "Flood of communication over pipe() between two processes", - bench_sched_pipe }, - suite_all, - { NULL, - NULL, - NULL } +static struct bench sched_benchmarks[] = { + { "messaging", "Benchmark for scheduling and IPC", bench_sched_messaging }, + { "pipe", "Benchmark for pipe() between two processes", bench_sched_pipe }, + { "all", "Test all scheduler benchmarks", NULL }, + { NULL, NULL, NULL } }; -static struct bench_suite mem_suites[] = { - { "memcpy", - "Simple memory copy in various ways", - bench_mem_memcpy }, - { "memset", - "Simple memory set in various ways", - bench_mem_memset }, - suite_all, - { NULL, - NULL, - NULL } +static struct bench mem_benchmarks[] = { + { "memcpy", "Benchmark for memcpy()", bench_mem_memcpy }, + { "memset", "Benchmark for memset() tests", bench_mem_memset }, + { "all", "Test all memory benchmarks", NULL }, + { NULL, NULL, NULL } }; -struct bench_subsys { - const char *name; - const char *summary; - struct bench_suite *suites; +struct collection { + const char *name; + const char *summary; + struct bench *benchmarks; }; -static struct bench_subsys subsystems[] = { -#ifdef LIBNUMA_SUPPORT - { "numa", - "NUMA scheduling and MM behavior", - numa_suites }, +static struct collection collections[] = { + { "sched", "Scheduler and IPC benchmarks", sched_benchmarks }, + { "mem", "Memory access benchmarks", mem_benchmarks }, +#ifdef HAVE_LIBNUMA_SUPPORT + { "numa", "NUMA scheduling and MM benchmarks", numa_benchmarks }, #endif - { "sched", - "scheduler and IPC mechanism", - sched_suites }, - { "mem", - "memory access performance", - mem_suites }, - { "all", /* sentinel: easy for help */ - "all benchmark subsystem", - NULL }, - { NULL, - NULL, - NULL } + { "all", "All benchmarks", NULL }, + { NULL, NULL, NULL } }; -static void dump_suites(int subsys_index) +/* Iterate over all benchmark collections: */ +#define for_each_collection(coll) \ + for (coll = collections; coll->name; coll++) + +/* Iterate over all benchmarks within a collection: */ +#define for_each_bench(coll, bench) \ + for (bench = coll->benchmarks; bench->name; bench++) + +static void dump_benchmarks(struct collection *coll) { - int i; + struct bench *bench; - printf("# List of available suites for %s...\n\n", - subsystems[subsys_index].name); + printf("\n # List of available benchmarks for collection '%s':\n\n", coll->name); - for (i = 0; subsystems[subsys_index].suites[i].name; i++) - printf("%14s: %s\n", - subsystems[subsys_index].suites[i].name, - subsystems[subsys_index].suites[i].summary); + for_each_bench(coll, bench) + printf("%14s: %s\n", bench->name, bench->summary); printf("\n"); - return; } static const char *bench_format_str; + +/* Output/formatting style, exported to benchmark modules: */ int bench_format = BENCH_FORMAT_DEFAULT; static const struct option bench_options[] = { - OPT_STRING('f', "format", &bench_format_str, "default", - "Specify format style"), + OPT_STRING('f', "format", &bench_format_str, "default", "Specify format style"), OPT_END() }; static const char * const bench_usage[] = { - "perf bench [<common options>] <subsystem> <suite> [<options>]", + "perf bench [<common options>] <collection> <benchmark> [<options>]", NULL }; static void print_usage(void) { + struct collection *coll; int i; printf("Usage: \n"); @@ -138,11 +115,10 @@ static void print_usage(void) printf("\t%s\n", bench_usage[i]); printf("\n"); - printf("# List of available subsystems...\n\n"); + printf(" # List of all available benchmark collections:\n\n"); - for (i = 0; subsystems[i].name; i++) - printf("%14s: %s\n", - subsystems[i].name, subsystems[i].summary); + for_each_collection(coll) + printf("%14s: %s\n", coll->name, coll->summary); printf("\n"); } @@ -159,44 +135,74 @@ static int bench_str2int(const char *str) return BENCH_FORMAT_UNKNOWN; } -static void all_suite(struct bench_subsys *subsys) /* FROM HERE */ +/* + * Run a specific benchmark but first rename the running task's ->comm[] + * to something meaningful: + */ +static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t fn, + int argc, const char **argv, const char *prefix) { - int i; + int size; + char *name; + int ret; + + size = strlen(coll_name) + 1 + strlen(bench_name) + 1; + + name = zalloc(size); + BUG_ON(!name); + + scnprintf(name, size, "%s-%s", coll_name, bench_name); + + prctl(PR_SET_NAME, name); + argv[0] = name; + + ret = fn(argc, argv, prefix); + + free(name); + + return ret; +} + +static void run_collection(struct collection *coll) +{ + struct bench *bench; const char *argv[2]; - struct bench_suite *suites = subsys->suites; argv[1] = NULL; /* * TODO: - * preparing preset parameters for + * + * Preparing preset parameters for * embedded, ordinary PC, HPC, etc... - * will be helpful + * would be helpful. */ - for (i = 0; suites[i].fn; i++) { - printf("# Running %s/%s benchmark...\n", - subsys->name, - suites[i].name); + for_each_bench(coll, bench) { + if (!bench->fn) + break; + printf("# Running %s/%s benchmark...\n", coll->name, bench->name); fflush(stdout); - argv[1] = suites[i].name; - suites[i].fn(1, argv, NULL); + argv[1] = bench->name; + run_bench(coll->name, bench->name, bench->fn, 1, argv, NULL); printf("\n"); } } -static void all_subsystem(void) +static void run_all_collections(void) { - int i; - for (i = 0; subsystems[i].suites; i++) - all_suite(&subsystems[i]); + struct collection *coll; + + for_each_collection(coll) + run_collection(coll); } int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused) { - int i, j, status = 0; + struct collection *coll; + int ret = 0; if (argc < 2) { - /* No subsystem specified. */ + /* No collection specified. */ print_usage(); goto end; } @@ -206,7 +212,7 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused) bench_format = bench_str2int(bench_format_str); if (bench_format == BENCH_FORMAT_UNKNOWN) { - printf("Unknown format descriptor:%s\n", bench_format_str); + printf("Unknown format descriptor: '%s'\n", bench_format_str); goto end; } @@ -216,52 +222,51 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused) } if (!strcmp(argv[0], "all")) { - all_subsystem(); + run_all_collections(); goto end; } - for (i = 0; subsystems[i].name; i++) { - if (strcmp(subsystems[i].name, argv[0])) + for_each_collection(coll) { + struct bench *bench; + + if (strcmp(coll->name, argv[0])) continue; if (argc < 2) { - /* No suite specified. */ - dump_suites(i); + /* No bench specified. */ + dump_benchmarks(coll); goto end; } if (!strcmp(argv[1], "all")) { - all_suite(&subsystems[i]); + run_collection(coll); goto end; } - for (j = 0; subsystems[i].suites[j].name; j++) { - if (strcmp(subsystems[i].suites[j].name, argv[1])) + for_each_bench(coll, bench) { + if (strcmp(bench->name, argv[1])) continue; if (bench_format == BENCH_FORMAT_DEFAULT) - printf("# Running %s/%s benchmark...\n", - subsystems[i].name, - subsystems[i].suites[j].name); + printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name); fflush(stdout); - status = subsystems[i].suites[j].fn(argc - 1, - argv + 1, prefix); + ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1, prefix); goto end; } if (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help")) { - dump_suites(i); + dump_benchmarks(coll); goto end; } - printf("Unknown suite:%s for %s\n", argv[1], argv[0]); - status = 1; + printf("Unknown benchmark: '%s' for collection '%s'\n", argv[1], argv[0]); + ret = 1; goto end; } - printf("Unknown subsystem:%s\n", argv[0]); - status = 1; + printf("Unknown collection: '%s'\n", argv[0]); + ret = 1; end: - return status; + return ret; } diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index c96c8fa3824..cfede86161d 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -6,6 +6,11 @@ * Copyright (C) 2010, Red Hat Inc. * Copyright (C) 2010, Arnaldo Carvalho de Melo <acme@redhat.com> */ +#include <sys/types.h> +#include <sys/time.h> +#include <time.h> +#include <dirent.h> +#include <unistd.h> #include "builtin.h" #include "perf.h" #include "util/cache.h" @@ -17,6 +22,140 @@ #include "util/session.h" #include "util/symbol.h" +static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid) +{ + char root_dir[PATH_MAX]; + char notes[PATH_MAX]; + u8 build_id[BUILD_ID_SIZE]; + char *p; + + strlcpy(root_dir, proc_dir, sizeof(root_dir)); + + p = strrchr(root_dir, '/'); + if (!p) + return -1; + *p = '\0'; + + scnprintf(notes, sizeof(notes), "%s/sys/kernel/notes", root_dir); + + if (sysfs__read_build_id(notes, build_id, sizeof(build_id))) + return -1; + + build_id__sprintf(build_id, sizeof(build_id), sbuildid); + + return 0; +} + +static int build_id_cache__kcore_dir(char *dir, size_t sz) +{ + struct timeval tv; + struct tm tm; + char dt[32]; + + if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm)) + return -1; + + if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm)) + return -1; + + scnprintf(dir, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000); + + return 0; +} + +static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir, + size_t to_dir_sz) +{ + char from[PATH_MAX]; + char to[PATH_MAX]; + struct dirent *dent; + int ret = -1; + DIR *d; + + d = opendir(to_dir); + if (!d) + return -1; + + scnprintf(from, sizeof(from), "%s/modules", from_dir); + + while (1) { + dent = readdir(d); + if (!dent) + break; + if (dent->d_type != DT_DIR) + continue; + scnprintf(to, sizeof(to), "%s/%s/modules", to_dir, + dent->d_name); + if (!compare_proc_modules(from, to)) { + scnprintf(to, sizeof(to), "%s/%s", to_dir, + dent->d_name); + strlcpy(to_dir, to, to_dir_sz); + ret = 0; + break; + } + } + + closedir(d); + + return ret; +} + +static int build_id_cache__add_kcore(const char *filename, const char *debugdir) +{ + char dir[32], sbuildid[BUILD_ID_SIZE * 2 + 1]; + char from_dir[PATH_MAX], to_dir[PATH_MAX]; + char *p; + + strlcpy(from_dir, filename, sizeof(from_dir)); + + p = strrchr(from_dir, '/'); + if (!p || strcmp(p + 1, "kcore")) + return -1; + *p = '\0'; + + if (build_id_cache__kcore_buildid(from_dir, sbuildid)) + return -1; + + scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s", + debugdir, sbuildid); + + if (!build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) { + pr_debug("same kcore found in %s\n", to_dir); + return 0; + } + + if (build_id_cache__kcore_dir(dir, sizeof(dir))) + return -1; + + scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s/%s", + debugdir, sbuildid, dir); + + if (mkdir_p(to_dir, 0755)) + return -1; + + if (kcore_copy(from_dir, to_dir)) { + /* Remove YYYYmmddHHMMSShh directory */ + if (!rmdir(to_dir)) { + p = strrchr(to_dir, '/'); + if (p) + *p = '\0'; + /* Try to remove buildid directory */ + if (!rmdir(to_dir)) { + p = strrchr(to_dir, '/'); + if (p) + *p = '\0'; + /* Try to remove [kernel.kcore] directory */ + rmdir(to_dir); + } + } + return -1; + } + + pr_debug("kcore added to build-id cache directory %s\n", to_dir); + + return 0; +} + static int build_id_cache__add_file(const char *filename, const char *debugdir) { char sbuild_id[BUILD_ID_SIZE * 2 + 1]; @@ -82,8 +221,12 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp) { - struct perf_session *session = perf_session__new(filename, O_RDONLY, - force, false, NULL); + struct perf_data_file file = { + .path = filename, + .mode = PERF_DATA_MODE_READ, + .force = force, + }; + struct perf_session *session = perf_session__new(&file, false, NULL); if (session == NULL) return -1; @@ -130,11 +273,14 @@ int cmd_buildid_cache(int argc, const char **argv, char const *add_name_list_str = NULL, *remove_name_list_str = NULL, *missing_filename = NULL, - *update_name_list_str = NULL; + *update_name_list_str = NULL, + *kcore_filename; const struct option buildid_cache_options[] = { OPT_STRING('a', "add", &add_name_list_str, "file list", "file(s) to add"), + OPT_STRING('k', "kcore", &kcore_filename, + "file", "kcore file to add"), OPT_STRING('r', "remove", &remove_name_list_str, "file list", "file(s) to remove"), OPT_STRING('M', "missing", &missing_filename, "file", @@ -217,5 +363,9 @@ int cmd_buildid_cache(int argc, const char **argv, } } + if (kcore_filename && + build_id_cache__add_kcore(kcore_filename, debugdir)) + pr_warning("Couldn't add %s\n", kcore_filename); + return ret; } diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index e74366a1321..ed3873b3e23 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -15,6 +15,7 @@ #include "util/parse-options.h" #include "util/session.h" #include "util/symbol.h" +#include "util/data.h" static int sysfs__fprintf_build_id(FILE *fp) { @@ -52,6 +53,11 @@ static bool dso__skip_buildid(struct dso *dso, int with_hits) static int perf_session__list_build_ids(bool force, bool with_hits) { struct perf_session *session; + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + .force = force, + }; symbol__elf_init(); /* @@ -60,15 +66,14 @@ static int perf_session__list_build_ids(bool force, bool with_hits) if (filename__fprintf_build_id(input_name, stdout)) goto out; - session = perf_session__new(input_name, O_RDONLY, force, false, - &build_id__mark_dso_hit_ops); + session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops); if (session == NULL) return -1; /* * in pipe-mode, the only way to get the buildids is to parse * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID */ - if (with_hits || session->fd_pipe) + if (with_hits || perf_data_file__is_pipe(&file)) perf_session__process_events(session, &build_id__mark_dso_hit_ops); perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits); diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 0aac5f3e594..3b67ea2444b 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -16,17 +16,56 @@ #include "util/sort.h" #include "util/symbol.h" #include "util/util.h" +#include "util/data.h" #include <stdlib.h> +#include <math.h> -static char const *input_old = "perf.data.old", - *input_new = "perf.data"; -static char diff__default_sort_order[] = "dso,symbol"; -static bool force; +/* Diff command specific HPP columns. */ +enum { + PERF_HPP_DIFF__BASELINE, + PERF_HPP_DIFF__PERIOD, + PERF_HPP_DIFF__PERIOD_BASELINE, + PERF_HPP_DIFF__DELTA, + PERF_HPP_DIFF__RATIO, + PERF_HPP_DIFF__WEIGHTED_DIFF, + PERF_HPP_DIFF__FORMULA, + + PERF_HPP_DIFF__MAX_INDEX +}; + +struct diff_hpp_fmt { + struct perf_hpp_fmt fmt; + int idx; + char *header; + int header_width; +}; + +struct data__file { + struct perf_session *session; + struct perf_data_file file; + int idx; + struct hists *hists; + struct diff_hpp_fmt fmt[PERF_HPP_DIFF__MAX_INDEX]; +}; + +static struct data__file *data__files; +static int data__files_cnt; + +#define data__for_each_file_start(i, d, s) \ + for (i = s, d = &data__files[s]; \ + i < data__files_cnt; \ + i++, d = &data__files[i]) + +#define data__for_each_file(i, d) data__for_each_file_start(i, d, 0) +#define data__for_each_file_new(i, d) data__for_each_file_start(i, d, 1) + +static char diff__default_sort_order[] = "dso,symbol"; +static bool force; static bool show_period; static bool show_formula; static bool show_baseline_only; -static bool sort_compute; +static unsigned int sort_compute; static s64 compute_wdiff_w1; static s64 compute_wdiff_w2; @@ -46,6 +85,47 @@ const char *compute_names[COMPUTE_MAX] = { static int compute; +static int compute_2_hpp[COMPUTE_MAX] = { + [COMPUTE_DELTA] = PERF_HPP_DIFF__DELTA, + [COMPUTE_RATIO] = PERF_HPP_DIFF__RATIO, + [COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF, +}; + +#define MAX_COL_WIDTH 70 + +static struct header_column { + const char *name; + int width; +} columns[PERF_HPP_DIFF__MAX_INDEX] = { + [PERF_HPP_DIFF__BASELINE] = { + .name = "Baseline", + }, + [PERF_HPP_DIFF__PERIOD] = { + .name = "Period", + .width = 14, + }, + [PERF_HPP_DIFF__PERIOD_BASELINE] = { + .name = "Base period", + .width = 14, + }, + [PERF_HPP_DIFF__DELTA] = { + .name = "Delta", + .width = 7, + }, + [PERF_HPP_DIFF__RATIO] = { + .name = "Ratio", + .width = 14, + }, + [PERF_HPP_DIFF__WEIGHTED_DIFF] = { + .name = "Weighted diff", + .width = 14, + }, + [PERF_HPP_DIFF__FORMULA] = { + .name = "Formula", + .width = MAX_COL_WIDTH, + } +}; + static int setup_compute_opt_wdiff(char *opt) { char *w1_str = opt; @@ -109,13 +189,6 @@ static int setup_compute(const struct option *opt, const char *str, return 0; } - if (*str == '+') { - sort_compute = true; - cstr = (char *) ++str; - if (!*str) - return 0; - } - option = strchr(str, ':'); if (option) { unsigned len = option++ - str; @@ -145,42 +218,42 @@ static int setup_compute(const struct option *opt, const char *str, return -EINVAL; } -double perf_diff__period_percent(struct hist_entry *he, u64 period) +static double period_percent(struct hist_entry *he, u64 period) { u64 total = he->hists->stats.total_period; return (period * 100.0) / total; } -double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair) +static double compute_delta(struct hist_entry *he, struct hist_entry *pair) { - double new_percent = perf_diff__period_percent(he, he->stat.period); - double old_percent = perf_diff__period_percent(pair, pair->stat.period); + double old_percent = period_percent(he, he->stat.period); + double new_percent = period_percent(pair, pair->stat.period); - he->diff.period_ratio_delta = new_percent - old_percent; - he->diff.computed = true; - return he->diff.period_ratio_delta; + pair->diff.period_ratio_delta = new_percent - old_percent; + pair->diff.computed = true; + return pair->diff.period_ratio_delta; } -double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair) +static double compute_ratio(struct hist_entry *he, struct hist_entry *pair) { - double new_period = he->stat.period; - double old_period = pair->stat.period; + double old_period = he->stat.period ?: 1; + double new_period = pair->stat.period; - he->diff.computed = true; - he->diff.period_ratio = new_period / old_period; - return he->diff.period_ratio; + pair->diff.computed = true; + pair->diff.period_ratio = new_period / old_period; + return pair->diff.period_ratio; } -s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair) +static s64 compute_wdiff(struct hist_entry *he, struct hist_entry *pair) { - u64 new_period = he->stat.period; - u64 old_period = pair->stat.period; + u64 old_period = he->stat.period; + u64 new_period = pair->stat.period; - he->diff.computed = true; - he->diff.wdiff = new_period * compute_wdiff_w2 - - old_period * compute_wdiff_w1; + pair->diff.computed = true; + pair->diff.wdiff = new_period * compute_wdiff_w2 - + old_period * compute_wdiff_w1; - return he->diff.wdiff; + return pair->diff.wdiff; } static int formula_delta(struct hist_entry *he, struct hist_entry *pair, @@ -189,15 +262,15 @@ static int formula_delta(struct hist_entry *he, struct hist_entry *pair, return scnprintf(buf, size, "(%" PRIu64 " * 100 / %" PRIu64 ") - " "(%" PRIu64 " * 100 / %" PRIu64 ")", - he->stat.period, he->hists->stats.total_period, - pair->stat.period, pair->hists->stats.total_period); + pair->stat.period, pair->hists->stats.total_period, + he->stat.period, he->hists->stats.total_period); } static int formula_ratio(struct hist_entry *he, struct hist_entry *pair, char *buf, size_t size) { - double new_period = he->stat.period; - double old_period = pair->stat.period; + double old_period = he->stat.period; + double new_period = pair->stat.period; return scnprintf(buf, size, "%.0F / %.0F", new_period, old_period); } @@ -205,16 +278,16 @@ static int formula_ratio(struct hist_entry *he, struct hist_entry *pair, static int formula_wdiff(struct hist_entry *he, struct hist_entry *pair, char *buf, size_t size) { - u64 new_period = he->stat.period; - u64 old_period = pair->stat.period; + u64 old_period = he->stat.period; + u64 new_period = pair->stat.period; return scnprintf(buf, size, "(%" PRIu64 " * " "%" PRId64 ") - (%" PRIu64 " * " "%" PRId64 ")", new_period, compute_wdiff_w2, old_period, compute_wdiff_w1); } -int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair, - char *buf, size_t size) +static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair, + char *buf, size_t size) { switch (compute) { case COMPUTE_DELTA: @@ -230,11 +303,12 @@ int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair, return -1; } -static int hists__add_entry(struct hists *self, +static int hists__add_entry(struct hists *hists, struct addr_location *al, u64 period, - u64 weight) + u64 weight, u64 transaction) { - if (__hists__add_entry(self, al, NULL, period, weight) != NULL) + if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight, + transaction) != NULL) return 0; return -ENOMEM; } @@ -247,7 +321,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, { struct addr_location al; - if (perf_event__preprocess_sample(event, machine, &al, sample, NULL) < 0) { + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { pr_warning("problem processing %d event, skipping it.\n", event->header.type); return -1; @@ -256,7 +330,8 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, if (al.filtered) return 0; - if (hists__add_entry(&evsel->hists, &al, sample->period, sample->weight)) { + if (hists__add_entry(&evsel->hists, &al, sample->period, + sample->weight, sample->transaction)) { pr_warning("problem incrementing symbol period, skipping event\n"); return -1; } @@ -295,8 +370,31 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist) list_for_each_entry(evsel, &evlist->entries, node) { struct hists *hists = &evsel->hists; - hists__collapse_resort(hists); + hists__collapse_resort(hists, NULL); + } +} + +static struct hist_entry* +get_pair_data(struct hist_entry *he, struct data__file *d) +{ + if (hist_entry__has_pairs(he)) { + struct hist_entry *pair; + + list_for_each_entry(pair, &he->pairs.head, pairs.node) + if (pair->hists == d->hists) + return pair; } + + return NULL; +} + +static struct hist_entry* +get_pair_fmt(struct hist_entry *he, struct diff_hpp_fmt *dfmt) +{ + void *ptr = dfmt - dfmt->idx; + struct data__file *d = container_of(ptr, struct data__file, fmt); + + return get_pair_data(he, d); } static void hists__baseline_only(struct hists *hists) @@ -333,22 +431,24 @@ static void hists__precompute(struct hists *hists) next = rb_first(root); while (next != NULL) { - struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in); - struct hist_entry *pair = hist_entry__next_pair(he); + struct hist_entry *he, *pair; + he = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&he->rb_node_in); + + pair = get_pair_data(he, &data__files[sort_compute]); if (!pair) continue; switch (compute) { case COMPUTE_DELTA: - perf_diff__compute_delta(he, pair); + compute_delta(he, pair); break; case COMPUTE_RATIO: - perf_diff__compute_ratio(he, pair); + compute_ratio(he, pair); break; case COMPUTE_WEIGHTED_DIFF: - perf_diff__compute_wdiff(he, pair); + compute_wdiff(he, pair); break; default: BUG_ON(1); @@ -367,7 +467,7 @@ static int64_t cmp_doubles(double l, double r) } static int64_t -hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, +__hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, int c) { switch (c) { @@ -399,6 +499,36 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, return 0; } +static int64_t +hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, + int c) +{ + bool pairs_left = hist_entry__has_pairs(left); + bool pairs_right = hist_entry__has_pairs(right); + struct hist_entry *p_right, *p_left; + + if (!pairs_left && !pairs_right) + return 0; + + if (!pairs_left || !pairs_right) + return pairs_left ? -1 : 1; + + p_left = get_pair_data(left, &data__files[sort_compute]); + p_right = get_pair_data(right, &data__files[sort_compute]); + + if (!p_left && !p_right) + return 0; + + if (!p_left || !p_right) + return p_left ? -1 : 1; + + /* + * We have 2 entries of same kind, let's + * make the data comparison. + */ + return __hist_entry__cmp_compute(p_left, p_right, c); +} + static void insert_hist_entry_by_compute(struct rb_root *root, struct hist_entry *he, int c) @@ -448,75 +578,120 @@ static void hists__compute_resort(struct hists *hists) } } -static void hists__process(struct hists *old, struct hists *new) +static void hists__process(struct hists *hists) { - hists__match(new, old); - if (show_baseline_only) - hists__baseline_only(new); - else - hists__link(new, old); + hists__baseline_only(hists); if (sort_compute) { - hists__precompute(new); - hists__compute_resort(new); + hists__precompute(hists); + hists__compute_resort(hists); } else { - hists__output_resort(new); + hists__output_resort(hists); } - hists__fprintf(new, true, 0, 0, 0, stdout); + hists__fprintf(hists, true, 0, 0, 0, stdout); } -static int __cmd_diff(void) +static void data__fprintf(void) { - int ret, i; -#define older (session[0]) -#define newer (session[1]) - struct perf_session *session[2]; - struct perf_evlist *evlist_new, *evlist_old; - struct perf_evsel *evsel; + struct data__file *d; + int i; + + fprintf(stdout, "# Data files:\n"); + + data__for_each_file(i, d) + fprintf(stdout, "# [%d] %s %s\n", + d->idx, d->file.path, + !d->idx ? "(Baseline)" : ""); + + fprintf(stdout, "#\n"); +} + +static void data_process(void) +{ + struct perf_evlist *evlist_base = data__files[0].session->evlist; + struct perf_evsel *evsel_base; bool first = true; - older = perf_session__new(input_old, O_RDONLY, force, false, - &tool); - newer = perf_session__new(input_new, O_RDONLY, force, false, - &tool); - if (session[0] == NULL || session[1] == NULL) - return -ENOMEM; + list_for_each_entry(evsel_base, &evlist_base->entries, node) { + struct data__file *d; + int i; - for (i = 0; i < 2; ++i) { - ret = perf_session__process_events(session[i], &tool); - if (ret) - goto out_delete; - } + data__for_each_file_new(i, d) { + struct perf_evlist *evlist = d->session->evlist; + struct perf_evsel *evsel; - evlist_old = older->evlist; - evlist_new = newer->evlist; + evsel = evsel_match(evsel_base, evlist); + if (!evsel) + continue; - perf_evlist__collapse_resort(evlist_old); - perf_evlist__collapse_resort(evlist_new); + d->hists = &evsel->hists; - list_for_each_entry(evsel, &evlist_new->entries, node) { - struct perf_evsel *evsel_old; + hists__match(&evsel_base->hists, &evsel->hists); - evsel_old = evsel_match(evsel, evlist_old); - if (!evsel_old) - continue; + if (!show_baseline_only) + hists__link(&evsel_base->hists, + &evsel->hists); + } fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n", - perf_evsel__name(evsel)); + perf_evsel__name(evsel_base)); first = false; - hists__process(&evsel_old->hists, &evsel->hists); + if (verbose || data__files_cnt > 2) + data__fprintf(); + + hists__process(&evsel_base->hists); + } +} + +static void data__free(struct data__file *d) +{ + int col; + + for (col = 0; col < PERF_HPP_DIFF__MAX_INDEX; col++) { + struct diff_hpp_fmt *fmt = &d->fmt[col]; + + free(fmt->header); + } +} + +static int __cmd_diff(void) +{ + struct data__file *d; + int ret = -EINVAL, i; + + data__for_each_file(i, d) { + d->session = perf_session__new(&d->file, false, &tool); + if (!d->session) { + pr_err("Failed to open %s\n", d->file.path); + ret = -ENOMEM; + goto out_delete; + } + + ret = perf_session__process_events(d->session, &tool); + if (ret) { + pr_err("Failed to process %s\n", d->file.path); + goto out_delete; + } + + perf_evlist__collapse_resort(d->session->evlist); + } + + data_process(); + + out_delete: + data__for_each_file(i, d) { + if (d->session) + perf_session__delete(d->session); + + data__free(d); } -out_delete: - for (i = 0; i < 2; ++i) - perf_session__delete(session[i]); + free(data__files); return ret; -#undef older -#undef newer } static const char * const diff_usage[] = { @@ -555,61 +730,315 @@ static const struct option options[] = { "columns '.' is reserved."), OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", "Look for files with symbols relative to this directory"), + OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."), OPT_END() }; -static void ui_init(void) +static double baseline_percent(struct hist_entry *he) { - /* - * Display baseline/delta/ratio - * formula/periods columns. - */ - perf_hpp__column_enable(PERF_HPP__BASELINE); + struct hists *hists = he->hists; + return 100.0 * he->stat.period / hists->stats.total_period; +} - switch (compute) { - case COMPUTE_DELTA: - perf_hpp__column_enable(PERF_HPP__DELTA); +static int hpp__color_baseline(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, struct hist_entry *he) +{ + struct diff_hpp_fmt *dfmt = + container_of(fmt, struct diff_hpp_fmt, fmt); + double percent = baseline_percent(he); + char pfmt[20] = " "; + + if (!he->dummy) { + scnprintf(pfmt, 20, "%%%d.2f%%%%", dfmt->header_width - 1); + return percent_color_snprintf(hpp->buf, hpp->size, + pfmt, percent); + } else + return scnprintf(hpp->buf, hpp->size, "%*s", + dfmt->header_width, pfmt); +} + +static int hpp__entry_baseline(struct hist_entry *he, char *buf, size_t size) +{ + double percent = baseline_percent(he); + const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%"; + int ret = 0; + + if (!he->dummy) + ret = scnprintf(buf, size, fmt, percent); + + return ret; +} + +static void +hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size) +{ + switch (idx) { + case PERF_HPP_DIFF__PERIOD_BASELINE: + scnprintf(buf, size, "%" PRIu64, he->stat.period); break; - case COMPUTE_RATIO: - perf_hpp__column_enable(PERF_HPP__RATIO); + + default: break; - case COMPUTE_WEIGHTED_DIFF: - perf_hpp__column_enable(PERF_HPP__WEIGHTED_DIFF); + } +} + +static void +hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair, + int idx, char *buf, size_t size) +{ + double diff; + double ratio; + s64 wdiff; + + switch (idx) { + case PERF_HPP_DIFF__DELTA: + if (pair->diff.computed) + diff = pair->diff.period_ratio_delta; + else + diff = compute_delta(he, pair); + + if (fabs(diff) >= 0.01) + scnprintf(buf, size, "%+4.2F%%", diff); + break; + + case PERF_HPP_DIFF__RATIO: + /* No point for ratio number if we are dummy.. */ + if (he->dummy) + break; + + if (pair->diff.computed) + ratio = pair->diff.period_ratio; + else + ratio = compute_ratio(he, pair); + + if (ratio > 0.0) + scnprintf(buf, size, "%14.6F", ratio); + break; + + case PERF_HPP_DIFF__WEIGHTED_DIFF: + /* No point for wdiff number if we are dummy.. */ + if (he->dummy) + break; + + if (pair->diff.computed) + wdiff = pair->diff.wdiff; + else + wdiff = compute_wdiff(he, pair); + + if (wdiff != 0) + scnprintf(buf, size, "%14ld", wdiff); + break; + + case PERF_HPP_DIFF__FORMULA: + formula_fprintf(he, pair, buf, size); + break; + + case PERF_HPP_DIFF__PERIOD: + scnprintf(buf, size, "%" PRIu64, pair->stat.period); break; + default: BUG_ON(1); }; +} + +static void +__hpp__entry_global(struct hist_entry *he, struct diff_hpp_fmt *dfmt, + char *buf, size_t size) +{ + struct hist_entry *pair = get_pair_fmt(he, dfmt); + int idx = dfmt->idx; + + /* baseline is special */ + if (idx == PERF_HPP_DIFF__BASELINE) + hpp__entry_baseline(he, buf, size); + else { + if (pair) + hpp__entry_pair(he, pair, idx, buf, size); + else + hpp__entry_unpair(he, idx, buf, size); + } +} + +static int hpp__entry_global(struct perf_hpp_fmt *_fmt, struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct diff_hpp_fmt *dfmt = + container_of(_fmt, struct diff_hpp_fmt, fmt); + char buf[MAX_COL_WIDTH] = " "; + + __hpp__entry_global(he, dfmt, buf, MAX_COL_WIDTH); + + if (symbol_conf.field_sep) + return scnprintf(hpp->buf, hpp->size, "%s", buf); + else + return scnprintf(hpp->buf, hpp->size, "%*s", + dfmt->header_width, buf); +} + +static int hpp__header(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp) +{ + struct diff_hpp_fmt *dfmt = + container_of(fmt, struct diff_hpp_fmt, fmt); + + BUG_ON(!dfmt->header); + return scnprintf(hpp->buf, hpp->size, dfmt->header); +} + +static int hpp__width(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp __maybe_unused) +{ + struct diff_hpp_fmt *dfmt = + container_of(fmt, struct diff_hpp_fmt, fmt); + + BUG_ON(dfmt->header_width <= 0); + return dfmt->header_width; +} + +static void init_header(struct data__file *d, struct diff_hpp_fmt *dfmt) +{ +#define MAX_HEADER_NAME 100 + char buf_indent[MAX_HEADER_NAME]; + char buf[MAX_HEADER_NAME]; + const char *header = NULL; + int width = 0; + + BUG_ON(dfmt->idx >= PERF_HPP_DIFF__MAX_INDEX); + header = columns[dfmt->idx].name; + width = columns[dfmt->idx].width; + + /* Only our defined HPP fmts should appear here. */ + BUG_ON(!header); + + if (data__files_cnt > 2) + scnprintf(buf, MAX_HEADER_NAME, "%s/%d", header, d->idx); + +#define NAME (data__files_cnt > 2 ? buf : header) + dfmt->header_width = width; + width = (int) strlen(NAME); + if (dfmt->header_width < width) + dfmt->header_width = width; + + scnprintf(buf_indent, MAX_HEADER_NAME, "%*s", + dfmt->header_width, NAME); + + dfmt->header = strdup(buf_indent); +#undef MAX_HEADER_NAME +#undef NAME +} + +static void data__hpp_register(struct data__file *d, int idx) +{ + struct diff_hpp_fmt *dfmt = &d->fmt[idx]; + struct perf_hpp_fmt *fmt = &dfmt->fmt; + + dfmt->idx = idx; + + fmt->header = hpp__header; + fmt->width = hpp__width; + fmt->entry = hpp__entry_global; + + /* TODO more colors */ + if (idx == PERF_HPP_DIFF__BASELINE) + fmt->color = hpp__color_baseline; + + init_header(d, dfmt); + perf_hpp__column_register(fmt); +} + +static void ui_init(void) +{ + struct data__file *d; + int i; + + data__for_each_file(i, d) { + + /* + * Baseline or compute realted columns: + * + * PERF_HPP_DIFF__BASELINE + * PERF_HPP_DIFF__DELTA + * PERF_HPP_DIFF__RATIO + * PERF_HPP_DIFF__WEIGHTED_DIFF + */ + data__hpp_register(d, i ? compute_2_hpp[compute] : + PERF_HPP_DIFF__BASELINE); - if (show_formula) - perf_hpp__column_enable(PERF_HPP__FORMULA); + /* + * And the rest: + * + * PERF_HPP_DIFF__FORMULA + * PERF_HPP_DIFF__PERIOD + * PERF_HPP_DIFF__PERIOD_BASELINE + */ + if (show_formula && i) + data__hpp_register(d, PERF_HPP_DIFF__FORMULA); - if (show_period) { - perf_hpp__column_enable(PERF_HPP__PERIOD); - perf_hpp__column_enable(PERF_HPP__PERIOD_BASELINE); + if (show_period) + data__hpp_register(d, i ? PERF_HPP_DIFF__PERIOD : + PERF_HPP_DIFF__PERIOD_BASELINE); } } -int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) +static int data_init(int argc, const char **argv) { - sort_order = diff__default_sort_order; - argc = parse_options(argc, argv, options, diff_usage, 0); + struct data__file *d; + static const char *defaults[] = { + "perf.data.old", + "perf.data", + }; + bool use_default = true; + int i; + + data__files_cnt = 2; + if (argc) { - if (argc > 2) - usage_with_options(diff_usage, options); - if (argc == 2) { - input_old = argv[0]; - input_new = argv[1]; - } else - input_new = argv[0]; + if (argc == 1) + defaults[1] = argv[0]; + else { + data__files_cnt = argc; + use_default = false; + } } else if (symbol_conf.default_guest_vmlinux_name || symbol_conf.default_guest_kallsyms) { - input_old = "perf.data.host"; - input_new = "perf.data.guest"; + defaults[0] = "perf.data.host"; + defaults[1] = "perf.data.guest"; + } + + if (sort_compute >= (unsigned int) data__files_cnt) { + pr_err("Order option out of limit.\n"); + return -EINVAL; + } + + data__files = zalloc(sizeof(*data__files) * data__files_cnt); + if (!data__files) + return -ENOMEM; + + data__for_each_file(i, d) { + struct perf_data_file *file = &d->file; + + file->path = use_default ? defaults[i] : argv[i]; + file->mode = PERF_DATA_MODE_READ, + file->force = force, + + d->idx = i; } + return 0; +} + +int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) +{ + sort_order = diff__default_sort_order; + argc = parse_options(argc, argv, options, diff_usage, 0); + if (symbol__init() < 0) return -1; + if (data_init(argc, argv) < 0) + return -1; + ui_init(); if (setup_sorting() < 0) diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index 05bd9dfe875..20b0f12763b 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -14,13 +14,18 @@ #include "util/parse-events.h" #include "util/parse-options.h" #include "util/session.h" +#include "util/data.h" static int __cmd_evlist(const char *file_name, struct perf_attr_details *details) { struct perf_session *session; struct perf_evsel *pos; + struct perf_data_file file = { + .path = file_name, + .mode = PERF_DATA_MODE_READ, + }; - session = perf_session__new(file_name, O_RDONLY, 0, false, NULL); + session = perf_session__new(&file, 0, NULL); if (session == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 84ad6abe425..6a250858946 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -15,6 +15,7 @@ #include "util/tool.h" #include "util/debug.h" #include "util/build-id.h" +#include "util/data.h" #include "util/parse-options.h" @@ -38,8 +39,7 @@ struct event_entry { }; static int perf_event__repipe_synth(struct perf_tool *tool, - union perf_event *event, - struct machine *machine __maybe_unused) + union perf_event *event) { struct perf_inject *inject = container_of(tool, struct perf_inject, tool); uint32_t size; @@ -65,39 +65,33 @@ static int perf_event__repipe_op2_synth(struct perf_tool *tool, struct perf_session *session __maybe_unused) { - return perf_event__repipe_synth(tool, event, NULL); + return perf_event__repipe_synth(tool, event); } -static int perf_event__repipe_event_type_synth(struct perf_tool *tool, - union perf_event *event) -{ - return perf_event__repipe_synth(tool, event, NULL); -} - -static int perf_event__repipe_tracing_data_synth(union perf_event *event, - struct perf_session *session - __maybe_unused) -{ - return perf_event__repipe_synth(NULL, event, NULL); -} - -static int perf_event__repipe_attr(union perf_event *event, - struct perf_evlist **pevlist __maybe_unused) +static int perf_event__repipe_attr(struct perf_tool *tool, + union perf_event *event, + struct perf_evlist **pevlist) { + struct perf_inject *inject = container_of(tool, struct perf_inject, + tool); int ret; - ret = perf_event__process_attr(event, pevlist); + + ret = perf_event__process_attr(tool, event, pevlist); if (ret) return ret; - return perf_event__repipe_synth(NULL, event, NULL); + if (!inject->pipe_output) + return 0; + + return perf_event__repipe_synth(tool, event); } static int perf_event__repipe(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample __maybe_unused, - struct machine *machine) + struct machine *machine __maybe_unused) { - return perf_event__repipe_synth(tool, event, machine); + return perf_event__repipe_synth(tool, event); } typedef int (*inject_handler)(struct perf_tool *tool, @@ -112,14 +106,14 @@ static int perf_event__repipe_sample(struct perf_tool *tool, struct perf_evsel *evsel, struct machine *machine) { - if (evsel->handler.func) { - inject_handler f = evsel->handler.func; + if (evsel->handler) { + inject_handler f = evsel->handler; return f(tool, event, sample, evsel, machine); } build_id__mark_dso_hit(tool, event, sample, evsel, machine); - return perf_event__repipe_synth(tool, event, machine); + return perf_event__repipe_synth(tool, event); } static int perf_event__repipe_mmap(struct perf_tool *tool, @@ -135,6 +129,19 @@ static int perf_event__repipe_mmap(struct perf_tool *tool, return err; } +static int perf_event__repipe_mmap2(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + int err; + + err = perf_event__process_mmap2(tool, event, sample, machine); + perf_event__repipe(tool, event, sample, machine); + + return err; +} + static int perf_event__repipe_fork(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -148,49 +155,50 @@ static int perf_event__repipe_fork(struct perf_tool *tool, return err; } -static int perf_event__repipe_tracing_data(union perf_event *event, +static int perf_event__repipe_tracing_data(struct perf_tool *tool, + union perf_event *event, struct perf_session *session) { int err; - perf_event__repipe_synth(NULL, event, NULL); - err = perf_event__process_tracing_data(event, session); + perf_event__repipe_synth(tool, event); + err = perf_event__process_tracing_data(tool, event, session); return err; } -static int dso__read_build_id(struct dso *self) +static int dso__read_build_id(struct dso *dso) { - if (self->has_build_id) + if (dso->has_build_id) return 0; - if (filename__read_build_id(self->long_name, self->build_id, - sizeof(self->build_id)) > 0) { - self->has_build_id = true; + if (filename__read_build_id(dso->long_name, dso->build_id, + sizeof(dso->build_id)) > 0) { + dso->has_build_id = true; return 0; } return -1; } -static int dso__inject_build_id(struct dso *self, struct perf_tool *tool, +static int dso__inject_build_id(struct dso *dso, struct perf_tool *tool, struct machine *machine) { u16 misc = PERF_RECORD_MISC_USER; int err; - if (dso__read_build_id(self) < 0) { - pr_debug("no build_id found for %s\n", self->long_name); + if (dso__read_build_id(dso) < 0) { + pr_debug("no build_id found for %s\n", dso->long_name); return -1; } - if (self->kernel) + if (dso->kernel) misc = PERF_RECORD_MISC_KERNEL; - err = perf_event__synthesize_build_id(tool, self, misc, perf_event__repipe, + err = perf_event__synthesize_build_id(tool, dso, misc, perf_event__repipe, machine); if (err) { - pr_err("Can't synthesize build_id event for %s\n", self->long_name); + pr_err("Can't synthesize build_id event for %s\n", dso->long_name); return -1; } @@ -209,7 +217,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - thread = machine__findnew_thread(machine, event->ip.pid); + thread = machine__findnew_thread(machine, sample->pid, sample->pid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", event->header.type); @@ -217,7 +225,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, } thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - event->ip.ip, &al); + sample->ip, &al); if (al.map != NULL) { if (!al.map->dso->hit) { @@ -229,7 +237,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool, * account this as unresolved. */ } else { -#ifdef LIBELF_SUPPORT +#ifdef HAVE_LIBELF_SUPPORT pr_warning("no symbols found in %s, maybe " "install a debug package?\n", al.map->dso->long_name); @@ -312,13 +320,13 @@ found: sample_sw.period = sample->period; sample_sw.time = sample->time; perf_event__synthesize_sample(event_sw, evsel->attr.sample_type, - &sample_sw, false); + evsel->attr.sample_regs_user, + evsel->attr.read_format, &sample_sw, + false); build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine); return perf_event__repipe(tool, event_sw, &sample_sw, machine); } -extern volatile int session_done; - static void sig_handler(int sig __maybe_unused) { session_done = 1; @@ -343,16 +351,21 @@ static int __cmd_inject(struct perf_inject *inject) { struct perf_session *session; int ret = -EINVAL; + struct perf_data_file file = { + .path = inject->input_name, + .mode = PERF_DATA_MODE_READ, + }; signal(SIGINT, sig_handler); if (inject->build_ids || inject->sched_stat) { inject->tool.mmap = perf_event__repipe_mmap; + inject->tool.mmap2 = perf_event__repipe_mmap2; inject->tool.fork = perf_event__repipe_fork; inject->tool.tracing_data = perf_event__repipe_tracing_data; } - session = perf_session__new(inject->input_name, O_RDONLY, false, true, &inject->tool); + session = perf_session__new(&file, true, &inject->tool); if (session == NULL) return -ENOMEM; @@ -370,11 +383,11 @@ static int __cmd_inject(struct perf_inject *inject) if (perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID")) return -EINVAL; - evsel->handler.func = perf_inject__sched_switch; + evsel->handler = perf_inject__sched_switch; } else if (!strcmp(name, "sched:sched_process_exit")) - evsel->handler.func = perf_inject__sched_process_exit; + evsel->handler = perf_inject__sched_process_exit; else if (!strncmp(name, "sched:sched_stat_", 17)) - evsel->handler.func = perf_inject__sched_stat; + evsel->handler = perf_inject__sched_stat; } } @@ -399,6 +412,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) .tool = { .sample = perf_event__repipe_sample, .mmap = perf_event__repipe, + .mmap2 = perf_event__repipe, .comm = perf_event__repipe, .fork = perf_event__repipe, .exit = perf_event__repipe, @@ -407,8 +421,8 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) .throttle = perf_event__repipe, .unthrottle = perf_event__repipe, .attr = perf_event__repipe_attr, - .event_type = perf_event__repipe_event_type_synth, - .tracing_data = perf_event__repipe_tracing_data_synth, + .tracing_data = perf_event__repipe_op2_synth, + .finished_round = perf_event__repipe_op2_synth, .build_id = perf_event__repipe_op2_synth, }, .input_name = "-", diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 0259502638b..929462aa494 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -13,6 +13,7 @@ #include "util/parse-options.h" #include "util/trace-event.h" +#include "util/data.h" #include "util/debug.h" @@ -101,7 +102,7 @@ static int setup_cpunode_map(void) dir1 = opendir(PATH_SYS_NODE); if (!dir1) - return -1; + return 0; while ((dent1 = readdir(dir1)) != NULL) { if (dent1->d_type != DT_DIR || @@ -305,7 +306,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct perf_evsel *evsel, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->pid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", @@ -313,10 +315,10 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, return -1; } - dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); + dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid); - if (evsel->handler.func != NULL) { - tracepoint_handler f = evsel->handler.func; + if (evsel->handler != NULL) { + tracepoint_handler f = evsel->handler; return f(evsel, sample); } @@ -485,8 +487,12 @@ static int __cmd_kmem(void) { "kmem:kfree", perf_evsel__process_free_event, }, { "kmem:kmem_cache_free", perf_evsel__process_free_event, }, }; + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + }; - session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_kmem); + session = perf_session__new(&file, false, &perf_kmem); if (session == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 24b78aecc92..cd9f92078ab 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -2,22 +2,29 @@ #include "perf.h" #include "util/evsel.h" +#include "util/evlist.h" #include "util/util.h" #include "util/cache.h" #include "util/symbol.h" #include "util/thread.h" #include "util/header.h" #include "util/session.h" - +#include "util/intlist.h" #include "util/parse-options.h" #include "util/trace-event.h" #include "util/debug.h" #include <lk/debugfs.h> #include "util/tool.h" #include "util/stat.h" +#include "util/top.h" +#include "util/data.h" #include <sys/prctl.h> +#ifdef HAVE_TIMERFD_SUPPORT +#include <sys/timerfd.h> +#endif +#include <termios.h> #include <semaphore.h> #include <pthread.h> #include <math.h> @@ -82,6 +89,8 @@ struct exit_reasons_table { struct perf_kvm_stat { struct perf_tool tool; + struct perf_record_opts opts; + struct perf_evlist *evlist; struct perf_session *session; const char *file_name; @@ -96,10 +105,20 @@ struct perf_kvm_stat { struct kvm_events_ops *events_ops; key_cmp_fun compare; struct list_head kvm_events_cache[EVENTS_CACHE_SIZE]; + u64 total_time; u64 total_count; + u64 lost_events; + u64 duration; + + const char *pid_str; + struct intlist *pid_list; struct rb_root result; + + int timerfd; + unsigned int display_time; + bool live; }; @@ -320,6 +339,30 @@ static void init_kvm_event_record(struct perf_kvm_stat *kvm) INIT_LIST_HEAD(&kvm->kvm_events_cache[i]); } +#ifdef HAVE_TIMERFD_SUPPORT +static void clear_events_cache_stats(struct list_head *kvm_events_cache) +{ + struct list_head *head; + struct kvm_event *event; + unsigned int i; + int j; + + for (i = 0; i < EVENTS_CACHE_SIZE; i++) { + head = &kvm_events_cache[i]; + list_for_each_entry(event, head, hash_entry) { + /* reset stats for event */ + event->total.time = 0; + init_stats(&event->total.stats); + + for (j = 0; j < event->max_vcpu; ++j) { + event->vcpu[j].time = 0; + init_stats(&event->vcpu[j].stats); + } + } + } +} +#endif + static int kvm_events_hash_fn(u64 key) { return key & (EVENTS_CACHE_SIZE - 1); @@ -436,7 +479,7 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id, static bool handle_end_event(struct perf_kvm_stat *kvm, struct vcpu_event_record *vcpu_record, struct event_key *key, - u64 timestamp) + struct perf_sample *sample) { struct kvm_event *event; u64 time_begin, time_diff; @@ -472,9 +515,25 @@ static bool handle_end_event(struct perf_kvm_stat *kvm, vcpu_record->last_event = NULL; vcpu_record->start_time = 0; - BUG_ON(timestamp < time_begin); + /* seems to happen once in a while during live mode */ + if (sample->time < time_begin) { + pr_debug("End time before begin time; skipping event.\n"); + return true; + } + + time_diff = sample->time - time_begin; + + if (kvm->duration && time_diff > kvm->duration) { + char decode[32]; + + kvm->events_ops->decode_key(kvm, &event->key, decode); + if (strcmp(decode, "HLT")) { + pr_info("%" PRIu64 " VM %d, vcpu %d: %s event took %" PRIu64 "usec\n", + sample->time, sample->pid, vcpu_record->vcpu_id, + decode, time_diff/1000); + } + } - time_diff = timestamp - time_begin; return update_kvm_event(event, vcpu, time_diff); } @@ -521,7 +580,7 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm, return handle_begin_event(kvm, vcpu_record, &key, sample->time); if (kvm->events_ops->is_end_event(evsel, sample, &key)) - return handle_end_event(kvm, vcpu_record, &key, sample->time); + return handle_end_event(kvm, vcpu_record, &key, sample); return true; } @@ -550,6 +609,8 @@ static int compare_kvm_event_ ## func(struct kvm_event *one, \ GET_EVENT_KEY(time, time); COMPARE_EVENT_KEY(count, stats.n); COMPARE_EVENT_KEY(mean, stats.mean); +GET_EVENT_KEY(max, stats.max); +GET_EVENT_KEY(min, stats.min); #define DEF_SORT_NAME_KEY(name, compare_key) \ { #name, compare_kvm_event_ ## compare_key } @@ -639,43 +700,81 @@ static struct kvm_event *pop_from_result(struct rb_root *result) return container_of(node, struct kvm_event, rb); } -static void print_vcpu_info(int vcpu) +static void print_vcpu_info(struct perf_kvm_stat *kvm) { + int vcpu = kvm->trace_vcpu; + pr_info("Analyze events for "); + if (kvm->live) { + if (kvm->opts.target.system_wide) + pr_info("all VMs, "); + else if (kvm->opts.target.pid) + pr_info("pid(s) %s, ", kvm->opts.target.pid); + else + pr_info("dazed and confused on what is monitored, "); + } + if (vcpu == -1) pr_info("all VCPUs:\n\n"); else pr_info("VCPU %d:\n\n", vcpu); } +static void show_timeofday(void) +{ + char date[64]; + struct timeval tv; + struct tm ltime; + + gettimeofday(&tv, NULL); + if (localtime_r(&tv.tv_sec, <ime)) { + strftime(date, sizeof(date), "%H:%M:%S", <ime); + pr_info("%s.%06ld", date, tv.tv_usec); + } else + pr_info("00:00:00.000000"); + + return; +} + static void print_result(struct perf_kvm_stat *kvm) { char decode[20]; struct kvm_event *event; int vcpu = kvm->trace_vcpu; + if (kvm->live) { + puts(CONSOLE_CLEAR); + show_timeofday(); + } + pr_info("\n\n"); - print_vcpu_info(vcpu); + print_vcpu_info(kvm); pr_info("%20s ", kvm->events_ops->name); pr_info("%10s ", "Samples"); pr_info("%9s ", "Samples%"); pr_info("%9s ", "Time%"); + pr_info("%10s ", "Min Time"); + pr_info("%10s ", "Max Time"); pr_info("%16s ", "Avg time"); pr_info("\n\n"); while ((event = pop_from_result(&kvm->result))) { - u64 ecount, etime; + u64 ecount, etime, max, min; ecount = get_event_count(event, vcpu); etime = get_event_time(event, vcpu); + max = get_event_max(event, vcpu); + min = get_event_min(event, vcpu); kvm->events_ops->decode_key(kvm, &event->key, decode); pr_info("%20s ", decode); pr_info("%10llu ", (unsigned long long)ecount); pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100); pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100); + pr_info("%8" PRIu64 "us ", min / 1000); + pr_info("%8" PRIu64 "us ", max / 1000); pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3, kvm_event_rel_stddev(vcpu, event)); pr_info("\n"); @@ -683,6 +782,31 @@ static void print_result(struct perf_kvm_stat *kvm) pr_info("\nTotal Samples:%" PRIu64 ", Total events handled time:%.2fus.\n\n", kvm->total_count, kvm->total_time / 1e3); + + if (kvm->lost_events) + pr_info("\nLost events: %" PRIu64 "\n\n", kvm->lost_events); +} + +#ifdef HAVE_TIMERFD_SUPPORT +static int process_lost_event(struct perf_tool *tool, + union perf_event *event __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat, tool); + + kvm->lost_events++; + return 0; +} +#endif + +static bool skip_sample(struct perf_kvm_stat *kvm, + struct perf_sample *sample) +{ + if (kvm->pid_list && intlist__find(kvm->pid_list, sample->pid) == NULL) + return true; + + return false; } static int process_sample_event(struct perf_tool *tool, @@ -691,10 +815,14 @@ static int process_sample_event(struct perf_tool *tool, struct perf_evsel *evsel, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, sample->tid); + struct thread *thread; struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat, tool); + if (skip_sample(kvm, sample)) + return 0; + + thread = machine__findnew_thread(machine, sample->pid, sample->tid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", event->header.type); @@ -707,10 +835,20 @@ static int process_sample_event(struct perf_tool *tool, return 0; } -static int get_cpu_isa(struct perf_session *session) +static int cpu_isa_config(struct perf_kvm_stat *kvm) { - char *cpuid = session->header.env.cpuid; - int isa; + char buf[64], *cpuid; + int err, isa; + + if (kvm->live) { + err = get_cpuid(buf, sizeof(buf)); + if (err != 0) { + pr_err("Failed to look up CPU type (Intel or AMD)\n"); + return err; + } + cpuid = buf; + } else + cpuid = kvm->session->header.env.cpuid; if (strstr(cpuid, "Intel")) isa = 1; @@ -718,12 +856,372 @@ static int get_cpu_isa(struct perf_session *session) isa = 0; else { pr_err("CPU %s is not supported.\n", cpuid); - isa = -ENOTSUP; + return -ENOTSUP; } - return isa; + if (isa == 1) { + kvm->exit_reasons = vmx_exit_reasons; + kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons); + kvm->exit_reasons_isa = "VMX"; + } + + return 0; } +static bool verify_vcpu(int vcpu) +{ + if (vcpu != -1 && vcpu < 0) { + pr_err("Invalid vcpu:%d.\n", vcpu); + return false; + } + + return true; +} + +#ifdef HAVE_TIMERFD_SUPPORT +/* keeping the max events to a modest level to keep + * the processing of samples per mmap smooth. + */ +#define PERF_KVM__MAX_EVENTS_PER_MMAP 25 + +static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, + u64 *mmap_time) +{ + union perf_event *event; + struct perf_sample sample; + s64 n = 0; + int err; + + *mmap_time = ULLONG_MAX; + while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) { + err = perf_evlist__parse_sample(kvm->evlist, event, &sample); + if (err) { + perf_evlist__mmap_consume(kvm->evlist, idx); + pr_err("Failed to parse sample\n"); + return -1; + } + + err = perf_session_queue_event(kvm->session, event, &sample, 0); + /* + * 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); + + if (err) { + pr_err("Failed to enqueue sample: %d\n", err); + return -1; + } + + /* save time stamp of our first sample for this mmap */ + if (n == 0) + *mmap_time = sample.time; + + /* limit events per mmap handled all at once */ + n++; + if (n == PERF_KVM__MAX_EVENTS_PER_MMAP) + break; + } + + return n; +} + +static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm) +{ + int i, err, throttled = 0; + s64 n, ntotal = 0; + u64 flush_time = ULLONG_MAX, mmap_time; + + for (i = 0; i < kvm->evlist->nr_mmaps; i++) { + n = perf_kvm__mmap_read_idx(kvm, i, &mmap_time); + if (n < 0) + return -1; + + /* flush time is going to be the minimum of all the individual + * mmap times. Essentially, we flush all the samples queued up + * from the last pass under our minimal start time -- that leaves + * a very small race for samples to come in with a lower timestamp. + * The ioctl to return the perf_clock timestamp should close the + * race entirely. + */ + if (mmap_time < flush_time) + flush_time = mmap_time; + + ntotal += n; + if (n == PERF_KVM__MAX_EVENTS_PER_MMAP) + throttled = 1; + } + + /* flush queue after each round in which we processed events */ + if (ntotal) { + kvm->session->ordered_samples.next_flush = flush_time; + err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session); + if (err) { + if (kvm->lost_events) + pr_info("\nLost events: %" PRIu64 "\n\n", + kvm->lost_events); + return err; + } + } + + return throttled; +} + +static volatile int done; + +static void sig_handler(int sig __maybe_unused) +{ + done = 1; +} + +static int perf_kvm__timerfd_create(struct perf_kvm_stat *kvm) +{ + struct itimerspec new_value; + int rc = -1; + + kvm->timerfd = timerfd_create(CLOCK_MONOTONIC, TFD_NONBLOCK); + if (kvm->timerfd < 0) { + pr_err("timerfd_create failed\n"); + goto out; + } + + new_value.it_value.tv_sec = kvm->display_time; + new_value.it_value.tv_nsec = 0; + new_value.it_interval.tv_sec = kvm->display_time; + new_value.it_interval.tv_nsec = 0; + + if (timerfd_settime(kvm->timerfd, 0, &new_value, NULL) != 0) { + pr_err("timerfd_settime failed: %d\n", errno); + close(kvm->timerfd); + goto out; + } + + rc = 0; +out: + return rc; +} + +static int perf_kvm__handle_timerfd(struct perf_kvm_stat *kvm) +{ + uint64_t c; + int rc; + + rc = read(kvm->timerfd, &c, sizeof(uint64_t)); + if (rc < 0) { + if (errno == EAGAIN) + return 0; + + pr_err("Failed to read timer fd: %d\n", errno); + return -1; + } + + if (rc != sizeof(uint64_t)) { + pr_err("Error reading timer fd - invalid size returned\n"); + return -1; + } + + if (c != 1) + pr_debug("Missed timer beats: %" PRIu64 "\n", c-1); + + /* update display */ + sort_result(kvm); + print_result(kvm); + + /* reset counts */ + clear_events_cache_stats(kvm->kvm_events_cache); + kvm->total_count = 0; + kvm->total_time = 0; + kvm->lost_events = 0; + + return 0; +} + +static int fd_set_nonblock(int fd) +{ + long arg = 0; + + arg = fcntl(fd, F_GETFL); + if (arg < 0) { + pr_err("Failed to get current flags for fd %d\n", fd); + return -1; + } + + if (fcntl(fd, F_SETFL, arg | O_NONBLOCK) < 0) { + pr_err("Failed to set non-block option on fd %d\n", fd); + return -1; + } + + return 0; +} + +static +int perf_kvm__handle_stdin(struct termios *tc_now, struct termios *tc_save) +{ + int c; + + tcsetattr(0, TCSANOW, tc_now); + c = getc(stdin); + tcsetattr(0, TCSAFLUSH, tc_save); + + if (c == 'q') + return 1; + + return 0; +} + +static int kvm_events_live_report(struct perf_kvm_stat *kvm) +{ + struct pollfd *pollfds = NULL; + int nr_fds, nr_stdin, ret, err = -EINVAL; + struct termios tc, save; + + /* live flag must be set first */ + kvm->live = true; + + ret = cpu_isa_config(kvm); + if (ret < 0) + return ret; + + if (!verify_vcpu(kvm->trace_vcpu) || + !select_key(kvm) || + !register_kvm_events_ops(kvm)) { + goto out; + } + + init_kvm_event_record(kvm); + + tcgetattr(0, &save); + tc = save; + tc.c_lflag &= ~(ICANON | ECHO); + tc.c_cc[VMIN] = 0; + tc.c_cc[VTIME] = 0; + + signal(SIGINT, sig_handler); + signal(SIGTERM, sig_handler); + + /* copy pollfds -- need to add timerfd and stdin */ + nr_fds = kvm->evlist->nr_fds; + pollfds = zalloc(sizeof(struct pollfd) * (nr_fds + 2)); + if (!pollfds) { + err = -ENOMEM; + goto out; + } + memcpy(pollfds, kvm->evlist->pollfd, + sizeof(struct pollfd) * kvm->evlist->nr_fds); + + /* add timer fd */ + if (perf_kvm__timerfd_create(kvm) < 0) { + err = -1; + goto out; + } + + pollfds[nr_fds].fd = kvm->timerfd; + pollfds[nr_fds].events = POLLIN; + nr_fds++; + + pollfds[nr_fds].fd = fileno(stdin); + pollfds[nr_fds].events = POLLIN; + nr_stdin = nr_fds; + nr_fds++; + if (fd_set_nonblock(fileno(stdin)) != 0) + goto out; + + /* everything is good - enable the events and process */ + perf_evlist__enable(kvm->evlist); + + while (!done) { + int rc; + + rc = perf_kvm__mmap_read(kvm); + if (rc < 0) + break; + + err = perf_kvm__handle_timerfd(kvm); + if (err) + goto out; + + if (pollfds[nr_stdin].revents & POLLIN) + done = perf_kvm__handle_stdin(&tc, &save); + + if (!rc && !done) + err = poll(pollfds, nr_fds, 100); + } + + perf_evlist__disable(kvm->evlist); + + if (err == 0) { + sort_result(kvm); + print_result(kvm); + } + +out: + if (kvm->timerfd >= 0) + close(kvm->timerfd); + + if (pollfds) + free(pollfds); + + return err; +} + +static int kvm_live_open_events(struct perf_kvm_stat *kvm) +{ + int err, rc = -1; + struct perf_evsel *pos; + struct perf_evlist *evlist = kvm->evlist; + + perf_evlist__config(evlist, &kvm->opts); + + /* + * Note: exclude_{guest,host} do not apply here. + * This command processes KVM tracepoints from host only + */ + list_for_each_entry(pos, &evlist->entries, node) { + struct perf_event_attr *attr = &pos->attr; + + /* make sure these *are* set */ + perf_evsel__set_sample_bit(pos, TID); + perf_evsel__set_sample_bit(pos, TIME); + perf_evsel__set_sample_bit(pos, CPU); + perf_evsel__set_sample_bit(pos, RAW); + /* make sure these are *not*; want as small a sample as possible */ + perf_evsel__reset_sample_bit(pos, PERIOD); + perf_evsel__reset_sample_bit(pos, IP); + perf_evsel__reset_sample_bit(pos, CALLCHAIN); + perf_evsel__reset_sample_bit(pos, ADDR); + perf_evsel__reset_sample_bit(pos, READ); + attr->mmap = 0; + attr->comm = 0; + attr->task = 0; + + attr->sample_period = 1; + + attr->watermark = 0; + attr->wakeup_events = 1000; + + /* will enable all once we are ready */ + attr->disabled = 1; + } + + err = perf_evlist__open(evlist); + if (err < 0) { + printf("Couldn't create the events: %s\n", strerror(errno)); + goto out; + } + + if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) { + ui__error("Failed to mmap the events: %s\n", strerror(errno)); + perf_evlist__close(evlist); + goto out; + } + + rc = 0; + +out: + return rc; +} +#endif + static int read_events(struct perf_kvm_stat *kvm) { int ret; @@ -733,10 +1231,13 @@ static int read_events(struct perf_kvm_stat *kvm) .comm = perf_event__process_comm, .ordered_samples = true, }; + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + }; kvm->tool = eops; - kvm->session = perf_session__new(kvm->file_name, O_RDONLY, 0, false, - &kvm->tool); + kvm->session = perf_session__new(&file, false, &kvm->tool); if (!kvm->session) { pr_err("Initializing perf session failed\n"); return -EINVAL; @@ -749,28 +1250,24 @@ static int read_events(struct perf_kvm_stat *kvm) * Do not use 'isa' recorded in kvm_exit tracepoint since it is not * traced in the old kernel. */ - ret = get_cpu_isa(kvm->session); - + ret = cpu_isa_config(kvm); if (ret < 0) return ret; - if (ret == 1) { - kvm->exit_reasons = vmx_exit_reasons; - kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons); - kvm->exit_reasons_isa = "VMX"; - } - return perf_session__process_events(kvm->session, &kvm->tool); } -static bool verify_vcpu(int vcpu) +static int parse_target_str(struct perf_kvm_stat *kvm) { - if (vcpu != -1 && vcpu < 0) { - pr_err("Invalid vcpu:%d.\n", vcpu); - return false; + if (kvm->pid_str) { + kvm->pid_list = intlist__new(kvm->pid_str); + if (kvm->pid_list == NULL) { + pr_err("Error parsing process id string\n"); + return -EINVAL; + } } - return true; + return 0; } static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm) @@ -778,6 +1275,9 @@ static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm) int ret = -EINVAL; int vcpu = kvm->trace_vcpu; + if (parse_target_str(kvm) != 0) + goto exit; + if (!verify_vcpu(vcpu)) goto exit; @@ -801,16 +1301,11 @@ exit: return ret; } -static const char * const record_args[] = { - "record", - "-R", - "-f", - "-m", "1024", - "-c", "1", - "-e", "kvm:kvm_entry", - "-e", "kvm:kvm_exit", - "-e", "kvm:kvm_mmio", - "-e", "kvm:kvm_pio", +static const char * const kvm_events_tp[] = { + "kvm:kvm_entry", + "kvm:kvm_exit", + "kvm:kvm_mmio", + "kvm:kvm_pio", }; #define STRDUP_FAIL_EXIT(s) \ @@ -826,8 +1321,15 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) { unsigned int rec_argc, i, j; const char **rec_argv; + const char * const record_args[] = { + "record", + "-R", + "-m", "1024", + "-c", "1", + }; - rec_argc = ARRAY_SIZE(record_args) + argc + 2; + rec_argc = ARRAY_SIZE(record_args) + argc + 2 + + 2 * ARRAY_SIZE(kvm_events_tp); rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (rec_argv == NULL) @@ -836,6 +1338,11 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) for (i = 0; i < ARRAY_SIZE(record_args); i++) rec_argv[i] = STRDUP_FAIL_EXIT(record_args[i]); + for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) { + rec_argv[i++] = "-e"; + rec_argv[i++] = STRDUP_FAIL_EXIT(kvm_events_tp[j]); + } + rec_argv[i++] = STRDUP_FAIL_EXIT("-o"); rec_argv[i++] = STRDUP_FAIL_EXIT(kvm->file_name); @@ -856,6 +1363,8 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv) OPT_STRING('k', "key", &kvm->sort_key, "sort-key", "key for sorting: sample(sort by samples number)" " time (sort by avg time)"), + OPT_STRING('p', "pid", &kvm->pid_str, "pid", + "analyze events only for given process id(s)"), OPT_END() }; @@ -878,6 +1387,196 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv) return kvm_events_report_vcpu(kvm); } +#ifdef HAVE_TIMERFD_SUPPORT +static struct perf_evlist *kvm_live_event_list(void) +{ + struct perf_evlist *evlist; + char *tp, *name, *sys; + unsigned int j; + int err = -1; + + evlist = perf_evlist__new(); + if (evlist == NULL) + return NULL; + + for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) { + + tp = strdup(kvm_events_tp[j]); + if (tp == NULL) + goto out; + + /* split tracepoint into subsystem and name */ + sys = tp; + name = strchr(tp, ':'); + if (name == NULL) { + pr_err("Error parsing %s tracepoint: subsystem delimiter not found\n", + kvm_events_tp[j]); + free(tp); + goto out; + } + *name = '\0'; + name++; + + if (perf_evlist__add_newtp(evlist, sys, name, NULL)) { + pr_err("Failed to add %s tracepoint to the list\n", kvm_events_tp[j]); + free(tp); + goto out; + } + + free(tp); + } + + err = 0; + +out: + if (err) { + perf_evlist__delete(evlist); + evlist = NULL; + } + + return evlist; +} + +static int kvm_events_live(struct perf_kvm_stat *kvm, + int argc, const char **argv) +{ + char errbuf[BUFSIZ]; + int err; + + const struct option live_options[] = { + OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid", + "record events on existing process id"), + OPT_CALLBACK('m', "mmap-pages", &kvm->opts.mmap_pages, "pages", + "number of mmap data pages", + perf_evlist__parse_mmap_pages), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show counter open errors, etc)"), + OPT_BOOLEAN('a', "all-cpus", &kvm->opts.target.system_wide, + "system-wide collection from all CPUs"), + OPT_UINTEGER('d', "display", &kvm->display_time, + "time in seconds between display updates"), + OPT_STRING(0, "event", &kvm->report_event, "report event", + "event for reporting: vmexit, mmio, ioport"), + OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu, + "vcpu id to report"), + OPT_STRING('k', "key", &kvm->sort_key, "sort-key", + "key for sorting: sample(sort by samples number)" + " time (sort by avg time)"), + OPT_U64(0, "duration", &kvm->duration, + "show events other than HALT that take longer than duration usecs"), + OPT_END() + }; + const char * const live_usage[] = { + "perf kvm stat live [<options>]", + NULL + }; + struct perf_data_file file = { + .mode = PERF_DATA_MODE_WRITE, + }; + + + /* event handling */ + kvm->tool.sample = process_sample_event; + kvm->tool.comm = perf_event__process_comm; + kvm->tool.exit = perf_event__process_exit; + kvm->tool.fork = perf_event__process_fork; + kvm->tool.lost = process_lost_event; + kvm->tool.ordered_samples = true; + perf_tool__fill_defaults(&kvm->tool); + + /* set defaults */ + kvm->display_time = 1; + kvm->opts.user_interval = 1; + kvm->opts.mmap_pages = 512; + kvm->opts.target.uses_mmap = false; + kvm->opts.target.uid_str = NULL; + kvm->opts.target.uid = UINT_MAX; + + symbol__init(); + disable_buildid_cache(); + + use_browser = 0; + setup_browser(false); + + if (argc) { + argc = parse_options(argc, argv, live_options, + live_usage, 0); + if (argc) + usage_with_options(live_usage, live_options); + } + + kvm->duration *= NSEC_PER_USEC; /* convert usec to nsec */ + + /* + * target related setups + */ + err = perf_target__validate(&kvm->opts.target); + if (err) { + perf_target__strerror(&kvm->opts.target, err, errbuf, BUFSIZ); + ui__warning("%s", errbuf); + } + + if (perf_target__none(&kvm->opts.target)) + kvm->opts.target.system_wide = true; + + + /* + * generate the event list + */ + kvm->evlist = kvm_live_event_list(); + if (kvm->evlist == NULL) { + err = -1; + 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); + + /* + * perf session + */ + kvm->session = perf_session__new(&file, false, &kvm->tool); + if (kvm->session == NULL) { + err = -ENOMEM; + goto out; + } + kvm->session->evlist = kvm->evlist; + perf_session__set_id_hdr_size(kvm->session); + + + if (perf_target__has_task(&kvm->opts.target)) + perf_event__synthesize_thread_map(&kvm->tool, + kvm->evlist->threads, + perf_event__process, + &kvm->session->machines.host); + else + perf_event__synthesize_threads(&kvm->tool, perf_event__process, + &kvm->session->machines.host); + + + err = kvm_live_open_events(kvm); + if (err) + goto out; + + err = kvm_events_live_report(kvm); + +out: + exit_browser(0); + + if (kvm->session) + perf_session__delete(kvm->session); + kvm->session = NULL; + if (kvm->evlist) { + perf_evlist__delete_maps(kvm->evlist); + perf_evlist__delete(kvm->evlist); + } + + return err; +} +#endif + static void print_kvm_stat_usage(void) { printf("Usage: perf kvm stat <command>\n\n"); @@ -885,6 +1584,7 @@ static void print_kvm_stat_usage(void) printf("# Available commands:\n"); printf("\trecord: record kvm events\n"); printf("\treport: report statistical data of kvm events\n"); + printf("\tlive: live reporting of statistical data of kvm events\n"); printf("\nOtherwise, it is the alias of 'perf stat':\n"); } @@ -914,6 +1614,11 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv) if (!strncmp(argv[1], "rep", 3)) return kvm_events_report(&kvm, argc - 1 , argv + 1); +#ifdef HAVE_TIMERFD_SUPPORT + if (!strncmp(argv[1], "live", 4)) + return kvm_events_live(&kvm, argc - 1 , argv + 1); +#endif + perf_stat: return cmd_stat(argc, argv, NULL); } diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 1948eceb517..011195e38f2 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -13,49 +13,64 @@ #include "util/parse-events.h" #include "util/cache.h" +#include "util/pmu.h" +#include "util/parse-options.h" int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) { + int i; + const struct option list_options[] = { + OPT_END() + }; + const char * const list_usage[] = { + "perf list [hw|sw|cache|tracepoint|pmu|event_glob]", + NULL + }; + + argc = parse_options(argc, argv, list_options, list_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + setup_pager(); - if (argc == 1) + if (argc == 0) { print_events(NULL, false); - else { - int i; - - for (i = 1; i < argc; ++i) { - if (i > 2) - putchar('\n'); - if (strncmp(argv[i], "tracepoint", 10) == 0) - print_tracepoint_events(NULL, NULL, false); - else if (strcmp(argv[i], "hw") == 0 || - strcmp(argv[i], "hardware") == 0) - print_events_type(PERF_TYPE_HARDWARE); - else if (strcmp(argv[i], "sw") == 0 || - strcmp(argv[i], "software") == 0) - print_events_type(PERF_TYPE_SOFTWARE); - else if (strcmp(argv[i], "cache") == 0 || - strcmp(argv[i], "hwcache") == 0) - print_hwcache_events(NULL, false); - else if (strcmp(argv[i], "--raw-dump") == 0) - print_events(NULL, true); - else { - char *sep = strchr(argv[i], ':'), *s; - int sep_idx; - - if (sep == NULL) { - print_events(argv[i], false); - continue; - } - sep_idx = sep - argv[i]; - s = strdup(argv[i]); - if (s == NULL) - return -1; - - s[sep_idx] = '\0'; - print_tracepoint_events(s, s + sep_idx + 1, false); - free(s); + return 0; + } + + for (i = 0; i < argc; ++i) { + if (i) + putchar('\n'); + if (strncmp(argv[i], "tracepoint", 10) == 0) + print_tracepoint_events(NULL, NULL, false); + else if (strcmp(argv[i], "hw") == 0 || + strcmp(argv[i], "hardware") == 0) + print_events_type(PERF_TYPE_HARDWARE); + else if (strcmp(argv[i], "sw") == 0 || + strcmp(argv[i], "software") == 0) + print_events_type(PERF_TYPE_SOFTWARE); + else if (strcmp(argv[i], "cache") == 0 || + strcmp(argv[i], "hwcache") == 0) + print_hwcache_events(NULL, false); + else if (strcmp(argv[i], "pmu") == 0) + print_pmu_events(NULL, false); + else if (strcmp(argv[i], "--raw-dump") == 0) + print_events(NULL, true); + else { + char *sep = strchr(argv[i], ':'), *s; + int sep_idx; + + if (sep == NULL) { + print_events(argv[i], false); + continue; } + sep_idx = sep - argv[i]; + s = strdup(argv[i]); + if (s == NULL) + return -1; + + s[sep_idx] = '\0'; + print_tracepoint_events(s, s + sep_idx + 1, false); + free(s); } } return 0; diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 76543a4a7a3..c852c7a85d3 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -15,6 +15,7 @@ #include "util/debug.h" #include "util/session.h" #include "util/tool.h" +#include "util/data.h" #include <sys/types.h> #include <sys/prctl.h> @@ -56,7 +57,9 @@ struct lock_stat { unsigned int nr_readlock; unsigned int nr_trylock; + /* these times are in nano sec. */ + u64 avg_wait_time; u64 wait_time_total; u64 wait_time_min; u64 wait_time_max; @@ -208,6 +211,7 @@ static struct thread_stat *thread_stat_findnew_first(u32 tid) SINGLE_KEY(nr_acquired) SINGLE_KEY(nr_contended) +SINGLE_KEY(avg_wait_time) SINGLE_KEY(wait_time_total) SINGLE_KEY(wait_time_max) @@ -244,6 +248,7 @@ static struct rb_root result; /* place to store sorted data */ struct lock_key keys[] = { DEF_KEY_LOCK(acquired, nr_acquired), DEF_KEY_LOCK(contended, nr_contended), + DEF_KEY_LOCK(avg_wait, avg_wait_time), DEF_KEY_LOCK(wait_total, wait_time_total), DEF_KEY_LOCK(wait_min, wait_time_min), DEF_KEY_LOCK(wait_max, wait_time_max), @@ -321,10 +326,12 @@ static struct lock_stat *lock_stat_findnew(void *addr, const char *name) new->addr = addr; new->name = zalloc(sizeof(char) * strlen(name) + 1); - if (!new->name) + if (!new->name) { + free(new); goto alloc_failed; - strcpy(new->name, name); + } + strcpy(new->name, name); new->wait_time_min = ULLONG_MAX; list_add(&new->hash_entry, entry); @@ -400,17 +407,17 @@ static int report_lock_acquire_event(struct perf_evsel *evsel, ls = lock_stat_findnew(addr, name); if (!ls) - return -1; + return -ENOMEM; if (ls->discard) return 0; ts = thread_stat_findnew(sample->tid); if (!ts) - return -1; + return -ENOMEM; seq = get_seq(ts, addr); if (!seq) - return -1; + return -ENOMEM; switch (seq->state) { case SEQ_STATE_UNINITIALIZED: @@ -446,7 +453,6 @@ broken: list_del(&seq->list); free(seq); goto end; - break; default: BUG_ON("Unknown state of lock sequence found!\n"); break; @@ -473,17 +479,17 @@ static int report_lock_acquired_event(struct perf_evsel *evsel, ls = lock_stat_findnew(addr, name); if (!ls) - return -1; + return -ENOMEM; if (ls->discard) return 0; ts = thread_stat_findnew(sample->tid); if (!ts) - return -1; + return -ENOMEM; seq = get_seq(ts, addr); if (!seq) - return -1; + return -ENOMEM; switch (seq->state) { case SEQ_STATE_UNINITIALIZED: @@ -508,8 +514,6 @@ static int report_lock_acquired_event(struct perf_evsel *evsel, list_del(&seq->list); free(seq); goto end; - break; - default: BUG_ON("Unknown state of lock sequence found!\n"); break; @@ -517,6 +521,7 @@ static int report_lock_acquired_event(struct perf_evsel *evsel, seq->state = SEQ_STATE_ACQUIRED; ls->nr_acquired++; + ls->avg_wait_time = ls->nr_contended ? ls->wait_time_total/ls->nr_contended : 0; seq->prev_event_time = sample->time; end: return 0; @@ -536,17 +541,17 @@ static int report_lock_contended_event(struct perf_evsel *evsel, ls = lock_stat_findnew(addr, name); if (!ls) - return -1; + return -ENOMEM; if (ls->discard) return 0; ts = thread_stat_findnew(sample->tid); if (!ts) - return -1; + return -ENOMEM; seq = get_seq(ts, addr); if (!seq) - return -1; + return -ENOMEM; switch (seq->state) { case SEQ_STATE_UNINITIALIZED: @@ -564,7 +569,6 @@ static int report_lock_contended_event(struct perf_evsel *evsel, list_del(&seq->list); free(seq); goto end; - break; default: BUG_ON("Unknown state of lock sequence found!\n"); break; @@ -572,6 +576,7 @@ static int report_lock_contended_event(struct perf_evsel *evsel, seq->state = SEQ_STATE_CONTENDED; ls->nr_contended++; + ls->avg_wait_time = ls->wait_time_total/ls->nr_contended; seq->prev_event_time = sample->time; end: return 0; @@ -591,22 +596,21 @@ static int report_lock_release_event(struct perf_evsel *evsel, ls = lock_stat_findnew(addr, name); if (!ls) - return -1; + return -ENOMEM; if (ls->discard) return 0; ts = thread_stat_findnew(sample->tid); if (!ts) - return -1; + return -ENOMEM; seq = get_seq(ts, addr); if (!seq) - return -1; + return -ENOMEM; switch (seq->state) { case SEQ_STATE_UNINITIALIZED: goto end; - break; case SEQ_STATE_ACQUIRED: break; case SEQ_STATE_READ_ACQUIRED: @@ -624,7 +628,6 @@ static int report_lock_release_event(struct perf_evsel *evsel, ls->discard = 1; bad_hist[BROKEN_RELEASE]++; goto free_seq; - break; default: BUG_ON("Unknown state of lock sequence found!\n"); break; @@ -690,7 +693,7 @@ static void print_bad_events(int bad, int total) pr_info("\n=== output for debug===\n\n"); pr_info("bad: %d, total: %d\n", bad, total); - pr_info("bad rate: %f %%\n", (double)bad / (double)total * 100); + pr_info("bad rate: %.2f %%\n", (double)bad / (double)total * 100); pr_info("histogram of events caused bad sequence\n"); for (i = 0; i < BROKEN_MAX; i++) pr_info(" %10s: %d\n", name[i], bad_hist[i]); @@ -707,6 +710,7 @@ static void print_result(void) pr_info("%10s ", "acquired"); pr_info("%10s ", "contended"); + pr_info("%15s ", "avg wait (ns)"); pr_info("%15s ", "total wait (ns)"); pr_info("%15s ", "max wait (ns)"); pr_info("%15s ", "min wait (ns)"); @@ -738,6 +742,7 @@ static void print_result(void) pr_info("%10u ", st->nr_acquired); pr_info("%10u ", st->nr_contended); + pr_info("%15" PRIu64 " ", st->avg_wait_time); pr_info("%15" PRIu64 " ", st->wait_time_total); pr_info("%15" PRIu64 " ", st->wait_time_max); pr_info("%15" PRIu64 " ", st->wait_time_min == ULLONG_MAX ? @@ -762,7 +767,7 @@ static void dump_threads(void) while (node) { st = container_of(node, struct thread_stat, rb); t = perf_session__findnew(session, st->tid); - pr_info("%10d: %s\n", st->tid, t->comm); + pr_info("%10d: %s\n", st->tid, thread__comm_str(t)); node = rb_next(node); }; } @@ -805,7 +810,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct perf_evsel *evsel, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, sample->tid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->tid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", @@ -813,14 +819,26 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, return -1; } - if (evsel->handler.func != NULL) { - tracepoint_handler f = evsel->handler.func; + if (evsel->handler != NULL) { + tracepoint_handler f = evsel->handler; return f(evsel, sample); } return 0; } +static void sort_result(void) +{ + unsigned int i; + struct lock_stat *st; + + for (i = 0; i < LOCKHASH_SIZE; i++) { + list_for_each_entry(st, &lockhash_table[i], hash_entry) { + insert_to_result(st, compare); + } + } +} + static const struct perf_evsel_str_handler lock_tracepoints[] = { { "lock:lock_acquire", perf_evsel__process_lock_acquire, }, /* CONFIG_LOCKDEP */ { "lock:lock_acquired", perf_evsel__process_lock_acquired, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */ @@ -828,51 +846,51 @@ static const struct perf_evsel_str_handler lock_tracepoints[] = { { "lock:lock_release", perf_evsel__process_lock_release, }, /* CONFIG_LOCKDEP */ }; -static int read_events(void) +static int __cmd_report(bool display_info) { + int err = -EINVAL; struct perf_tool eops = { .sample = process_sample_event, .comm = perf_event__process_comm, .ordered_samples = true, }; - session = perf_session__new(input_name, O_RDONLY, 0, false, &eops); + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + }; + + session = perf_session__new(&file, false, &eops); if (!session) { pr_err("Initializing perf session failed\n"); - return -1; + return -ENOMEM; } + if (!perf_session__has_traces(session, "lock record")) + goto out_delete; + if (perf_session__set_tracepoints_handlers(session, lock_tracepoints)) { pr_err("Initializing perf session tracepoint handlers failed\n"); - return -1; + goto out_delete; } - return perf_session__process_events(session, &eops); -} - -static void sort_result(void) -{ - unsigned int i; - struct lock_stat *st; + if (select_key()) + goto out_delete; - for (i = 0; i < LOCKHASH_SIZE; i++) { - list_for_each_entry(st, &lockhash_table[i], hash_entry) { - insert_to_result(st, compare); - } - } -} + err = perf_session__process_events(session, &eops); + if (err) + goto out_delete; -static int __cmd_report(void) -{ setup_pager(); + if (display_info) /* used for info subcommand */ + err = dump_info(); + else { + sort_result(); + print_result(); + } - if ((select_key() != 0) || - (read_events() != 0)) - return -1; - - sort_result(); - print_result(); - - return 0; +out_delete: + perf_session__delete(session); + return err; } static int __cmd_record(int argc, const char **argv) @@ -880,7 +898,7 @@ static int __cmd_record(int argc, const char **argv) const char *record_args[] = { "record", "-R", "-m", "1024", "-c", "1", }; - unsigned int rec_argc, i, j; + unsigned int rec_argc, i, j, ret; const char **rec_argv; for (i = 0; i < ARRAY_SIZE(lock_tracepoints); i++) { @@ -897,7 +915,7 @@ static int __cmd_record(int argc, const char **argv) rec_argc += 2 * ARRAY_SIZE(lock_tracepoints); rec_argv = calloc(rec_argc + 1, sizeof(char *)); - if (rec_argv == NULL) + if (!rec_argv) return -ENOMEM; for (i = 0; i < ARRAY_SIZE(record_args); i++) @@ -913,7 +931,9 @@ static int __cmd_record(int argc, const char **argv) BUG_ON(i != rec_argc); - return cmd_record(i, rec_argv, NULL); + ret = cmd_record(i, rec_argv, NULL); + free(rec_argv); + return ret; } int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) @@ -933,7 +953,7 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) }; const struct option report_options[] = { OPT_STRING('k', "key", &sort_key, "acquired", - "key for sorting (acquired / contended / wait_total / wait_max / wait_min)"), + "key for sorting (acquired / contended / avg_wait / wait_total / wait_max / wait_min)"), /* TODO: type */ OPT_END() }; @@ -971,7 +991,7 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) if (argc) usage_with_options(report_usage, report_options); } - __cmd_report(); + rc = __cmd_report(false); } else if (!strcmp(argv[0], "script")) { /* Aliased to 'perf script' */ return cmd_script(argc, argv, prefix); @@ -984,11 +1004,7 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) } /* recycling report_lock_ops */ trace_handler = &report_lock_ops; - setup_pager(); - if (read_events() != 0) - rc = -1; - else - rc = dump_info(); + rc = __cmd_report(true); } else { usage_with_options(lock_usage, lock_options); } diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index a8ff6d264e5..31c00f186da 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -5,6 +5,7 @@ #include "util/trace-event.h" #include "util/tool.h" #include "util/session.h" +#include "util/data.h" #define MEM_OPERATION_LOAD "load" #define MEM_OPERATION_STORE "store" @@ -14,7 +15,6 @@ static const char *mem_operation = MEM_OPERATION_LOAD; struct perf_mem { struct perf_tool tool; char const *input_name; - symbol_filter_t annotate_init; bool hide_unresolved; bool dump_raw; const char *cpu_list; @@ -69,8 +69,7 @@ dump_raw_samples(struct perf_tool *tool, struct addr_location al; const char *fmt; - if (perf_event__preprocess_sample(event, machine, &al, sample, - mem->annotate_init) < 0) { + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { fprintf(stderr, "problem processing %d event, skipping it.\n", event->header.type); return -1; @@ -96,7 +95,7 @@ dump_raw_samples(struct perf_tool *tool, symbol_conf.field_sep, sample->tid, symbol_conf.field_sep, - event->ip.ip, + sample->ip, symbol_conf.field_sep, sample->addr, symbol_conf.field_sep, @@ -121,10 +120,14 @@ static int process_sample_event(struct perf_tool *tool, static int report_raw_events(struct perf_mem *mem) { + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + }; int err = -EINVAL; int ret; - struct perf_session *session = perf_session__new(input_name, O_RDONLY, - 0, false, &mem->tool); + struct perf_session *session = perf_session__new(&file, false, + &mem->tool); if (session == NULL) return -ENOMEM; @@ -192,6 +195,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) .tool = { .sample = process_sample_event, .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, .lost = perf_event__process_lost, .fork = perf_event__process_fork, diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index e8a66f9a671..89acc17cf2a 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -173,7 +173,7 @@ static int opt_set_target(const struct option *opt, const char *str, if (str && !params.target) { if (!strcmp(opt->long_name, "exec")) params.uprobes = true; -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT else if (!strcmp(opt->long_name, "module")) params.uprobes = false; #endif @@ -187,7 +187,7 @@ static int opt_set_target(const struct option *opt, const char *str, return ret; } -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT static int opt_show_lines(const struct option *opt __maybe_unused, const char *str, int unset __maybe_unused) { @@ -257,7 +257,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) "perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]", "perf probe [<options>] --del '[GROUP:]EVENT' ...", "perf probe --list", -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT "perf probe [<options>] --line 'LINEDESC'", "perf probe [<options>] --vars 'PROBEPOINT'", #endif @@ -271,7 +271,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.", opt_del_probe_event), OPT_CALLBACK('a', "add", NULL, -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT "[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT" " [[NAME=]ARG ...]", #else @@ -283,7 +283,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) "\t\tFUNC:\tFunction name\n" "\t\tOFF:\tOffset from function entry (in byte)\n" "\t\t%return:\tPut the probe at function return\n" -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT "\t\tSRC:\tSource code path\n" "\t\tRL:\tRelative line number from function entry.\n" "\t\tAL:\tAbsolute line number in file.\n" @@ -296,7 +296,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) opt_add_probe_event), OPT_BOOLEAN('f', "force", ¶ms.force_add, "forcibly add events" " with existing name"), -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT OPT_CALLBACK('L', "line", NULL, "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]", "Show source code lines.", opt_show_lines), @@ -408,7 +408,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) return ret; } -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT if (params.show_lines && !params.uprobes) { if (params.mod_events) { pr_err(" Error: Don't use --line with" diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index ecca62e27b2..15280b5e557 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -24,12 +24,13 @@ #include "util/symbol.h" #include "util/cpumap.h" #include "util/thread_map.h" +#include "util/data.h" #include <unistd.h> #include <sched.h> #include <sys/mman.h> -#ifndef HAVE_ON_EXIT +#ifndef HAVE_ON_EXIT_SUPPORT #ifndef ATEXIT_MAX #define ATEXIT_MAX 32 #endif @@ -65,31 +66,25 @@ struct perf_record { struct perf_tool tool; struct perf_record_opts opts; u64 bytes_written; - const char *output_name; + struct perf_data_file file; struct perf_evlist *evlist; struct perf_session *session; const char *progname; - int output; - unsigned int page_size; int realtime_prio; bool no_buildid; bool no_buildid_cache; long samples; - off_t post_processing_offset; }; -static void advance_output(struct perf_record *rec, size_t size) -{ - rec->bytes_written += size; -} - static int write_output(struct perf_record *rec, void *buf, size_t size) { + struct perf_data_file *file = &rec->file; + while (size) { - int ret = write(rec->output, buf, size); + int ret = write(file->fd, buf, size); if (ret < 0) { - pr_err("failed to write\n"); + pr_err("failed to write perf data, error: %m\n"); return -1; } @@ -119,7 +114,7 @@ static int perf_record__mmap_read(struct perf_record *rec, { unsigned int head = perf_mmap__read_head(md); unsigned int old = md->prev; - unsigned char *data = md->base + rec->page_size; + unsigned char *data = md->base + page_size; unsigned long size; void *buf; int rc = 0; @@ -234,10 +229,6 @@ try_again: "or try again with a smaller value of -m/--mmap_pages.\n" "(current value: %d)\n", opts->mmap_pages); rc = -errno; - } else if (!is_power_of_2(opts->mmap_pages) && - (opts->mmap_pages != UINT_MAX)) { - pr_err("--mmap_pages/-m value must be a power of two."); - rc = -EINVAL; } else { pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno)); rc = -errno; @@ -253,31 +244,34 @@ out: static int process_buildids(struct perf_record *rec) { - u64 size = lseek(rec->output, 0, SEEK_CUR); + struct perf_data_file *file = &rec->file; + struct perf_session *session = rec->session; + u64 start = session->header.data_offset; + u64 size = lseek(file->fd, 0, SEEK_CUR); if (size == 0) return 0; - rec->session->fd = rec->output; - return __perf_session__process_events(rec->session, rec->post_processing_offset, - size - rec->post_processing_offset, + return __perf_session__process_events(session, start, + size - start, size, &build_id__mark_dso_hit_ops); } static void perf_record__exit(int status, void *arg) { struct perf_record *rec = arg; + struct perf_data_file *file = &rec->file; if (status != 0) return; - if (!rec->opts.pipe_output) { + if (!file->is_pipe) { rec->session->header.data_size += rec->bytes_written; if (!rec->no_buildid) process_buildids(rec); perf_session__write_header(rec->session, rec->evlist, - rec->output, true); + file->fd, true); perf_session__delete(rec->session); perf_evlist__delete(rec->evlist); symbol__exit(); @@ -343,64 +337,47 @@ out: return rc; } +static void perf_record__init_features(struct perf_record *rec) +{ + struct perf_evlist *evsel_list = rec->evlist; + struct perf_session *session = rec->session; + int feat; + + for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++) + perf_header__set_feat(&session->header, feat); + + if (rec->no_buildid) + perf_header__clear_feat(&session->header, HEADER_BUILD_ID); + + if (!have_tracepoints(&evsel_list->entries)) + perf_header__clear_feat(&session->header, HEADER_TRACING_DATA); + + if (!rec->opts.branch_stack) + perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK); +} + static int __cmd_record(struct perf_record *rec, int argc, const char **argv) { - struct stat st; - int flags; - int err, output, feat; + int err; unsigned long waking = 0; const bool forks = argc > 0; struct machine *machine; struct perf_tool *tool = &rec->tool; struct perf_record_opts *opts = &rec->opts; struct perf_evlist *evsel_list = rec->evlist; - const char *output_name = rec->output_name; + struct perf_data_file *file = &rec->file; struct perf_session *session; bool disabled = false; rec->progname = argv[0]; - rec->page_size = sysconf(_SC_PAGE_SIZE); - on_exit(perf_record__sig_exit, rec); signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); signal(SIGUSR1, sig_handler); signal(SIGTERM, sig_handler); - if (!output_name) { - if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode)) - opts->pipe_output = true; - else - rec->output_name = output_name = "perf.data"; - } - if (output_name) { - if (!strcmp(output_name, "-")) - opts->pipe_output = true; - else if (!stat(output_name, &st) && st.st_size) { - char oldname[PATH_MAX]; - snprintf(oldname, sizeof(oldname), "%s.old", - output_name); - unlink(oldname); - rename(output_name, oldname); - } - } - - flags = O_CREAT|O_RDWR|O_TRUNC; - - if (opts->pipe_output) - output = STDOUT_FILENO; - else - output = open(output_name, flags, S_IRUSR | S_IWUSR); - if (output < 0) { - perror("failed to create output file"); - return -1; - } - - rec->output = output; - - session = perf_session__new(output_name, O_WRONLY, - true, false, NULL); + session = perf_session__new(file, false, NULL); if (session == NULL) { pr_err("Not enough memory for reading perf file header\n"); return -1; @@ -408,21 +385,11 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) rec->session = session; - for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++) - perf_header__set_feat(&session->header, feat); - - if (rec->no_buildid) - perf_header__clear_feat(&session->header, HEADER_BUILD_ID); - - if (!have_tracepoints(&evsel_list->entries)) - perf_header__clear_feat(&session->header, HEADER_TRACING_DATA); - - if (!rec->opts.branch_stack) - perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK); + perf_record__init_features(rec); if (forks) { err = perf_evlist__prepare_workload(evsel_list, &opts->target, - argv, opts->pipe_output, + argv, file->is_pipe, true); if (err < 0) { pr_err("Couldn't run the workload!\n"); @@ -443,13 +410,13 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) */ on_exit(perf_record__exit, rec); - if (opts->pipe_output) { - err = perf_header__write_pipe(output); + if (file->is_pipe) { + err = perf_header__write_pipe(file->fd); if (err < 0) goto out_delete_session; } else { err = perf_session__write_header(session, evsel_list, - output, false); + file->fd, false); if (err < 0) goto out_delete_session; } @@ -462,11 +429,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) goto out_delete_session; } - rec->post_processing_offset = lseek(output, 0, SEEK_CUR); - machine = &session->machines.host; - if (opts->pipe_output) { + if (file->is_pipe) { err = perf_event__synthesize_attrs(tool, session, process_synthesized_event); if (err < 0) { @@ -474,13 +439,6 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) goto out_delete_session; } - err = perf_event__synthesize_event_types(tool, process_synthesized_event, - machine); - if (err < 0) { - pr_err("Couldn't synthesize event_types.\n"); - goto out_delete_session; - } - if (have_tracepoints(&evsel_list->entries)) { /* * FIXME err <= 0 here actually means that @@ -490,13 +448,13 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) * return this more properly and also * propagate errors that now are calling die() */ - err = perf_event__synthesize_tracing_data(tool, output, evsel_list, + err = perf_event__synthesize_tracing_data(tool, file->fd, evsel_list, process_synthesized_event); if (err <= 0) { pr_err("Couldn't record tracing data.\n"); goto out_delete_session; } - advance_output(rec, err); + rec->bytes_written += err; } } @@ -597,7 +555,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n", (double)rec->bytes_written / 1024.0 / 1024.0, - output_name, + file->path, rec->bytes_written / 24); return 0; @@ -625,6 +583,9 @@ static const struct branch_mode branch_modes[] = { BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL), BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN), BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL), + BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX), + BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX), + BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX), BRANCH_END }; @@ -691,7 +652,7 @@ error: return ret; } -#ifdef LIBUNWIND_SUPPORT +#ifdef HAVE_LIBUNWIND_SUPPORT static int get_stack_size(char *str, unsigned long *_size) { char *endptr; @@ -717,23 +678,14 @@ static int get_stack_size(char *str, unsigned long *_size) max_size, str); return -1; } -#endif /* LIBUNWIND_SUPPORT */ +#endif /* HAVE_LIBUNWIND_SUPPORT */ -int record_parse_callchain_opt(const struct option *opt, - const char *arg, int unset) +int record_parse_callchain(const char *arg, struct perf_record_opts *opts) { - struct perf_record_opts *opts = opt->value; char *tok, *name, *saveptr = NULL; char *buf; int ret = -1; - /* --no-call-graph */ - if (unset) - return 0; - - /* We specified default option if none is provided. */ - BUG_ON(!arg); - /* We need buffer that we know we can write to. */ buf = malloc(strlen(arg) + 1); if (!buf) @@ -755,7 +707,7 @@ int record_parse_callchain_opt(const struct option *opt, "needed for -g fp\n"); break; -#ifdef LIBUNWIND_SUPPORT +#ifdef HAVE_LIBUNWIND_SUPPORT /* Dwarf style */ } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { const unsigned long default_stack_dump_size = 8192; @@ -771,13 +723,9 @@ int record_parse_callchain_opt(const struct option *opt, ret = get_stack_size(tok, &size); opts->stack_dump_size = size; } - - if (!ret) - pr_debug("callchain: stack dump size %d\n", - opts->stack_dump_size); -#endif /* LIBUNWIND_SUPPORT */ +#endif /* HAVE_LIBUNWIND_SUPPORT */ } else { - pr_err("callchain: Unknown -g option " + pr_err("callchain: Unknown --call-graph option " "value: %s\n", arg); break; } @@ -785,13 +733,52 @@ int record_parse_callchain_opt(const struct option *opt, } while (0); free(buf); + return ret; +} + +static void callchain_debug(struct perf_record_opts *opts) +{ + pr_debug("callchain: type %d\n", opts->call_graph); + + if (opts->call_graph == CALLCHAIN_DWARF) + pr_debug("callchain: stack dump size %d\n", + opts->stack_dump_size); +} + +int record_parse_callchain_opt(const struct option *opt, + const char *arg, + int unset) +{ + struct perf_record_opts *opts = opt->value; + int ret; + /* --no-call-graph */ + if (unset) { + opts->call_graph = CALLCHAIN_NONE; + pr_debug("callchain: disabled\n"); + return 0; + } + + ret = record_parse_callchain(arg, opts); if (!ret) - pr_debug("callchain: type %d\n", opts->call_graph); + callchain_debug(opts); return ret; } +int record_callchain_opt(const struct option *opt, + const char *arg __maybe_unused, + int unset __maybe_unused) +{ + struct perf_record_opts *opts = opt->value; + + if (opts->call_graph == CALLCHAIN_NONE) + opts->call_graph = CALLCHAIN_FP; + + callchain_debug(opts); + return 0; +} + static const char * const record_usage[] = { "perf record [<options>] [<command>]", "perf record [<options>] -- <command> [<options>]", @@ -820,12 +807,12 @@ static struct perf_record record = { }, }; -#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: " +#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: " -#ifdef LIBUNWIND_SUPPORT -const char record_callchain_help[] = CALLCHAIN_HELP "[fp] dwarf"; +#ifdef HAVE_LIBUNWIND_SUPPORT +const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf"; #else -const char record_callchain_help[] = CALLCHAIN_HELP "[fp]"; +const char record_callchain_help[] = CALLCHAIN_HELP "fp"; #endif /* @@ -856,18 +843,22 @@ const struct option record_options[] = { OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu", "list of cpus to monitor"), OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"), - OPT_STRING('o', "output", &record.output_name, "file", + OPT_STRING('o', "output", &record.file.path, "file", "output file name"), OPT_BOOLEAN('i', "no-inherit", &record.opts.no_inherit, "child tasks do not inherit counters"), OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"), - OPT_UINTEGER('m', "mmap-pages", &record.opts.mmap_pages, - "number of mmap data pages"), + OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages", + "number of mmap data pages", + perf_evlist__parse_mmap_pages), OPT_BOOLEAN(0, "group", &record.opts.group, "put the counters into a counter group"), - OPT_CALLBACK_DEFAULT('g', "call-graph", &record.opts, - "mode[,dump_size]", record_callchain_help, - &record_parse_callchain_opt, "fp"), + OPT_CALLBACK_NOOPT('g', NULL, &record.opts, + NULL, "enables call-graph recording" , + &record_callchain_opt), + OPT_CALLBACK(0, "call-graph", &record.opts, + "mode[,dump_size]", record_callchain_help, + &record_parse_callchain_opt), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"), @@ -898,13 +889,14 @@ const struct option record_options[] = { parse_branch_stack), OPT_BOOLEAN('W', "weight", &record.opts.sample_weight, "sample by weight (on special events only)"), + OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction, + "sample transaction flags (special events only)"), OPT_END() }; int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) { int err = -ENOMEM; - struct perf_evsel *pos; struct perf_evlist *evsel_list; struct perf_record *rec = &record; char errbuf[BUFSIZ]; @@ -968,25 +960,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (perf_evlist__create_maps(evsel_list, &rec->opts.target) < 0) usage_with_options(record_usage, record_options); - list_for_each_entry(pos, &evsel_list->entries, node) { - if (perf_header__push_event(pos->attr.config, perf_evsel__name(pos))) - goto out_free_fd; - } - - if (rec->opts.user_interval != ULLONG_MAX) - rec->opts.default_interval = rec->opts.user_interval; - if (rec->opts.user_freq != UINT_MAX) - rec->opts.freq = rec->opts.user_freq; - - /* - * User specified count overrides default frequency. - */ - if (rec->opts.default_interval) - rec->opts.freq = 0; - else if (rec->opts.freq) { - rec->opts.default_interval = rec->opts.freq; - } else { - ui__error("frequency and count are zero, aborting\n"); + if (perf_record_opts__config(&rec->opts)) { err = -EINVAL; goto out_free_fd; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 3662047cc6b..8cf8e66ba59 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -33,8 +33,10 @@ #include "util/thread.h" #include "util/sort.h" #include "util/hist.h" +#include "util/data.h" #include "arch/common.h" +#include <dlfcn.h> #include <linux/bitmap.h> struct perf_report { @@ -47,9 +49,9 @@ struct perf_report { bool show_threads; bool inverted_callchain; bool mem_mode; + int max_stack; struct perf_read_values show_threads_values; const char *pretty_printing_style; - symbol_filter_t annotate_init; const char *cpu_list; const char *symbol_filter_str; float min_percent; @@ -89,7 +91,8 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool, if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { err = machine__resolve_callchain(machine, evsel, al->thread, - sample, &parent); + sample, &parent, al, + rep->max_stack); if (err) return err; } @@ -112,7 +115,8 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool, * and this is indirectly achieved by passing period=weight here * and the he_stat__add_period() function. */ - he = __hists__add_mem_entry(&evsel->hists, al, parent, mi, cost, cost); + he = __hists__add_entry(&evsel->hists, al, parent, NULL, mi, + cost, cost, 0); if (!he) return -ENOMEM; @@ -180,7 +184,8 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { err = machine__resolve_callchain(machine, evsel, al->thread, - sample, &parent); + sample, &parent, al, + rep->max_stack); if (err) return err; } @@ -196,12 +201,16 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, err = -ENOMEM; + /* overwrite the 'al' to branch-to info */ + al->map = bi[i].to.map; + al->sym = bi[i].to.sym; + al->addr = bi[i].to.addr; /* * The report shows the percentage of total branches captured * and not events sampled. Thus we use a pseudo period of 1. */ - he = __hists__add_branch_entry(&evsel->hists, al, parent, - &bi[i], 1, 1); + he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL, + 1, 1, 0); if (he) { struct annotation *notes; bx = he->branch_info; @@ -243,24 +252,28 @@ out: return err; } -static int perf_evsel__add_hist_entry(struct perf_evsel *evsel, +static int perf_evsel__add_hist_entry(struct perf_tool *tool, + struct perf_evsel *evsel, struct addr_location *al, struct perf_sample *sample, struct machine *machine) { + struct perf_report *rep = container_of(tool, struct perf_report, tool); struct symbol *parent = NULL; int err = 0; struct hist_entry *he; if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { err = machine__resolve_callchain(machine, evsel, al->thread, - sample, &parent); + sample, &parent, al, + rep->max_stack); if (err) return err; } - he = __hists__add_entry(&evsel->hists, al, parent, sample->period, - sample->weight); + he = __hists__add_entry(&evsel->hists, al, parent, NULL, NULL, + sample->period, sample->weight, + sample->transaction); if (he == NULL) return -ENOMEM; @@ -305,8 +318,7 @@ static int process_sample_event(struct perf_tool *tool, struct addr_location al; int ret; - if (perf_event__preprocess_sample(event, machine, &al, sample, - rep->annotate_init) < 0) { + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { fprintf(stderr, "problem processing %d event, skipping it.\n", event->header.type); return -1; @@ -332,7 +344,8 @@ static int process_sample_event(struct perf_tool *tool, if (al.map != NULL) al.map->dso->hit = 1; - ret = perf_evsel__add_hist_entry(evsel, &al, sample, machine); + ret = perf_evsel__add_hist_entry(tool, evsel, &al, sample, + machine); if (ret < 0) pr_debug("problem incrementing symbol period, skipping event\n"); } @@ -366,10 +379,11 @@ static int process_read_event(struct perf_tool *tool, /* For pipe mode, sample_type is not currently set */ static int perf_report__setup_sample_type(struct perf_report *rep) { - struct perf_session *self = rep->session; - u64 sample_type = perf_evlist__sample_type(self->evlist); + struct perf_session *session = rep->session; + u64 sample_type = perf_evlist__combined_sample_type(session->evlist); + bool is_pipe = perf_data_file__is_pipe(session->file); - if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) { + if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) { if (sort__has_parent) { ui__error("Selected --sort parent, but no " "callchain data. Did you call " @@ -392,7 +406,7 @@ static int perf_report__setup_sample_type(struct perf_report *rep) } if (sort__mode == SORT_MODE__BRANCH) { - if (!self->fd_pipe && + if (!is_pipe && !(sample_type & PERF_SAMPLE_BRANCH_STACK)) { ui__error("Selected -b but no branch data. " "Did you call perf record without -b?\n"); @@ -403,22 +417,20 @@ static int perf_report__setup_sample_type(struct perf_report *rep) return 0; } -extern volatile int session_done; - static void sig_handler(int sig __maybe_unused) { session_done = 1; } static size_t hists__fprintf_nr_sample_events(struct perf_report *rep, - struct hists *self, + struct hists *hists, const char *evname, FILE *fp) { size_t ret; char unit; - unsigned long nr_samples = self->stats.nr_events[PERF_RECORD_SAMPLE]; - u64 nr_events = self->stats.total_period; - struct perf_evsel *evsel = hists_to_evsel(self); + 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); char buf[512]; size_t size = sizeof(buf); @@ -490,6 +502,8 @@ static int __cmd_report(struct perf_report *rep) struct map *kernel_map; struct kmap *kernel_kmap; const char *help = "For a higher level overview, try: perf report --sort comm,dso"; + struct ui_progress prog; + struct perf_data_file *file = session->file; signal(SIGINT, sig_handler); @@ -497,7 +511,7 @@ static int __cmd_report(struct perf_report *rep) ret = perf_session__cpu_bitmap(session, rep->cpu_list, rep->cpu_bitmap); if (ret) - goto out_delete; + return ret; } if (use_browser <= 0) @@ -508,11 +522,11 @@ static int __cmd_report(struct perf_report *rep) ret = perf_report__setup_sample_type(rep); if (ret) - goto out_delete; + return ret; ret = perf_session__process_events(session, &rep->tool); if (ret) - goto out_delete; + return ret; kernel_map = session->machines.host.vmlinux_maps[MAP__FUNCTION]; kernel_kmap = map__kmap(kernel_map); @@ -547,17 +561,23 @@ static int __cmd_report(struct perf_report *rep) if (dump_trace) { perf_session__fprintf_nr_events(session, stdout); - goto out_delete; + return 0; } nr_samples = 0; + list_for_each_entry(pos, &session->evlist->entries, node) + nr_samples += pos->hists.nr_entries; + + ui_progress__init(&prog, nr_samples, "Merging related events..."); + + nr_samples = 0; list_for_each_entry(pos, &session->evlist->entries, node) { struct hists *hists = &pos->hists; if (pos->idx == 0) hists->symbol_filter_str = rep->symbol_filter_str; - hists__collapse_resort(hists); + hists__collapse_resort(hists, &prog); nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE]; /* Non-group events are considered as leader */ @@ -569,10 +589,14 @@ static int __cmd_report(struct perf_report *rep) hists__link(leader_hists, hists); } } + ui_progress__finish(); + + if (session_done()) + return 0; if (nr_samples == 0) { - ui__error("The %s file has no samples!\n", session->filename); - goto out_delete; + ui__error("The %s file has no samples!\n", file->path); + return 0; } list_for_each_entry(pos, &session->evlist->entries, node) @@ -592,25 +616,23 @@ static int __cmd_report(struct perf_report *rep) ret = 0; } else if (use_browser == 2) { - perf_evlist__gtk_browse_hists(session->evlist, help, - NULL, rep->min_percent); + int (*hist_browser)(struct perf_evlist *, + const char *, + struct hist_browser_timer *, + float min_pcnt); + + hist_browser = dlsym(perf_gtk_handle, + "perf_evlist__gtk_browse_hists"); + if (hist_browser == NULL) { + ui__error("GTK browser not found!\n"); + return ret; + } + hist_browser(session->evlist, help, NULL, + rep->min_percent); } } else perf_evlist__tty_browse_hists(session->evlist, rep, help); -out_delete: - /* - * Speed up the exit process, for large files this can - * take quite a while. - * - * XXX Enable this when using valgrind or if we ever - * librarize this command. - * - * Also experiment with obstacks to see how much speed - * up we'll get here. - * - * perf_session__delete(session); - */ return ret; } @@ -680,12 +702,23 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset) } /* get the call chain order */ - if (!strcmp(tok2, "caller")) + if (!strncmp(tok2, "caller", strlen("caller"))) callchain_param.order = ORDER_CALLER; - else if (!strcmp(tok2, "callee")) + else if (!strncmp(tok2, "callee", strlen("callee"))) callchain_param.order = ORDER_CALLEE; else return -1; + + /* Get the sort key */ + tok2 = strtok(NULL, ","); + if (!tok2) + goto setup; + if (!strncmp(tok2, "function", strlen("function"))) + callchain_param.key = CCKEY_FUNCTION; + else if (!strncmp(tok2, "address", strlen("address"))) + callchain_param.key = CCKEY_ADDRESS; + else + return -1; setup: if (callchain_register_param(&callchain_param) < 0) { fprintf(stderr, "Can't register callchain params\n"); @@ -694,6 +727,24 @@ setup: return 0; } +int +report_parse_ignore_callees_opt(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused) +{ + if (arg) { + int err = regcomp(&ignore_callees_regex, arg, REG_EXTENDED); + if (err) { + char buf[BUFSIZ]; + regerror(err, &ignore_callees_regex, buf, sizeof(buf)); + pr_err("Invalid --ignore-callees regex: %s\n%s", arg, buf); + return -1; + } + have_ignore_callees = 1; + } + + return 0; +} + static int parse_branch_mode(const struct option *opt __maybe_unused, const char *str __maybe_unused, int unset) @@ -730,18 +781,19 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .tool = { .sample = process_sample_event, .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost, .read = process_read_event, .attr = perf_event__process_attr, - .event_type = perf_event__process_event_type, .tracing_data = perf_event__process_tracing_data, .build_id = perf_event__process_build_id, .ordered_samples = true, .ordering_requires_timestamps = true, }, + .max_stack = PERF_MAX_STACK_DEPTH, .pretty_printing_style = "normal", }; const struct option options[] = { @@ -772,7 +824,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline," " dso_to, dso_from, symbol_to, symbol_from, mispredict," " weight, local_weight, mem, symbol_daddr, dso_daddr, tlb, " - "snoop, locked"), + "snoop, locked, abort, in_tx, transaction"), OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_STRING('p', "parent", &parent_pattern, "regex", @@ -780,10 +832,17 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other, "Only display entries with parent-match"), OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order", - "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit and callchain order. " - "Default: fractal,0.5,callee", &parse_callchain_opt, callchain_default_opt), + "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). " + "Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt), + OPT_INTEGER(0, "max-stack", &report.max_stack, + "Set the maximum stack depth when parsing the callchain, " + "anything beyond the specified depth will be ignored. " + "Default: " __stringify(PERF_MAX_STACK_DEPTH)), OPT_BOOLEAN('G', "inverted", &report.inverted_callchain, "alias for inverted call graph"), + OPT_CALLBACK(0, "ignore-callees", NULL, "regex", + "ignore callees of these functions in call graphs", + report_parse_ignore_callees_opt), OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", "only consider symbols in these dsos"), OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]", @@ -827,6 +886,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Don't show entries under that percent", parse_percent_limit), OPT_END() }; + struct perf_data_file file = { + .mode = PERF_DATA_MODE_READ, + }; perf_config(perf_report_config, &report); @@ -849,17 +911,11 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) input_name = "perf.data"; } - if (strcmp(input_name, "-") != 0) - setup_browser(true); - else { - use_browser = 0; - perf_hpp__column_enable(PERF_HPP__OVERHEAD); - perf_hpp__init(); - } + file.path = input_name; + file.force = report.force; repeat: - session = perf_session__new(input_name, O_RDONLY, - report.force, false, &report.tool); + session = perf_session__new(&file, false, &report.tool); if (session == NULL) return -ENOMEM; @@ -897,8 +953,22 @@ repeat: sort_order = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked"; } - if (setup_sorting() < 0) - usage_with_options(report_usage, options); + if (setup_sorting() < 0) { + parse_options_usage(report_usage, options, "s", 1); + goto error; + } + + if (parent_pattern != default_parent_pattern) { + if (sort_dimension__add("parent") < 0) + goto error; + } + + if (strcmp(input_name, "-") != 0) + setup_browser(true); + else { + use_browser = 0; + perf_hpp__init(); + } /* * Only in the TUI browser we are doing integrated annotation, @@ -907,7 +977,8 @@ repeat: */ if (use_browser == 1 && sort__has_sym) { symbol_conf.priv_size = sizeof(struct annotation); - report.annotate_init = symbol__annotate_init; + machines__set_symbol_filter(&session->machines, + symbol__annotate_init); /* * For searching by name on the "Browse map details". * providing it only in verbose mode not to bloat too @@ -928,19 +999,6 @@ repeat: if (symbol__init() < 0) goto error; - if (parent_pattern != default_parent_pattern) { - if (sort_dimension__add("parent") < 0) - goto error; - - /* - * Only show the parent fields if we explicitly - * sort that way. If we only use parent machinery - * for filtering, we don't want it. - */ - if (!strstr(sort_order, "parent")) - sort_parent.elide = 1; - } - if (argc) { /* * Special case: if there's an argument left then assume that diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index fed9ae432c1..0f3c65518a2 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -109,8 +109,9 @@ struct trace_sched_handler { int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel, struct perf_sample *sample, struct machine *machine); - int (*fork_event)(struct perf_sched *sched, struct perf_evsel *evsel, - struct perf_sample *sample); + /* PERF_RECORD_FORK event, not sched_process_fork tracepoint */ + int (*fork_event)(struct perf_sched *sched, union perf_event *event, + struct machine *machine); int (*migrate_task_event)(struct perf_sched *sched, struct perf_evsel *evsel, @@ -717,22 +718,31 @@ static int replay_switch_event(struct perf_sched *sched, return 0; } -static int replay_fork_event(struct perf_sched *sched, struct perf_evsel *evsel, - struct perf_sample *sample) +static int replay_fork_event(struct perf_sched *sched, + union perf_event *event, + struct machine *machine) { - const char *parent_comm = perf_evsel__strval(evsel, sample, "parent_comm"), - *child_comm = perf_evsel__strval(evsel, sample, "child_comm"); - const u32 parent_pid = perf_evsel__intval(evsel, sample, "parent_pid"), - child_pid = perf_evsel__intval(evsel, sample, "child_pid"); + struct thread *child, *parent; + + child = machine__findnew_thread(machine, event->fork.pid, + event->fork.tid); + parent = machine__findnew_thread(machine, event->fork.ppid, + event->fork.ptid); + + if (child == NULL || parent == NULL) { + pr_debug("thread does not exist on fork event: child %p, parent %p\n", + child, parent); + return 0; + } if (verbose) { - printf("sched_fork event %p\n", evsel); - printf("... parent: %s/%d\n", parent_comm, parent_pid); - printf("... child: %s/%d\n", child_comm, child_pid); + printf("fork event\n"); + printf("... parent: %s/%d\n", thread__comm_str(parent), parent->tid); + printf("... child: %s/%d\n", thread__comm_str(child), child->tid); } - register_pid(sched, parent_pid, parent_comm); - register_pid(sched, child_pid, child_comm); + register_pid(sched, parent->tid, thread__comm_str(parent)); + register_pid(sched, child->tid, thread__comm_str(child)); return 0; } @@ -824,14 +834,6 @@ static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread) return 0; } -static int latency_fork_event(struct perf_sched *sched __maybe_unused, - struct perf_evsel *evsel __maybe_unused, - struct perf_sample *sample __maybe_unused) -{ - /* should insert the newcomer */ - return 0; -} - static char sched_out_state(u64 prev_state) { const char *str = TASK_STATE_TO_CHAR_STR; @@ -934,8 +936,8 @@ static int latency_switch_event(struct perf_sched *sched, return -1; } - sched_out = machine__findnew_thread(machine, prev_pid); - sched_in = machine__findnew_thread(machine, next_pid); + sched_out = machine__findnew_thread(machine, 0, prev_pid); + sched_in = machine__findnew_thread(machine, 0, next_pid); out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid); if (!out_events) { @@ -978,7 +980,7 @@ static int latency_runtime_event(struct perf_sched *sched, { const u32 pid = perf_evsel__intval(evsel, sample, "pid"); const u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); - struct thread *thread = machine__findnew_thread(machine, pid); + struct thread *thread = machine__findnew_thread(machine, 0, pid); struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid); u64 timestamp = sample->time; int cpu = sample->cpu; @@ -1016,7 +1018,7 @@ static int latency_wakeup_event(struct perf_sched *sched, if (!success) return 0; - wakee = machine__findnew_thread(machine, pid); + wakee = machine__findnew_thread(machine, 0, pid); atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, wakee)) @@ -1070,12 +1072,12 @@ static int latency_migrate_task_event(struct perf_sched *sched, if (sched->profile_cpu == -1) return 0; - migrant = machine__findnew_thread(machine, pid); + migrant = machine__findnew_thread(machine, 0, pid); atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); if (!atoms) { if (thread_atoms_insert(sched, migrant)) return -1; - register_pid(sched, migrant->pid, migrant->comm); + register_pid(sched, migrant->tid, thread__comm_str(migrant)); atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid); if (!atoms) { pr_err("migration-event: Internal tree error"); @@ -1109,13 +1111,13 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_ /* * Ignore idle threads: */ - if (!strcmp(work_list->thread->comm, "swapper")) + if (!strcmp(thread__comm_str(work_list->thread), "swapper")) return; sched->all_runtime += work_list->total_runtime; sched->all_count += work_list->nb_atoms; - ret = printf(" %s:%d ", work_list->thread->comm, work_list->thread->pid); + ret = printf(" %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid); for (i = 0; i < 24 - ret; i++) printf(" "); @@ -1131,9 +1133,9 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_ static int pid_cmp(struct work_atoms *l, struct work_atoms *r) { - if (l->thread->pid < r->thread->pid) + if (l->thread->tid < r->thread->tid) return -1; - if (l->thread->pid > r->thread->pid) + if (l->thread->tid > r->thread->tid) return 1; return 0; @@ -1289,8 +1291,8 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, return -1; } - sched_out = machine__findnew_thread(machine, prev_pid); - sched_in = machine__findnew_thread(machine, next_pid); + sched_out = machine__findnew_thread(machine, 0, prev_pid); + sched_in = machine__findnew_thread(machine, 0, next_pid); sched->curr_thread[this_cpu] = sched_in; @@ -1321,7 +1323,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, printf("*"); if (sched->curr_thread[cpu]) { - if (sched->curr_thread[cpu]->pid) + if (sched->curr_thread[cpu]->tid) printf("%2s ", sched->curr_thread[cpu]->shortname); else printf(". "); @@ -1332,7 +1334,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, printf(" %12.6f secs ", (double)timestamp/1e9); if (new_shortname) { printf("%s => %s:%d\n", - sched_in->shortname, sched_in->comm, sched_in->pid); + sched_in->shortname, thread__comm_str(sched_in), sched_in->tid); } else { printf("\n"); } @@ -1379,25 +1381,20 @@ static int process_sched_runtime_event(struct perf_tool *tool, return 0; } -static int process_sched_fork_event(struct perf_tool *tool, - struct perf_evsel *evsel, - struct perf_sample *sample, - struct machine *machine __maybe_unused) +static int perf_sched__process_fork_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) { struct perf_sched *sched = container_of(tool, struct perf_sched, tool); - if (sched->tp_handler->fork_event) - return sched->tp_handler->fork_event(sched, evsel, sample); + /* run the fork event through the perf machineruy */ + perf_event__process_fork(tool, event, sample, machine); - return 0; -} + /* and then run additional processing needed for this command */ + if (sched->tp_handler->fork_event) + return sched->tp_handler->fork_event(sched, event, machine); -static int process_sched_exit_event(struct perf_tool *tool __maybe_unused, - struct perf_evsel *evsel, - struct perf_sample *sample __maybe_unused, - struct machine *machine __maybe_unused) -{ - pr_debug("sched_exit event %p\n", evsel); return 0; } @@ -1425,27 +1422,20 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_ struct perf_evsel *evsel, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, sample->tid); int err = 0; - if (thread == NULL) { - pr_debug("problem processing %s event, skipping it.\n", - perf_evsel__name(evsel)); - return -1; - } - evsel->hists.stats.total_period += sample->period; hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); - if (evsel->handler.func != NULL) { - tracepoint_handler f = evsel->handler.func; + if (evsel->handler != NULL) { + tracepoint_handler f = evsel->handler; err = f(tool, evsel, sample, machine); } return err; } -static int perf_sched__read_events(struct perf_sched *sched, bool destroy, +static int perf_sched__read_events(struct perf_sched *sched, struct perf_session **psession) { const struct perf_evsel_str_handler handlers[] = { @@ -1453,13 +1443,15 @@ static int perf_sched__read_events(struct perf_sched *sched, bool destroy, { "sched:sched_stat_runtime", process_sched_runtime_event, }, { "sched:sched_wakeup", process_sched_wakeup_event, }, { "sched:sched_wakeup_new", process_sched_wakeup_event, }, - { "sched:sched_process_fork", process_sched_fork_event, }, - { "sched:sched_process_exit", process_sched_exit_event, }, { "sched:sched_migrate_task", process_sched_migrate_task_event, }, }; struct perf_session *session; + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + }; - session = perf_session__new(input_name, O_RDONLY, 0, false, &sched->tool); + session = perf_session__new(&file, false, &sched->tool); if (session == NULL) { pr_debug("No Memory for session\n"); return -1; @@ -1480,11 +1472,10 @@ static int perf_sched__read_events(struct perf_sched *sched, bool destroy, sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST]; } - if (destroy) - perf_session__delete(session); - if (psession) *psession = session; + else + perf_session__delete(session); return 0; @@ -1529,8 +1520,11 @@ static int perf_sched__lat(struct perf_sched *sched) struct perf_session *session; setup_pager(); - if (perf_sched__read_events(sched, false, &session)) + + /* save session -- references to threads are held in work_list */ + if (perf_sched__read_events(sched, &session)) return -1; + perf_sched__sort_lat(sched); printf("\n ---------------------------------------------------------------------------------------------------------------\n"); @@ -1565,7 +1559,7 @@ static int perf_sched__map(struct perf_sched *sched) sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); setup_pager(); - if (perf_sched__read_events(sched, true, NULL)) + if (perf_sched__read_events(sched, NULL)) return -1; print_bad_events(sched); return 0; @@ -1580,7 +1574,7 @@ static int perf_sched__replay(struct perf_sched *sched) test_calibrations(sched); - if (perf_sched__read_events(sched, true, NULL)) + if (perf_sched__read_events(sched, NULL)) return -1; printf("nr_run_events: %ld\n", sched->nr_run_events); @@ -1639,7 +1633,6 @@ static int __cmd_record(int argc, const char **argv) "-e", "sched:sched_stat_sleep", "-e", "sched:sched_stat_iowait", "-e", "sched:sched_stat_runtime", - "-e", "sched:sched_process_exit", "-e", "sched:sched_process_fork", "-e", "sched:sched_wakeup", "-e", "sched:sched_migrate_task", @@ -1670,14 +1663,13 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) .sample = perf_sched__process_tracepoint_sample, .comm = perf_event__process_comm, .lost = perf_event__process_lost, - .fork = perf_event__process_fork, + .fork = perf_sched__process_fork_event, .ordered_samples = true, }, .cmp_pid = LIST_HEAD_INIT(sched.cmp_pid), .sort_list = LIST_HEAD_INIT(sched.sort_list), .start_work_mutex = PTHREAD_MUTEX_INITIALIZER, .work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER, - .curr_pid = { [0 ... MAX_CPUS - 1] = -1 }, .sort_order = default_sort_order, .replay_repeat = 10, .profile_cpu = -1, @@ -1729,7 +1721,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) .wakeup_event = latency_wakeup_event, .switch_event = latency_switch_event, .runtime_event = latency_runtime_event, - .fork_event = latency_fork_event, .migrate_task_event = latency_migrate_task_event, }; struct trace_sched_handler map_ops = { @@ -1740,6 +1731,10 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) .switch_event = replay_switch_event, .fork_event = replay_fork_event, }; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(sched.curr_pid); i++) + sched.curr_pid[i] = -1; argc = parse_options(argc, argv, sched_options, sched_usage, PARSE_OPT_STOP_AT_NON_OPTION); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 92d4658f56f..baf17989a21 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -15,6 +15,7 @@ #include "util/evlist.h" #include "util/evsel.h" #include "util/sort.h" +#include "util/data.h" #include <linux/bitmap.h> static char const *script_name; @@ -24,6 +25,7 @@ static u64 last_timestamp; static u64 nr_unordered; extern const struct option record_options[]; static bool no_callchain; +static bool latency_format; static bool system_wide; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); @@ -65,6 +67,7 @@ struct output_option { static struct { bool user_set; bool wildcard_set; + unsigned int print_ip_opts; u64 fields; u64 invalid_fields; } output[PERF_TYPE_MAX] = { @@ -226,6 +229,24 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, return 0; } +static void set_print_ip_opts(struct perf_event_attr *attr) +{ + unsigned int type = attr->type; + + output[type].print_ip_opts = 0; + if (PRINT_FIELD(IP)) + output[type].print_ip_opts |= PRINT_IP_OPT_IP; + + if (PRINT_FIELD(SYM)) + output[type].print_ip_opts |= PRINT_IP_OPT_SYM; + + if (PRINT_FIELD(DSO)) + output[type].print_ip_opts |= PRINT_IP_OPT_DSO; + + if (PRINT_FIELD(SYMOFFSET)) + output[type].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET; +} + /* * verify all user requested events exist and the samples * have the expected data @@ -252,6 +273,11 @@ static int perf_session__check_output_opt(struct perf_session *session) if (evsel && output[j].fields && perf_evsel__check_attr(evsel, session)) return -1; + + if (evsel == NULL) + continue; + + set_print_ip_opts(&evsel->attr); } return 0; @@ -269,11 +295,11 @@ static void print_sample_start(struct perf_sample *sample, if (PRINT_FIELD(COMM)) { if (latency_format) - printf("%8.8s ", thread->comm); + printf("%8.8s ", thread__comm_str(thread)); else if (PRINT_FIELD(IP) && symbol_conf.use_callchain) - printf("%s ", thread->comm); + printf("%s ", thread__comm_str(thread)); else - printf("%16s ", thread->comm); + printf("%16s ", thread__comm_str(thread)); } if (PRINT_FIELD(PID) && PRINT_FIELD(TID)) @@ -381,14 +407,16 @@ static void print_sample_bts(union perf_event *event, else printf("\n"); perf_evsel__print_ip(evsel, event, sample, machine, - PRINT_FIELD(SYM), PRINT_FIELD(DSO), - PRINT_FIELD(SYMOFFSET)); + output[attr->type].print_ip_opts, + PERF_MAX_STACK_DEPTH); } printf(" => "); /* print branch_to information */ - if (PRINT_FIELD(ADDR)) + if (PRINT_FIELD(ADDR) || + ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && + !output[attr->type].user_set)) print_sample_addr(event, sample, machine, thread, attr); printf("\n"); @@ -396,10 +424,10 @@ static void print_sample_bts(union perf_event *event, static void process_event(union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, - struct addr_location *al) + struct thread *thread, + struct addr_location *al __maybe_unused) { struct perf_event_attr *attr = &evsel->attr; - struct thread *thread = al->thread; if (output[attr->type].fields == 0) return; @@ -422,9 +450,10 @@ static void process_event(union perf_event *event, struct perf_sample *sample, printf(" "); else printf("\n"); + perf_evsel__print_ip(evsel, event, sample, machine, - PRINT_FIELD(SYM), PRINT_FIELD(DSO), - PRINT_FIELD(SYMOFFSET)); + output[attr->type].print_ip_opts, + PERF_MAX_STACK_DEPTH); } printf("\n"); @@ -479,7 +508,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct machine *machine) { struct addr_location al; - struct thread *thread = machine__findnew_thread(machine, event->ip.tid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->tid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", @@ -498,7 +528,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, return 0; } - if (perf_event__preprocess_sample(event, machine, &al, sample, 0) < 0) { + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { pr_err("problem processing %d event, skipping it.\n", event->header.type); return -1; @@ -510,40 +540,57 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) return 0; - scripting_ops->process_event(event, sample, evsel, machine, &al); + scripting_ops->process_event(event, sample, evsel, machine, thread, &al); evsel->hists.stats.total_period += sample->period; return 0; } -static struct perf_tool perf_script = { - .sample = process_sample_event, - .mmap = perf_event__process_mmap, - .comm = perf_event__process_comm, - .exit = perf_event__process_exit, - .fork = perf_event__process_fork, - .attr = perf_event__process_attr, - .event_type = perf_event__process_event_type, - .tracing_data = perf_event__process_tracing_data, - .build_id = perf_event__process_build_id, - .ordered_samples = true, - .ordering_requires_timestamps = true, +struct perf_script { + struct perf_tool tool; + struct perf_session *session; }; -extern volatile int session_done; +static int process_attr(struct perf_tool *tool, union perf_event *event, + struct perf_evlist **pevlist) +{ + struct perf_script *scr = container_of(tool, struct perf_script, tool); + struct perf_evlist *evlist; + struct perf_evsel *evsel, *pos; + int err; + + err = perf_event__process_attr(tool, event, pevlist); + if (err) + return err; + + evlist = *pevlist; + evsel = perf_evlist__last(*pevlist); + + if (evsel->attr.type >= PERF_TYPE_MAX) + return 0; + + list_for_each_entry(pos, &evlist->entries, node) { + if (pos->attr.type == evsel->attr.type && pos != evsel) + return 0; + } + + set_print_ip_opts(&evsel->attr); + + return perf_evsel__check_attr(evsel, scr->session); +} static void sig_handler(int sig __maybe_unused) { session_done = 1; } -static int __cmd_script(struct perf_session *session) +static int __cmd_script(struct perf_script *script) { int ret; signal(SIGINT, sig_handler); - ret = perf_session__process_events(session, &perf_script); + ret = perf_session__process_events(script->session, &script->tool); if (debug_mode) pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered); @@ -1092,10 +1139,14 @@ int find_scripts(char **scripts_array, char **scripts_path_array) char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; struct perf_session *session; + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + }; char *temp; int i = 0; - session = perf_session__new(input_name, O_RDONLY, 0, false, NULL); + session = perf_session__new(&file, false, NULL); if (!session) return -1; @@ -1245,6 +1296,21 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) char *script_path = NULL; const char **__argv; int i, j, err; + struct perf_script script = { + .tool = { + .sample = process_sample_event, + .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, + .comm = perf_event__process_comm, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, + .attr = process_attr, + .tracing_data = perf_event__process_tracing_data, + .build_id = perf_event__process_build_id, + .ordered_samples = true, + .ordering_requires_timestamps = true, + }, + }; const struct option options[] = { OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), @@ -1296,12 +1362,17 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "perf script [<options>] <top-script> [script-args]", NULL }; + struct perf_data_file file = { + .mode = PERF_DATA_MODE_READ, + }; setup_scripting(); argc = parse_options(argc, argv, options, script_usage, PARSE_OPT_STOP_AT_NON_OPTION); + file.path = input_name; + if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) { rec_script_path = get_script_path(argv[1], RECORD_SUFFIX); if (!rec_script_path) @@ -1465,11 +1536,12 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) if (!script_name) setup_pager(); - session = perf_session__new(input_name, O_RDONLY, 0, false, - &perf_script); + session = perf_session__new(&file, false, &script.tool); if (session == NULL) return -ENOMEM; + script.session = session; + if (cpu_list) { if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap)) return -1; @@ -1493,7 +1565,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) return -1; } - input = open(session->filename, O_RDONLY); /* input_name */ + input = open(file.path, O_RDONLY); /* input_name */ if (input < 0) { perror("failed to open file"); return -1; @@ -1533,7 +1605,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) if (err < 0) goto out; - err = __cmd_script(session); + err = __cmd_script(&script); perf_session__delete(session); cleanup_scripting(); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 352fbd7ff4a..0fc1c941a73 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -46,6 +46,7 @@ #include "util/util.h" #include "util/parse-options.h" #include "util/parse-events.h" +#include "util/pmu.h" #include "util/event.h" #include "util/evlist.h" #include "util/evsel.h" @@ -70,6 +71,41 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix); static void print_counter(struct perf_evsel *counter, char *prefix); static void print_aggr(char *prefix); +/* Default events used for perf stat -T */ +static const char * const transaction_attrs[] = { + "task-clock", + "{" + "instructions," + "cycles," + "cpu/cycles-t/," + "cpu/tx-start/," + "cpu/el-start/," + "cpu/cycles-ct/" + "}" +}; + +/* More limited version when the CPU does not have all events. */ +static const char * const transaction_limited_attrs[] = { + "task-clock", + "{" + "instructions," + "cycles," + "cpu/cycles-t/," + "cpu/tx-start/" + "}" +}; + +/* must match transaction_attrs and the beginning limited_attrs */ +enum { + T_TASK_CLOCK, + T_INSTRUCTIONS, + T_CYCLES, + T_CYCLES_IN_TX, + T_TRANSACTION_START, + T_ELISION_START, + T_CYCLES_IN_TX_CP, +}; + static struct perf_evlist *evsel_list; static struct perf_target target = { @@ -90,6 +126,7 @@ static enum aggr_mode aggr_mode = AGGR_GLOBAL; static volatile pid_t child_pid = -1; static bool null_run = false; static int detailed_run = 0; +static bool transaction_run; static bool big_num = true; static int big_num_opt = -1; static const char *csv_sep = NULL; @@ -100,6 +137,7 @@ static const char *pre_cmd = NULL; static const char *post_cmd = NULL; static bool sync_run = false; static unsigned int interval = 0; +static unsigned int initial_delay = 0; static bool forever = false; static struct timespec ref_time; static struct cpu_map *aggr_map; @@ -213,7 +251,10 @@ static struct stats runtime_l1_icache_stats[MAX_NR_CPUS]; static struct stats runtime_ll_cache_stats[MAX_NR_CPUS]; static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS]; static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS]; +static struct stats runtime_cycles_in_tx_stats[MAX_NR_CPUS]; static struct stats walltime_nsecs_stats; +static struct stats runtime_transaction_stats[MAX_NR_CPUS]; +static struct stats runtime_elision_stats[MAX_NR_CPUS]; static void perf_stat__reset_stats(struct perf_evlist *evlist) { @@ -235,6 +276,11 @@ static void perf_stat__reset_stats(struct perf_evlist *evlist) memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats)); memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats)); memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats)); + memset(runtime_cycles_in_tx_stats, 0, + sizeof(runtime_cycles_in_tx_stats)); + memset(runtime_transaction_stats, 0, + sizeof(runtime_transaction_stats)); + memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats)); memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats)); } @@ -254,7 +300,8 @@ static int create_perf_stat_counter(struct perf_evsel *evsel) if (!perf_target__has_task(&target) && perf_evsel__is_group_leader(evsel)) { attr->disabled = 1; - attr->enable_on_exec = 1; + if (!initial_delay) + attr->enable_on_exec = 1; } return perf_evsel__open_per_thread(evsel, evsel_list->threads); @@ -272,6 +319,29 @@ static inline int nsec_counter(struct perf_evsel *evsel) return 0; } +static struct perf_evsel *nth_evsel(int n) +{ + static struct perf_evsel **array; + static int array_len; + struct perf_evsel *ev; + int j; + + /* Assumes this only called when evsel_list does not change anymore. */ + if (!array) { + list_for_each_entry(ev, &evsel_list->entries, node) + array_len++; + array = malloc(array_len * sizeof(void *)); + if (!array) + exit(ENOMEM); + j = 0; + list_for_each_entry(ev, &evsel_list->entries, node) + array[j++] = ev; + } + if (n < array_len) + return array[n]; + return NULL; +} + /* * Update various tracking values we maintain to print * more semantic information such as miss/hit ratios, @@ -283,6 +353,15 @@ static void update_shadow_stats(struct perf_evsel *counter, u64 *count) update_stats(&runtime_nsecs_stats[0], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) update_stats(&runtime_cycles_stats[0], count[0]); + else if (transaction_run && + perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX))) + update_stats(&runtime_cycles_in_tx_stats[0], count[0]); + else if (transaction_run && + perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START))) + update_stats(&runtime_transaction_stats[0], count[0]); + else if (transaction_run && + perf_evsel__cmp(counter, nth_evsel(T_ELISION_START))) + update_stats(&runtime_elision_stats[0], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) update_stats(&runtime_stalled_cycles_front_stats[0], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) @@ -414,6 +493,22 @@ static void print_interval(void) list_for_each_entry(counter, &evsel_list->entries, node) print_counter_aggr(counter, prefix); } + + fflush(output); +} + +static void handle_initial_delay(void) +{ + struct perf_evsel *counter; + + if (initial_delay) { + const int ncpus = cpu_map__nr(evsel_list->cpus), + nthreads = thread_map__nr(evsel_list->threads); + + usleep(initial_delay * 1000); + list_for_each_entry(counter, &evsel_list->entries, node) + perf_evsel__enable(counter, ncpus, nthreads); + } } static int __run_perf_stat(int argc, const char **argv) @@ -439,6 +534,7 @@ static int __run_perf_stat(int argc, const char **argv) perror("failed to prepare workload"); return -1; } + child_pid = evsel_list->workload.pid; } if (group) @@ -486,6 +582,7 @@ static int __run_perf_stat(int argc, const char **argv) if (forks) { perf_evlist__start_workload(evsel_list); + handle_initial_delay(); if (interval) { while (!waitpid(child_pid, &status, WNOHANG)) { @@ -497,6 +594,7 @@ static int __run_perf_stat(int argc, const char **argv) if (WIFSIGNALED(status)) psignal(WTERMSIG(status), argv[0]); } else { + handle_initial_delay(); while (!done) { nanosleep(&ts, NULL); if (interval) @@ -608,10 +706,13 @@ static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) { double msecs = avg / 1e6; const char *fmt = csv_output ? "%.6f%s%s" : "%18.6f%s%-25s"; + char name[25]; aggr_printout(evsel, cpu, nr); - fprintf(output, fmt, msecs, csv_sep, perf_evsel__name(evsel)); + scnprintf(name, sizeof(name), "%s%s", + perf_evsel__name(evsel), csv_output ? "" : " (msec)"); + fprintf(output, fmt, msecs, csv_sep, name); if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); @@ -807,7 +908,7 @@ static void print_ll_cache_misses(int cpu, static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) { - double total, ratio = 0.0; + double total, ratio = 0.0, total2; const char *fmt; if (csv_output) @@ -832,11 +933,10 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { total = avg_stats(&runtime_cycles_stats[cpu]); - if (total) + if (total) { ratio = avg / total; - - fprintf(output, " # %5.2f insns per cycle ", ratio); - + fprintf(output, " # %5.2f insns per cycle ", ratio); + } total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]); total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu])); @@ -899,10 +999,47 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { total = avg_stats(&runtime_nsecs_stats[cpu]); + if (total) { + ratio = avg / total; + fprintf(output, " # %8.3f GHz ", ratio); + } + } else if (transaction_run && + perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX))) { + total = avg_stats(&runtime_cycles_stats[cpu]); + if (total) + fprintf(output, + " # %5.2f%% transactional cycles ", + 100.0 * (avg / total)); + } else if (transaction_run && + perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX_CP))) { + total = avg_stats(&runtime_cycles_stats[cpu]); + total2 = avg_stats(&runtime_cycles_in_tx_stats[cpu]); + if (total2 < avg) + total2 = avg; + if (total) + fprintf(output, + " # %5.2f%% aborted cycles ", + 100.0 * ((total2-avg) / total)); + } else if (transaction_run && + perf_evsel__cmp(evsel, nth_evsel(T_TRANSACTION_START)) && + avg > 0 && + runtime_cycles_in_tx_stats[cpu].n != 0) { + total = avg_stats(&runtime_cycles_in_tx_stats[cpu]); + + if (total) + ratio = total / avg; + + fprintf(output, " # %8.0f cycles / transaction ", ratio); + } else if (transaction_run && + perf_evsel__cmp(evsel, nth_evsel(T_ELISION_START)) && + avg > 0 && + runtime_cycles_in_tx_stats[cpu].n != 0) { + total = avg_stats(&runtime_cycles_in_tx_stats[cpu]); + if (total) - ratio = 1.0 * avg / total; + ratio = total / avg; - fprintf(output, " # %8.3f GHz ", ratio); + fprintf(output, " # %8.0f cycles / elision ", ratio); } else if (runtime_nsecs_stats[cpu].n != 0) { char unit = 'M'; @@ -1095,7 +1232,11 @@ static void print_stat(int argc, const char **argv) if (!csv_output) { fprintf(output, "\n"); fprintf(output, " Performance counter stats for "); - if (!perf_target__has_task(&target)) { + if (target.system_wide) + fprintf(output, "\'system wide"); + else if (target.cpu_list) + fprintf(output, "\'CPU(s) %s", target.cpu_list); + else if (!perf_target__has_task(&target)) { fprintf(output, "\'%s", argv[0]); for (i = 1; i < argc; i++) fprintf(output, " %s", argv[i]); @@ -1216,6 +1357,16 @@ static int perf_stat_init_aggr_mode(void) return 0; } +static int setup_events(const char * const *attrs, unsigned len) +{ + unsigned i; + + for (i = 0; i < len; i++) { + if (parse_events(evsel_list, attrs[i])) + return -1; + } + return 0; +} /* * Add default attributes, if there were no attributes specified or @@ -1334,6 +1485,22 @@ static int add_default_attributes(void) if (null_run) return 0; + if (transaction_run) { + int err; + if (pmu_have_event("cpu", "cycles-ct") && + pmu_have_event("cpu", "el-start")) + err = setup_events(transaction_attrs, + ARRAY_SIZE(transaction_attrs)); + else + err = setup_events(transaction_limited_attrs, + ARRAY_SIZE(transaction_limited_attrs)); + if (err < 0) { + fprintf(stderr, "Cannot set up transaction events\n"); + return -1; + } + return 0; + } + if (!evsel_list->nr_entries) { if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0) return -1; @@ -1368,6 +1535,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) int output_fd = 0; const char *output_name = NULL; const struct option options[] = { + OPT_BOOLEAN('T', "transaction", &transaction_run, + "hardware transaction statistics"), OPT_CALLBACK('e', "event", &evsel_list, "event", "event selector. use 'perf list' to list available events", parse_events_option), @@ -1419,13 +1588,15 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) "aggregate counts per processor socket", AGGR_SOCKET), OPT_SET_UINT(0, "per-core", &aggr_mode, "aggregate counts per physical processor core", AGGR_CORE), + OPT_UINTEGER('D', "delay", &initial_delay, + "ms to wait before starting measurement after program start"), OPT_END() }; const char * const stat_usage[] = { "perf stat [<options>] [<command>]", NULL }; - int status = -ENOMEM, run_idx; + int status = -EINVAL, run_idx; const char *mode; setlocale(LC_ALL, ""); @@ -1443,12 +1614,15 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) if (output_name && output_fd) { fprintf(stderr, "cannot use both --output and --log-fd\n"); - usage_with_options(stat_usage, options); + parse_options_usage(stat_usage, options, "o", 1); + parse_options_usage(NULL, options, "log-fd", 0); + goto out; } if (output_fd < 0) { fprintf(stderr, "argument to --log-fd must be a > 0\n"); - usage_with_options(stat_usage, options); + parse_options_usage(stat_usage, options, "log-fd", 0); + goto out; } if (!output) { @@ -1485,16 +1659,21 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) /* User explicitly passed -B? */ if (big_num_opt == 1) { fprintf(stderr, "-B option not supported with -x\n"); - usage_with_options(stat_usage, options); + parse_options_usage(stat_usage, options, "B", 1); + parse_options_usage(NULL, options, "x", 1); + goto out; } else /* Nope, so disable big number formatting */ big_num = false; } else if (big_num_opt == 0) /* User passed --no-big-num */ big_num = false; - if (!argc && !perf_target__has_task(&target)) + if (!argc && perf_target__none(&target)) usage_with_options(stat_usage, options); + if (run_count < 0) { - usage_with_options(stat_usage, options); + pr_err("Run count must be a positive number\n"); + parse_options_usage(stat_usage, options, "r", 1); + goto out; } else if (run_count == 0) { forever = true; run_count = 1; @@ -1506,8 +1685,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) fprintf(stderr, "both cgroup and no-aggregation " "modes only available in system-wide mode\n"); - usage_with_options(stat_usage, options); - return -1; + parse_options_usage(stat_usage, options, "G", 1); + parse_options_usage(NULL, options, "A", 1); + parse_options_usage(NULL, options, "a", 1); + goto out; } if (add_default_attributes()) @@ -1516,25 +1697,28 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) perf_target__validate(&target); if (perf_evlist__create_maps(evsel_list, &target) < 0) { - if (perf_target__has_task(&target)) + if (perf_target__has_task(&target)) { pr_err("Problems finding threads of monitor\n"); - if (perf_target__has_cpu(&target)) + parse_options_usage(stat_usage, options, "p", 1); + parse_options_usage(NULL, options, "t", 1); + } else if (perf_target__has_cpu(&target)) { perror("failed to parse CPUs map"); - - usage_with_options(stat_usage, options); - return -1; + parse_options_usage(stat_usage, options, "C", 1); + parse_options_usage(NULL, options, "a", 1); + } + goto out; } if (interval && interval < 100) { pr_err("print interval must be >= 100ms\n"); - usage_with_options(stat_usage, options); - return -1; + parse_options_usage(stat_usage, options, "I", 1); + goto out_free_maps; } if (perf_evlist__alloc_stats(evsel_list, interval)) goto out_free_maps; if (perf_stat_init_aggr_mode()) - goto out; + goto out_free_maps; /* * We dont want to block the signals - that would cause diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 4536a92b18f..41c9bde2fb6 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -12,6 +12,8 @@ * of the License. */ +#include <traceevent/event-parse.h> + #include "builtin.h" #include "util/util.h" @@ -19,6 +21,7 @@ #include "util/color.h" #include <linux/list.h> #include "util/cache.h" +#include "util/evlist.h" #include "util/evsel.h" #include <linux/rbtree.h> #include "util/symbol.h" @@ -33,6 +36,7 @@ #include "util/session.h" #include "util/svghelper.h" #include "util/tool.h" +#include "util/data.h" #define SUPPORT_OLD_POWER_EVENTS 1 #define PWR_EVENT_EXIT -1 @@ -328,25 +332,6 @@ struct wakeup_entry { int success; }; -/* - * trace_flag_type is an enumeration that holds different - * states when a trace occurs. These are: - * IRQS_OFF - interrupts were disabled - * IRQS_NOSUPPORT - arch does not support irqs_disabled_flags - * NEED_RESCED - reschedule is requested - * HARDIRQ - inside an interrupt handler - * SOFTIRQ - inside a softirq handler - */ -enum trace_flag_type { - TRACE_FLAG_IRQS_OFF = 0x01, - TRACE_FLAG_IRQS_NOSUPPORT = 0x02, - TRACE_FLAG_NEED_RESCHED = 0x04, - TRACE_FLAG_HARDIRQ = 0x08, - TRACE_FLAG_SOFTIRQ = 0x10, -}; - - - struct sched_switch { struct trace_entry te; char prev_comm[TASK_COMM_LEN]; @@ -479,6 +464,8 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te) } } +typedef int (*tracepoint_handler)(struct perf_evsel *evsel, + struct perf_sample *sample); static int process_sample_event(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, @@ -486,8 +473,6 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, struct perf_evsel *evsel, struct machine *machine __maybe_unused) { - struct trace_entry *te; - if (evsel->attr.sample_type & PERF_SAMPLE_TIME) { if (!first_time || first_time > sample->time) first_time = sample->time; @@ -495,68 +480,89 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, last_time = sample->time; } - te = (void *)sample->raw_data; - if ((evsel->attr.sample_type & PERF_SAMPLE_RAW) && sample->raw_size > 0) { - char *event_str; -#ifdef SUPPORT_OLD_POWER_EVENTS - struct power_entry_old *peo; - peo = (void *)te; -#endif - /* - * FIXME: use evsel, its already mapped from id to perf_evsel, - * remove perf_header__find_event infrastructure bits. - * Mapping all these "power:cpu_idle" strings to the tracepoint - * ID and then just comparing against evsel->attr.config. - * - * e.g.: - * - * if (evsel->attr.config == power_cpu_idle_id) - */ - event_str = perf_header__find_event(te->type); - - if (!event_str) - return 0; - - if (sample->cpu > numcpus) - numcpus = sample->cpu; - - if (strcmp(event_str, "power:cpu_idle") == 0) { - struct power_processor_entry *ppe = (void *)te; - if (ppe->state == (u32)PWR_EVENT_EXIT) - c_state_end(ppe->cpu_id, sample->time); - else - c_state_start(ppe->cpu_id, sample->time, - ppe->state); - } - else if (strcmp(event_str, "power:cpu_frequency") == 0) { - struct power_processor_entry *ppe = (void *)te; - p_state_change(ppe->cpu_id, sample->time, ppe->state); - } + if (sample->cpu > numcpus) + numcpus = sample->cpu; + + if (evsel->handler != NULL) { + tracepoint_handler f = evsel->handler; + return f(evsel, sample); + } + + return 0; +} + +static int +process_sample_cpu_idle(struct perf_evsel *evsel __maybe_unused, + struct perf_sample *sample) +{ + struct power_processor_entry *ppe = sample->raw_data; + + if (ppe->state == (u32) PWR_EVENT_EXIT) + c_state_end(ppe->cpu_id, sample->time); + else + c_state_start(ppe->cpu_id, sample->time, ppe->state); + return 0; +} + +static int +process_sample_cpu_frequency(struct perf_evsel *evsel __maybe_unused, + struct perf_sample *sample) +{ + struct power_processor_entry *ppe = sample->raw_data; + + p_state_change(ppe->cpu_id, sample->time, ppe->state); + return 0; +} + +static int +process_sample_sched_wakeup(struct perf_evsel *evsel __maybe_unused, + struct perf_sample *sample) +{ + struct trace_entry *te = sample->raw_data; - else if (strcmp(event_str, "sched:sched_wakeup") == 0) - sched_wakeup(sample->cpu, sample->time, sample->pid, te); + sched_wakeup(sample->cpu, sample->time, sample->pid, te); + return 0; +} + +static int +process_sample_sched_switch(struct perf_evsel *evsel __maybe_unused, + struct perf_sample *sample) +{ + struct trace_entry *te = sample->raw_data; - else if (strcmp(event_str, "sched:sched_switch") == 0) - sched_switch(sample->cpu, sample->time, te); + sched_switch(sample->cpu, sample->time, te); + return 0; +} #ifdef SUPPORT_OLD_POWER_EVENTS - if (use_old_power_events) { - if (strcmp(event_str, "power:power_start") == 0) - c_state_start(peo->cpu_id, sample->time, - peo->value); - - else if (strcmp(event_str, "power:power_end") == 0) - c_state_end(sample->cpu, sample->time); - - else if (strcmp(event_str, - "power:power_frequency") == 0) - p_state_change(peo->cpu_id, sample->time, - peo->value); - } -#endif - } +static int +process_sample_power_start(struct perf_evsel *evsel __maybe_unused, + struct perf_sample *sample) +{ + struct power_entry_old *peo = sample->raw_data; + + c_state_start(peo->cpu_id, sample->time, peo->value); + return 0; +} + +static int +process_sample_power_end(struct perf_evsel *evsel __maybe_unused, + struct perf_sample *sample) +{ + c_state_end(sample->cpu, sample->time); + return 0; +} + +static int +process_sample_power_frequency(struct perf_evsel *evsel __maybe_unused, + struct perf_sample *sample) +{ + struct power_entry_old *peo = sample->raw_data; + + p_state_change(peo->cpu_id, sample->time, peo->value); return 0; } +#endif /* SUPPORT_OLD_POWER_EVENTS */ /* * After the last sample we need to wrap up the current C/P state @@ -974,8 +980,24 @@ static int __cmd_timechart(const char *output_name) .sample = process_sample_event, .ordered_samples = true, }; - struct perf_session *session = perf_session__new(input_name, O_RDONLY, - 0, false, &perf_timechart); + const struct perf_evsel_str_handler power_tracepoints[] = { + { "power:cpu_idle", process_sample_cpu_idle }, + { "power:cpu_frequency", process_sample_cpu_frequency }, + { "sched:sched_wakeup", process_sample_sched_wakeup }, + { "sched:sched_switch", process_sample_sched_switch }, +#ifdef SUPPORT_OLD_POWER_EVENTS + { "power:power_start", process_sample_power_start }, + { "power:power_end", process_sample_power_end }, + { "power:power_frequency", process_sample_power_frequency }, +#endif + }; + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + }; + + struct perf_session *session = perf_session__new(&file, false, + &perf_timechart); int ret = -EINVAL; if (session == NULL) @@ -984,6 +1006,12 @@ static int __cmd_timechart(const char *output_name) if (!perf_session__has_traces(session, "timechart record")) goto out_delete; + if (perf_session__set_tracepoints_handlers(session, + power_tracepoints)) { + pr_err("Initializing session tracepoint handlers failed\n"); + goto out_delete; + } + ret = perf_session__process_events(session, &perf_timechart); if (ret) goto out_delete; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index e06c4f86933..9acca8856cc 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -40,6 +40,7 @@ #include "util/xyarray.h" #include "util/sort.h" #include "util/intlist.h" +#include "arch/common.h" #include "util/debug.h" @@ -102,7 +103,8 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) /* * We can't annotate with just /proc/kallsyms */ - if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) { + if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && + !dso__is_kcore(map->dso)) { pr_err("Can't annotate %s: No vmlinux file was found in the " "path\n", sym->name); sleep(1); @@ -237,8 +239,6 @@ out_unlock: pthread_mutex_unlock(¬es->lock); } -static const char CONSOLE_CLEAR[] = "[H[2J"; - static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel, struct addr_location *al, struct perf_sample *sample) @@ -246,10 +246,10 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel, struct hist_entry *he; pthread_mutex_lock(&evsel->hists.lock); - he = __hists__add_entry(&evsel->hists, al, NULL, sample->period, - sample->weight); + he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, + sample->period, sample->weight, + sample->transaction); pthread_mutex_unlock(&evsel->hists.lock); - if (he == NULL) return NULL; @@ -287,7 +287,7 @@ static void perf_top__print_sym_table(struct perf_top *top) return; } - hists__collapse_resort(&top->sym_evsel->hists); + hists__collapse_resort(&top->sym_evsel->hists, NULL); hists__output_resort(&top->sym_evsel->hists); hists__decay_entries(&top->sym_evsel->hists, top->hide_user_symbols, @@ -553,7 +553,7 @@ static void perf_top__sort_new_samples(void *arg) if (t->evlist->selected != NULL) t->sym_evsel = t->evlist->selected; - hists__collapse_resort(&t->sym_evsel->hists); + hists__collapse_resort(&t->sym_evsel->hists, NULL); hists__output_resort(&t->sym_evsel->hists); hists__decay_entries(&t->sym_evsel->hists, t->hide_user_symbols, @@ -689,7 +689,7 @@ static void perf_event__process_sample(struct perf_tool *tool, { struct perf_top *top = container_of(tool, struct perf_top, tool); struct symbol *parent = NULL; - u64 ip = event->ip.ip; + u64 ip = sample->ip; struct addr_location al; int err; @@ -699,10 +699,10 @@ static void perf_event__process_sample(struct perf_tool *tool, if (!seen) seen = intlist__new(NULL); - if (!intlist__has_entry(seen, event->ip.pid)) { + if (!intlist__has_entry(seen, sample->pid)) { pr_err("Can't find guest [%d]'s kernel information\n", - event->ip.pid); - intlist__add(seen, event->ip.pid); + sample->pid); + intlist__add(seen, sample->pid); } return; } @@ -716,8 +716,7 @@ static void perf_event__process_sample(struct perf_tool *tool, if (event->header.misc & PERF_RECORD_MISC_EXACT_IP) top->exact_samples++; - if (perf_event__preprocess_sample(event, machine, &al, sample, - symbol_filter) < 0 || + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0 || al.filtered) return; @@ -772,8 +771,8 @@ static void perf_event__process_sample(struct perf_tool *tool, sample->callchain) { err = machine__resolve_callchain(machine, evsel, al.thread, sample, - &parent); - + &parent, &al, + top->max_stack); if (err) return; } @@ -812,7 +811,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) ret = perf_evlist__parse_sample(top->evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); - continue; + goto next_event; } evsel = perf_evlist__id2evsel(session->evlist, sample.id); @@ -827,18 +826,19 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) case PERF_RECORD_MISC_USER: ++top->us_samples; if (top->hide_user_symbols) - continue; + goto next_event; machine = &session->machines.host; break; case PERF_RECORD_MISC_KERNEL: ++top->kernel_samples; if (top->hide_kernel_symbols) - continue; + goto next_event; machine = &session->machines.host; break; case PERF_RECORD_MISC_GUEST_KERNEL: ++top->guest_kernel_samples; - machine = perf_session__find_machine(session, event->ip.pid); + machine = perf_session__find_machine(session, + sample.pid); break; case PERF_RECORD_MISC_GUEST_USER: ++top->guest_us_samples; @@ -848,7 +848,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) */ /* Fall thru */ default: - continue; + goto next_event; } @@ -857,9 +857,11 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) &sample, machine); } else if (event->header.type < PERF_RECORD_MAX) { hists__inc_nr_events(&evsel->hists, event->header.type); - machine__process_event(machine, event); + machine__process_event(machine, event, &sample); } else ++session->stats.nr_unknown_events; +next_event: + perf_evlist__mmap_consume(top->evlist, idx); } } @@ -931,14 +933,19 @@ static int __cmd_top(struct perf_top *top) struct perf_record_opts *opts = &top->record_opts; pthread_t thread; int ret; - /* - * FIXME: perf_session__new should allow passing a O_MMAP, so that all this - * mmap reading, etc is encapsulated in it. Use O_WRONLY for now. - */ - top->session = perf_session__new(NULL, O_WRONLY, false, false, NULL); + + top->session = perf_session__new(NULL, false, NULL); if (top->session == NULL) return -ENOMEM; + machines__set_symbol_filter(&top->session->machines, symbol_filter); + + if (!objdump_path) { + ret = perf_session_env__lookup_objdump(&top->session->header.env); + if (ret) + goto out_delete; + } + ret = perf_top__setup_sample_type(top); if (ret) goto out_delete; @@ -1009,16 +1016,16 @@ out_delete: } static int -parse_callchain_opt(const struct option *opt, const char *arg, int unset) +callchain_opt(const struct option *opt, const char *arg, int unset) { - /* - * --no-call-graph - */ - if (unset) - return 0; - symbol_conf.use_callchain = true; + return record_callchain_opt(opt, arg, unset); +} +static int +parse_callchain_opt(const struct option *opt, const char *arg, int unset) +{ + symbol_conf.use_callchain = true; return record_parse_callchain_opt(opt, arg, unset); } @@ -1034,7 +1041,7 @@ parse_percent_limit(const struct option *opt, const char *arg, int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) { - int status; + int status = -1; char errbuf[BUFSIZ]; struct perf_top top = { .count_filter = 5, @@ -1044,10 +1051,11 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, .freq = 4000, /* 4 KHz */ - .target = { + .target = { .uses_mmap = true, }, }, + .max_stack = PERF_MAX_STACK_DEPTH, .sym_pcnt_filter = 5, }; struct perf_record_opts *opts = &top.record_opts; @@ -1067,10 +1075,13 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "list of cpus to monitor"), 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_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols, "hide kernel symbols"), - OPT_UINTEGER('m', "mmap-pages", &opts->mmap_pages, - "number of mmap data pages"), + OPT_CALLBACK('m', "mmap-pages", &opts->mmap_pages, "pages", + "number of mmap data pages", + perf_evlist__parse_mmap_pages), OPT_INTEGER('r', "realtime", &top.realtime_prio, "collect data with this RT SCHED_FIFO priority"), OPT_INTEGER('d', "delay", &top.delay_secs, @@ -1096,12 +1107,22 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight"), + "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight," + " abort, in_tx, transaction"), OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples, "Show a column with the number of samples"), - OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts, - "mode[,dump_size]", record_callchain_help, - &parse_callchain_opt, "fp"), + OPT_CALLBACK_NOOPT('G', NULL, &top.record_opts, + NULL, "enables call-graph recording", + &callchain_opt), + OPT_CALLBACK(0, "call-graph", &top.record_opts, + "mode[,dump_size]", record_callchain_help, + &parse_callchain_opt), + OPT_INTEGER(0, "max-stack", &top.max_stack, + "Set the maximum stack depth when parsing the callchain. " + "Default: " __stringify(PERF_MAX_STACK_DEPTH)), + OPT_CALLBACK(0, "ignore-callees", NULL, "regex", + "ignore callees of these functions in call graphs", + report_parse_ignore_callees_opt), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), OPT_STRING(0, "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", @@ -1114,6 +1135,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "Interleave source code with assembly code (default)"), OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw, "Display raw encoding of assembly instructions (default)"), + OPT_STRING(0, "objdump", &objdump_path, "path", + "objdump binary to use for disassembly and annotations"), OPT_STRING('M', "disassembler-style", &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"), @@ -1137,8 +1160,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (sort_order == default_sort_order) sort_order = "dso,symbol"; - if (setup_sorting() < 0) - usage_with_options(top_usage, options); + if (setup_sorting() < 0) { + parse_options_usage(top_usage, options, "s", 1); + goto out_delete_evlist; + } /* display thread wants entries to be collapsed in a different tree */ sort__need_collapse = 1; @@ -1184,20 +1209,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (top.delay_secs < 1) top.delay_secs = 1; - if (opts->user_interval != ULLONG_MAX) - opts->default_interval = opts->user_interval; - if (opts->user_freq != UINT_MAX) - opts->freq = opts->user_freq; - - /* - * User specified count overrides default frequency. - */ - if (opts->default_interval) - opts->freq = 0; - else if (opts->freq) { - opts->default_interval = opts->freq; - } else { - ui__error("frequency and count are zero, aborting\n"); + if (perf_record_opts__config(opts)) { status = -EINVAL; goto out_delete_maps; } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index ab3ed4af146..329b7832b5d 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1,34 +1,1050 @@ +#include <traceevent/event-parse.h> #include "builtin.h" #include "util/color.h" +#include "util/debug.h" #include "util/evlist.h" #include "util/machine.h" +#include "util/session.h" #include "util/thread.h" #include "util/parse-options.h" +#include "util/strlist.h" +#include "util/intlist.h" #include "util/thread_map.h" -#include "event-parse.h" +#include "util/stat.h" #include <libaudit.h> #include <stdlib.h> +#include <sys/eventfd.h> +#include <sys/mman.h> +#include <linux/futex.h> + +/* For older distros: */ +#ifndef MAP_STACK +# define MAP_STACK 0x20000 +#endif + +#ifndef MADV_HWPOISON +# define MADV_HWPOISON 100 +#endif + +#ifndef MADV_MERGEABLE +# define MADV_MERGEABLE 12 +#endif + +#ifndef MADV_UNMERGEABLE +# define MADV_UNMERGEABLE 13 +#endif + +struct tp_field { + int offset; + union { + u64 (*integer)(struct tp_field *field, struct perf_sample *sample); + void *(*pointer)(struct tp_field *field, struct perf_sample *sample); + }; +}; + +#define TP_UINT_FIELD(bits) \ +static u64 tp_field__u##bits(struct tp_field *field, struct perf_sample *sample) \ +{ \ + return *(u##bits *)(sample->raw_data + field->offset); \ +} + +TP_UINT_FIELD(8); +TP_UINT_FIELD(16); +TP_UINT_FIELD(32); +TP_UINT_FIELD(64); + +#define TP_UINT_FIELD__SWAPPED(bits) \ +static u64 tp_field__swapped_u##bits(struct tp_field *field, struct perf_sample *sample) \ +{ \ + u##bits value = *(u##bits *)(sample->raw_data + field->offset); \ + return bswap_##bits(value);\ +} + +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) +{ + field->offset = format_field->offset; + + switch (format_field->size) { + case 1: + field->integer = tp_field__u8; + break; + case 2: + field->integer = needs_swap ? tp_field__swapped_u16 : tp_field__u16; + break; + case 4: + field->integer = needs_swap ? tp_field__swapped_u32 : tp_field__u32; + break; + case 8: + field->integer = needs_swap ? tp_field__swapped_u64 : tp_field__u64; + break; + default: + return -1; + } + + return 0; +} + +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) +{ + field->offset = format_field->offset; + field->pointer = tp_field__ptr; + return 0; +} + +struct syscall_tp { + struct tp_field id; + union { + struct tp_field args, ret; + }; +}; + +static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel, + struct tp_field *field, + const char *name) +{ + struct format_field *format_field = perf_evsel__field(evsel, name); + + if (format_field == NULL) + return -1; + + return tp_field__init_uint(field, format_field, evsel->needs_swap); +} + +#define perf_evsel__init_sc_tp_uint_field(evsel, name) \ + ({ struct syscall_tp *sc = evsel->priv;\ + perf_evsel__init_tp_uint_field(evsel, &sc->name, #name); }) + +static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel, + struct tp_field *field, + const char *name) +{ + struct format_field *format_field = perf_evsel__field(evsel, name); + + if (format_field == NULL) + return -1; + + return tp_field__init_ptr(field, format_field); +} + +#define perf_evsel__init_sc_tp_ptr_field(evsel, name) \ + ({ struct syscall_tp *sc = evsel->priv;\ + perf_evsel__init_tp_ptr_field(evsel, &sc->name, #name); }) + +static void perf_evsel__delete_priv(struct perf_evsel *evsel) +{ + free(evsel->priv); + evsel->priv = NULL; + perf_evsel__delete(evsel); +} + +static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, + void *handler, int idx) +{ + struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction, idx); + + if (evsel) { + evsel->priv = malloc(sizeof(struct syscall_tp)); + + if (evsel->priv == NULL) + goto out_delete; + + if (perf_evsel__init_sc_tp_uint_field(evsel, id)) + goto out_delete; + + evsel->handler = handler; + } + + return evsel; + +out_delete: + perf_evsel__delete_priv(evsel); + return NULL; +} + +#define perf_evsel__sc_tp_uint(evsel, name, sample) \ + ({ struct syscall_tp *fields = evsel->priv; \ + fields->name.integer(&fields->name, sample); }) + +#define perf_evsel__sc_tp_ptr(evsel, name, sample) \ + ({ struct syscall_tp *fields = evsel->priv; \ + fields->name.pointer(&fields->name, sample); }) + +static int perf_evlist__add_syscall_newtp(struct perf_evlist *evlist, + void *sys_enter_handler, + void *sys_exit_handler) +{ + int ret = -1; + int idx = evlist->nr_entries; + struct perf_evsel *sys_enter, *sys_exit; + + sys_enter = perf_evsel__syscall_newtp("sys_enter", sys_enter_handler, idx++); + 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", sys_exit_handler, idx++); + if (sys_exit == NULL) + goto out_delete_sys_enter; + + if (perf_evsel__init_sc_tp_uint_field(sys_exit, ret)) + goto out_delete_sys_exit; + + perf_evlist__add(evlist, sys_enter); + perf_evlist__add(evlist, sys_exit); + + ret = 0; +out: + return ret; + +out_delete_sys_exit: + perf_evsel__delete_priv(sys_exit); +out_delete_sys_enter: + perf_evsel__delete_priv(sys_enter); + goto out; +} + + +struct syscall_arg { + unsigned long val; + struct thread *thread; + struct trace *trace; + void *parm; + u8 idx; + u8 mask; +}; + +struct strarray { + int offset; + int nr_entries; + const char **entries; +}; + +#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \ + .nr_entries = ARRAY_SIZE(array), \ + .entries = array, \ +} + +#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \ + .offset = off, \ + .nr_entries = ARRAY_SIZE(array), \ + .entries = array, \ +} + +static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size, + const char *intfmt, + struct syscall_arg *arg) +{ + struct strarray *sa = arg->parm; + int idx = arg->val - sa->offset; + + if (idx < 0 || idx >= sa->nr_entries) + return scnprintf(bf, size, intfmt, arg->val); + + return scnprintf(bf, size, "%s", sa->entries[idx]); +} + +static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size, + struct syscall_arg *arg) +{ + return __syscall_arg__scnprintf_strarray(bf, size, "%d", arg); +} + +#define SCA_STRARRAY syscall_arg__scnprintf_strarray + +static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size, + struct syscall_arg *arg) +{ + return __syscall_arg__scnprintf_strarray(bf, size, "%#x", arg); +} + +#define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray + +static size_t syscall_arg__scnprintf_fd(char *bf, size_t size, + struct syscall_arg *arg); + +#define SCA_FD syscall_arg__scnprintf_fd + +static size_t syscall_arg__scnprintf_fd_at(char *bf, size_t size, + struct syscall_arg *arg) +{ + int fd = arg->val; + + if (fd == AT_FDCWD) + return scnprintf(bf, size, "CWD"); + + return syscall_arg__scnprintf_fd(bf, size, arg); +} + +#define SCA_FDAT syscall_arg__scnprintf_fd_at + +static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size, + struct syscall_arg *arg); + +#define SCA_CLOSE_FD syscall_arg__scnprintf_close_fd + +static size_t syscall_arg__scnprintf_hex(char *bf, size_t size, + struct syscall_arg *arg) +{ + return scnprintf(bf, size, "%#lx", arg->val); +} + +#define SCA_HEX syscall_arg__scnprintf_hex + +static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, prot = arg->val; + + if (prot == PROT_NONE) + return scnprintf(bf, size, "NONE"); +#define P_MMAP_PROT(n) \ + if (prot & PROT_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + prot &= ~PROT_##n; \ + } + + P_MMAP_PROT(EXEC); + P_MMAP_PROT(READ); + P_MMAP_PROT(WRITE); +#ifdef PROT_SEM + P_MMAP_PROT(SEM); +#endif + P_MMAP_PROT(GROWSDOWN); + P_MMAP_PROT(GROWSUP); +#undef P_MMAP_PROT + + if (prot) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", prot); + + return printed; +} + +#define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot + +static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_MMAP_FLAG(n) \ + if (flags & MAP_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~MAP_##n; \ + } + + P_MMAP_FLAG(SHARED); + P_MMAP_FLAG(PRIVATE); +#ifdef MAP_32BIT + P_MMAP_FLAG(32BIT); +#endif + P_MMAP_FLAG(ANONYMOUS); + P_MMAP_FLAG(DENYWRITE); + P_MMAP_FLAG(EXECUTABLE); + P_MMAP_FLAG(FILE); + P_MMAP_FLAG(FIXED); + P_MMAP_FLAG(GROWSDOWN); +#ifdef MAP_HUGETLB + P_MMAP_FLAG(HUGETLB); +#endif + P_MMAP_FLAG(LOCKED); + P_MMAP_FLAG(NONBLOCK); + P_MMAP_FLAG(NORESERVE); + P_MMAP_FLAG(POPULATE); + P_MMAP_FLAG(STACK); +#ifdef MAP_UNINITIALIZED + P_MMAP_FLAG(UNINITIALIZED); +#endif +#undef P_MMAP_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags + +static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size, + struct syscall_arg *arg) +{ + int behavior = arg->val; + + switch (behavior) { +#define P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n) + P_MADV_BHV(NORMAL); + P_MADV_BHV(RANDOM); + P_MADV_BHV(SEQUENTIAL); + P_MADV_BHV(WILLNEED); + P_MADV_BHV(DONTNEED); + P_MADV_BHV(REMOVE); + P_MADV_BHV(DONTFORK); + P_MADV_BHV(DOFORK); + P_MADV_BHV(HWPOISON); +#ifdef MADV_SOFT_OFFLINE + P_MADV_BHV(SOFT_OFFLINE); +#endif + P_MADV_BHV(MERGEABLE); + P_MADV_BHV(UNMERGEABLE); +#ifdef MADV_HUGEPAGE + P_MADV_BHV(HUGEPAGE); +#endif +#ifdef MADV_NOHUGEPAGE + P_MADV_BHV(NOHUGEPAGE); +#endif +#ifdef MADV_DONTDUMP + P_MADV_BHV(DONTDUMP); +#endif +#ifdef MADV_DODUMP + P_MADV_BHV(DODUMP); +#endif +#undef P_MADV_PHV + default: break; + } + + return scnprintf(bf, size, "%#x", behavior); +} + +#define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior + +static size_t syscall_arg__scnprintf_flock(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, op = arg->val; + + if (op == 0) + return scnprintf(bf, size, "NONE"); +#define P_CMD(cmd) \ + if ((op & LOCK_##cmd) == LOCK_##cmd) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #cmd); \ + op &= ~LOCK_##cmd; \ + } + + P_CMD(SH); + P_CMD(EX); + P_CMD(NB); + P_CMD(UN); + P_CMD(MAND); + P_CMD(RW); + P_CMD(READ); + P_CMD(WRITE); +#undef P_OP + + if (op) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", op); + + return printed; +} + +#define SCA_FLOCK syscall_arg__scnprintf_flock + +static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg) +{ + enum syscall_futex_args { + SCF_UADDR = (1 << 0), + SCF_OP = (1 << 1), + SCF_VAL = (1 << 2), + SCF_TIMEOUT = (1 << 3), + SCF_UADDR2 = (1 << 4), + SCF_VAL3 = (1 << 5), + }; + int op = arg->val; + int cmd = op & FUTEX_CMD_MASK; + size_t printed = 0; + + switch (cmd) { +#define P_FUTEX_OP(n) case FUTEX_##n: printed = scnprintf(bf, size, #n); + P_FUTEX_OP(WAIT); arg->mask |= SCF_VAL3|SCF_UADDR2; break; + P_FUTEX_OP(WAKE); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; + P_FUTEX_OP(FD); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; + P_FUTEX_OP(REQUEUE); arg->mask |= SCF_VAL3|SCF_TIMEOUT; break; + P_FUTEX_OP(CMP_REQUEUE); arg->mask |= SCF_TIMEOUT; break; + P_FUTEX_OP(CMP_REQUEUE_PI); arg->mask |= SCF_TIMEOUT; break; + P_FUTEX_OP(WAKE_OP); break; + P_FUTEX_OP(LOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; + P_FUTEX_OP(UNLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break; + P_FUTEX_OP(TRYLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2; break; + P_FUTEX_OP(WAIT_BITSET); arg->mask |= SCF_UADDR2; break; + P_FUTEX_OP(WAKE_BITSET); arg->mask |= SCF_UADDR2; break; + P_FUTEX_OP(WAIT_REQUEUE_PI); break; + default: printed = scnprintf(bf, size, "%#x", cmd); break; + } + + if (op & FUTEX_PRIVATE_FLAG) + printed += scnprintf(bf + printed, size - printed, "|PRIV"); + + if (op & FUTEX_CLOCK_REALTIME) + printed += scnprintf(bf + printed, size - printed, "|CLKRT"); + + return printed; +} + +#define SCA_FUTEX_OP syscall_arg__scnprintf_futex_op + +static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", }; +static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, 1); + +static const char *itimers[] = { "REAL", "VIRTUAL", "PROF", }; +static DEFINE_STRARRAY(itimers); + +static const char *whences[] = { "SET", "CUR", "END", +#ifdef SEEK_DATA +"DATA", +#endif +#ifdef SEEK_HOLE +"HOLE", +#endif +}; +static DEFINE_STRARRAY(whences); + +static const char *fcntl_cmds[] = { + "DUPFD", "GETFD", "SETFD", "GETFL", "SETFL", "GETLK", "SETLK", + "SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "F_GETLK64", + "F_SETLK64", "F_SETLKW64", "F_SETOWN_EX", "F_GETOWN_EX", + "F_GETOWNER_UIDS", +}; +static DEFINE_STRARRAY(fcntl_cmds); + +static const char *rlimit_resources[] = { + "CPU", "FSIZE", "DATA", "STACK", "CORE", "RSS", "NPROC", "NOFILE", + "MEMLOCK", "AS", "LOCKS", "SIGPENDING", "MSGQUEUE", "NICE", "RTPRIO", + "RTTIME", +}; +static DEFINE_STRARRAY(rlimit_resources); + +static const char *sighow[] = { "BLOCK", "UNBLOCK", "SETMASK", }; +static DEFINE_STRARRAY(sighow); + +static const char *clockid[] = { + "REALTIME", "MONOTONIC", "PROCESS_CPUTIME_ID", "THREAD_CPUTIME_ID", + "MONOTONIC_RAW", "REALTIME_COARSE", "MONOTONIC_COARSE", +}; +static DEFINE_STRARRAY(clockid); + +static const char *socket_families[] = { + "UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM", + "BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI", + "SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC", + "RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC", + "BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF", + "ALG", "NFC", "VSOCK", +}; +static DEFINE_STRARRAY(socket_families); + +#ifndef SOCK_TYPE_MASK +#define SOCK_TYPE_MASK 0xf +#endif + +static size_t syscall_arg__scnprintf_socket_type(char *bf, size_t size, + struct syscall_arg *arg) +{ + size_t printed; + int type = arg->val, + flags = type & ~SOCK_TYPE_MASK; + + type &= SOCK_TYPE_MASK; + /* + * Can't use a strarray, MIPS may override for ABI reasons. + */ + switch (type) { +#define P_SK_TYPE(n) case SOCK_##n: printed = scnprintf(bf, size, #n); break; + P_SK_TYPE(STREAM); + P_SK_TYPE(DGRAM); + P_SK_TYPE(RAW); + P_SK_TYPE(RDM); + P_SK_TYPE(SEQPACKET); + P_SK_TYPE(DCCP); + P_SK_TYPE(PACKET); +#undef P_SK_TYPE + default: + printed = scnprintf(bf, size, "%#x", type); + } + +#define P_SK_FLAG(n) \ + if (flags & SOCK_##n) { \ + printed += scnprintf(bf + printed, size - printed, "|%s", #n); \ + flags &= ~SOCK_##n; \ + } + + P_SK_FLAG(CLOEXEC); + P_SK_FLAG(NONBLOCK); +#undef P_SK_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "|%#x", flags); + + return printed; +} + +#define SCA_SK_TYPE syscall_arg__scnprintf_socket_type + +#ifndef MSG_PROBE +#define MSG_PROBE 0x10 +#endif +#ifndef MSG_WAITFORONE +#define MSG_WAITFORONE 0x10000 +#endif +#ifndef MSG_SENDPAGE_NOTLAST +#define MSG_SENDPAGE_NOTLAST 0x20000 +#endif +#ifndef MSG_FASTOPEN +#define MSG_FASTOPEN 0x20000000 +#endif + +static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + + if (flags == 0) + return scnprintf(bf, size, "NONE"); +#define P_MSG_FLAG(n) \ + if (flags & MSG_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~MSG_##n; \ + } + + P_MSG_FLAG(OOB); + P_MSG_FLAG(PEEK); + P_MSG_FLAG(DONTROUTE); + P_MSG_FLAG(TRYHARD); + P_MSG_FLAG(CTRUNC); + P_MSG_FLAG(PROBE); + P_MSG_FLAG(TRUNC); + P_MSG_FLAG(DONTWAIT); + P_MSG_FLAG(EOR); + P_MSG_FLAG(WAITALL); + P_MSG_FLAG(FIN); + P_MSG_FLAG(SYN); + P_MSG_FLAG(CONFIRM); + P_MSG_FLAG(RST); + P_MSG_FLAG(ERRQUEUE); + P_MSG_FLAG(NOSIGNAL); + P_MSG_FLAG(MORE); + P_MSG_FLAG(WAITFORONE); + P_MSG_FLAG(SENDPAGE_NOTLAST); + P_MSG_FLAG(FASTOPEN); + P_MSG_FLAG(CMSG_CLOEXEC); +#undef P_MSG_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_MSG_FLAGS syscall_arg__scnprintf_msg_flags + +static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size, + struct syscall_arg *arg) +{ + size_t printed = 0; + int mode = arg->val; + + if (mode == F_OK) /* 0 */ + return scnprintf(bf, size, "F"); +#define P_MODE(n) \ + if (mode & n##_OK) { \ + printed += scnprintf(bf + printed, size - printed, "%s", #n); \ + mode &= ~n##_OK; \ + } + + P_MODE(R); + P_MODE(W); + P_MODE(X); +#undef P_MODE + + if (mode) + printed += scnprintf(bf + printed, size - printed, "|%#x", mode); + + return printed; +} + +#define SCA_ACCMODE syscall_arg__scnprintf_access_mode + +static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + + if (!(flags & O_CREAT)) + arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */ + + if (flags == 0) + return scnprintf(bf, size, "RDONLY"); +#define P_FLAG(n) \ + if (flags & O_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~O_##n; \ + } + + P_FLAG(APPEND); + P_FLAG(ASYNC); + P_FLAG(CLOEXEC); + P_FLAG(CREAT); + P_FLAG(DIRECT); + P_FLAG(DIRECTORY); + P_FLAG(EXCL); + P_FLAG(LARGEFILE); + P_FLAG(NOATIME); + P_FLAG(NOCTTY); +#ifdef O_NONBLOCK + P_FLAG(NONBLOCK); +#elif O_NDELAY + P_FLAG(NDELAY); +#endif +#ifdef O_PATH + P_FLAG(PATH); +#endif + P_FLAG(RDWR); +#ifdef O_DSYNC + if ((flags & O_SYNC) == O_SYNC) + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC"); + else { + P_FLAG(DSYNC); + } +#else + P_FLAG(SYNC); +#endif + P_FLAG(TRUNC); + P_FLAG(WRONLY); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags + +static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + + if (flags == 0) + return scnprintf(bf, size, "NONE"); +#define P_FLAG(n) \ + if (flags & EFD_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~EFD_##n; \ + } + + P_FLAG(SEMAPHORE); + P_FLAG(CLOEXEC); + P_FLAG(NONBLOCK); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_EFD_FLAGS syscall_arg__scnprintf_eventfd_flags + +static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_FLAG(n) \ + if (flags & O_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~O_##n; \ + } + + P_FLAG(CLOEXEC); + P_FLAG(NONBLOCK); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags + +static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg) +{ + int sig = arg->val; + + switch (sig) { +#define P_SIGNUM(n) case SIG##n: return scnprintf(bf, size, #n) + P_SIGNUM(HUP); + P_SIGNUM(INT); + P_SIGNUM(QUIT); + P_SIGNUM(ILL); + P_SIGNUM(TRAP); + P_SIGNUM(ABRT); + P_SIGNUM(BUS); + P_SIGNUM(FPE); + P_SIGNUM(KILL); + P_SIGNUM(USR1); + P_SIGNUM(SEGV); + P_SIGNUM(USR2); + P_SIGNUM(PIPE); + P_SIGNUM(ALRM); + P_SIGNUM(TERM); + P_SIGNUM(STKFLT); + P_SIGNUM(CHLD); + P_SIGNUM(CONT); + P_SIGNUM(STOP); + P_SIGNUM(TSTP); + P_SIGNUM(TTIN); + P_SIGNUM(TTOU); + P_SIGNUM(URG); + P_SIGNUM(XCPU); + P_SIGNUM(XFSZ); + P_SIGNUM(VTALRM); + P_SIGNUM(PROF); + P_SIGNUM(WINCH); + P_SIGNUM(IO); + P_SIGNUM(PWR); + P_SIGNUM(SYS); + default: break; + } + + return scnprintf(bf, size, "%#x", sig); +} + +#define SCA_SIGNUM syscall_arg__scnprintf_signum + +#define TCGETS 0x5401 + +static const char *tioctls[] = { + "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW", + "TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL", + "TIOCSCTTY", "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI", + "TIOCGWINSZ", "TIOCSWINSZ", "TIOCMGET", "TIOCMBIS", "TIOCMBIC", + "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", "FIONREAD", "TIOCLINUX", + "TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", "FIONBIO", + "TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", [0x27] = "TIOCSBRK", + "TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", "TCSETSW2", "TCSETSF2", + "TIOCGRS485", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK", + "TIOCGDEV||TCGETX", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG", + "TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", "TIOCGEXCL", + [0x50] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG", + "TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS", + "TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI", + "TIOCMIWAIT", "TIOCGICOUNT", [0x60] = "FIOQSIZE", +}; + +static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401); + +#define STRARRAY(arg, name, array) \ + .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \ + .arg_parm = { [arg] = &strarray__##array, } static struct syscall_fmt { const char *name; const char *alias; + size_t (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg); + void *arg_parm[6]; bool errmsg; bool timeout; + bool hexret; } syscall_fmts[] = { - { .name = "access", .errmsg = true, }, + { .name = "access", .errmsg = true, + .arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, }, { .name = "arch_prctl", .errmsg = true, .alias = "prctl", }, - { .name = "fstat", .errmsg = true, .alias = "newfstat", }, - { .name = "fstatat", .errmsg = true, .alias = "newfstatat", }, - { .name = "futex", .errmsg = true, }, - { .name = "open", .errmsg = true, }, + { .name = "brk", .hexret = true, + .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, }, + { .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), }, + { .name = "close", .errmsg = true, + .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, + { .name = "connect", .errmsg = true, }, + { .name = "dup", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "dup2", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "dup3", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "epoll_ctl", .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), }, + { .name = "eventfd2", .errmsg = true, + .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, }, + { .name = "faccessat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + { .name = "fadvise64", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fallocate", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fchdir", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fchmod", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fchmodat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + { .name = "fchown", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fchownat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + { .name = "fcntl", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ + [1] = SCA_STRARRAY, /* cmd */ }, + .arg_parm = { [1] = &strarray__fcntl_cmds, /* cmd */ }, }, + { .name = "fdatasync", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "flock", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ + [1] = SCA_FLOCK, /* cmd */ }, }, + { .name = "fsetxattr", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fstat", .errmsg = true, .alias = "newfstat", + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fstatat", .errmsg = true, .alias = "newfstatat", + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + { .name = "fstatfs", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "fsync", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "ftruncate", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "futex", .errmsg = true, + .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, }, + { .name = "futimesat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + { .name = "getdents", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "getdents64", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), }, + { .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, + { .name = "ioctl", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ + [1] = SCA_STRHEXARRAY, /* cmd */ + [2] = SCA_HEX, /* arg */ }, + .arg_parm = { [1] = &strarray__tioctls, /* cmd */ }, }, + { .name = "kill", .errmsg = true, + .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, + { .name = "linkat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + { .name = "lseek", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ + [2] = SCA_STRARRAY, /* whence */ }, + .arg_parm = { [2] = &strarray__whences, /* whence */ }, }, + { .name = "lstat", .errmsg = true, .alias = "newlstat", }, + { .name = "madvise", .errmsg = true, + .arg_scnprintf = { [0] = SCA_HEX, /* start */ + [2] = SCA_MADV_BHV, /* behavior */ }, }, + { .name = "mkdirat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + { .name = "mknodat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, + { .name = "mlock", .errmsg = true, + .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, + { .name = "mlockall", .errmsg = true, + .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, + { .name = "mmap", .hexret = true, + .arg_scnprintf = { [0] = SCA_HEX, /* addr */ + [2] = SCA_MMAP_PROT, /* prot */ + [3] = SCA_MMAP_FLAGS, /* flags */ }, }, + { .name = "mprotect", .errmsg = true, + .arg_scnprintf = { [0] = SCA_HEX, /* start */ + [2] = SCA_MMAP_PROT, /* prot */ }, }, + { .name = "mremap", .hexret = true, + .arg_scnprintf = { [0] = SCA_HEX, /* addr */ + [4] = SCA_HEX, /* new_addr */ }, }, + { .name = "munlock", .errmsg = true, + .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, + { .name = "munmap", .errmsg = true, + .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, + { .name = "name_to_handle_at", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + { .name = "newfstatat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + { .name = "open", .errmsg = true, + .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, }, + { .name = "open_by_handle_at", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ + [2] = SCA_OPEN_FLAGS, /* flags */ }, }, + { .name = "openat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ + [2] = SCA_OPEN_FLAGS, /* flags */ }, }, + { .name = "pipe2", .errmsg = true, + .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, }, { .name = "poll", .errmsg = true, .timeout = true, }, { .name = "ppoll", .errmsg = true, .timeout = true, }, - { .name = "read", .errmsg = true, }, - { .name = "recvfrom", .errmsg = true, }, + { .name = "pread", .errmsg = true, .alias = "pread64", + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "preadv", .errmsg = true, .alias = "pread", + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "prlimit64", .errmsg = true, STRARRAY(1, resource, rlimit_resources), }, + { .name = "pwrite", .errmsg = true, .alias = "pwrite64", + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "pwritev", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "read", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "readlinkat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + { .name = "readv", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "recvfrom", .errmsg = true, + .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, + { .name = "recvmmsg", .errmsg = true, + .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, + { .name = "recvmsg", .errmsg = true, + .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, }, + { .name = "renameat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + { .name = "rt_sigaction", .errmsg = true, + .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, }, + { .name = "rt_sigprocmask", .errmsg = true, STRARRAY(0, how, sighow), }, + { .name = "rt_sigqueueinfo", .errmsg = true, + .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, + { .name = "rt_tgsigqueueinfo", .errmsg = true, + .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, }, { .name = "select", .errmsg = true, .timeout = true, }, - { .name = "socket", .errmsg = true, }, + { .name = "sendmmsg", .errmsg = true, + .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, + { .name = "sendmsg", .errmsg = true, + .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, }, + { .name = "sendto", .errmsg = true, + .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, }, + { .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), }, + { .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, + { .name = "shutdown", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "socket", .errmsg = true, + .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */ + [1] = SCA_SK_TYPE, /* type */ }, + .arg_parm = { [0] = &strarray__socket_families, /* family */ }, }, + { .name = "socketpair", .errmsg = true, + .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */ + [1] = SCA_SK_TYPE, /* type */ }, + .arg_parm = { [0] = &strarray__socket_families, /* family */ }, }, { .name = "stat", .errmsg = true, .alias = "newstat", }, + { .name = "symlinkat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + { .name = "tgkill", .errmsg = true, + .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, }, + { .name = "tkill", .errmsg = true, + .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, + { .name = "uname", .errmsg = true, .alias = "newuname", }, + { .name = "unlinkat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, + { .name = "utimensat", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, }, + { .name = "write", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "writev", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, }; static int syscall_fmt__cmp(const void *name, const void *fmtp) @@ -46,7 +1062,10 @@ static struct syscall_fmt *syscall_fmt__find(const char *name) struct syscall { struct event_format *tp_format; const char *name; + bool filtered; struct syscall_fmt *fmt; + size_t (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg); + void **arg_parm; }; static size_t fprintf_duration(unsigned long t, FILE *fp) @@ -60,7 +1079,7 @@ static size_t fprintf_duration(unsigned long t, FILE *fp) printed += color_fprintf(fp, PERF_COLOR_YELLOW, "%6.3f ms", duration); else printed += color_fprintf(fp, PERF_COLOR_NORMAL, "%6.3f ms", duration); - return printed + fprintf(stdout, "): "); + return printed + fprintf(fp, "): "); } struct thread_trace { @@ -70,14 +1089,27 @@ struct thread_trace { unsigned long nr_events; char *entry_str; double runtime_ms; + struct { + int max; + char **table; + } paths; + + struct intlist *syscall_stats; }; static struct thread_trace *thread_trace__new(void) { - return zalloc(sizeof(struct thread_trace)); + struct thread_trace *ttrace = zalloc(sizeof(struct thread_trace)); + + if (ttrace) + ttrace->paths.max = -1; + + ttrace->syscall_stats = intlist__new(NULL); + + return ttrace; } -static struct thread_trace *thread__trace(struct thread *thread) +static struct thread_trace *thread__trace(struct thread *thread, FILE *fp) { struct thread_trace *ttrace; @@ -95,27 +1127,147 @@ static struct thread_trace *thread__trace(struct thread *thread) return ttrace; fail: - color_fprintf(stdout, PERF_COLOR_RED, + color_fprintf(fp, PERF_COLOR_RED, "WARNING: not enough memory, dropping samples!\n"); return NULL; } struct trace { - int audit_machine; + struct perf_tool tool; + struct { + int machine; + int open_id; + } audit; struct { int max; struct syscall *table; } syscalls; struct perf_record_opts opts; - struct machine host; + struct machine *host; u64 base_time; + bool full_time; + FILE *output; unsigned long nr_events; + struct strlist *ev_qualifier; + bool not_ev_qualifier; + bool live; + const char *last_vfs_getname; + struct intlist *tid_list; + struct intlist *pid_list; bool sched; bool multiple_threads; + bool summary; + bool show_comm; + bool show_tool_stats; double duration_filter; double runtime_ms; + struct { + u64 vfs_getname, proc_getname; + } stats; }; +static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname) +{ + struct thread_trace *ttrace = thread->priv; + + if (fd > ttrace->paths.max) { + char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *)); + + if (npath == NULL) + return -1; + + if (ttrace->paths.max != -1) { + memset(npath + ttrace->paths.max + 1, 0, + (fd - ttrace->paths.max) * sizeof(char *)); + } else { + memset(npath, 0, (fd + 1) * sizeof(char *)); + } + + ttrace->paths.table = npath; + ttrace->paths.max = fd; + } + + ttrace->paths.table[fd] = strdup(pathname); + + return ttrace->paths.table[fd] != NULL ? 0 : -1; +} + +static int thread__read_fd_path(struct thread *thread, int fd) +{ + char linkname[PATH_MAX], pathname[PATH_MAX]; + struct stat st; + int ret; + + if (thread->pid_ == thread->tid) { + scnprintf(linkname, sizeof(linkname), + "/proc/%d/fd/%d", thread->pid_, fd); + } else { + scnprintf(linkname, sizeof(linkname), + "/proc/%d/task/%d/fd/%d", thread->pid_, thread->tid, fd); + } + + if (lstat(linkname, &st) < 0 || st.st_size + 1 > (off_t)sizeof(pathname)) + return -1; + + ret = readlink(linkname, pathname, sizeof(pathname)); + + if (ret < 0 || ret > st.st_size) + return -1; + + pathname[ret] = '\0'; + return trace__set_fd_pathname(thread, fd, pathname); +} + +static const char *thread__fd_path(struct thread *thread, int fd, + struct trace *trace) +{ + struct thread_trace *ttrace = thread->priv; + + if (ttrace == NULL) + return NULL; + + if (fd < 0) + return NULL; + + if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) + if (!trace->live) + return NULL; + ++trace->stats.proc_getname; + if (thread__read_fd_path(thread, fd)) { + return NULL; + } + + return ttrace->paths.table[fd]; +} + +static size_t syscall_arg__scnprintf_fd(char *bf, size_t size, + struct syscall_arg *arg) +{ + int fd = arg->val; + size_t printed = scnprintf(bf, size, "%d", fd); + const char *path = thread__fd_path(arg->thread, fd, arg->trace); + + if (path) + printed += scnprintf(bf + printed, size - printed, "<%s>", path); + + return printed; +} + +static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size, + struct syscall_arg *arg) +{ + int fd = arg->val; + size_t printed = syscall_arg__scnprintf_fd(bf, size, arg); + struct thread_trace *ttrace = arg->thread->priv; + + if (ttrace && fd >= 0 && fd <= ttrace->paths.max) { + free(ttrace->paths.table[fd]); + ttrace->paths.table[fd] = NULL; + } + + return printed; +} + static bool trace__filter_duration(struct trace *trace, double t) { return t < (trace->duration_filter * NSEC_PER_MSEC); @@ -129,10 +1281,12 @@ static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp) } static bool done = false; +static bool interrupted = false; -static void sig_handler(int sig __maybe_unused) +static void sig_handler(int sig) { done = true; + interrupted = sig == SIGINT; } static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread, @@ -141,35 +1295,40 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre size_t printed = trace__fprintf_tstamp(trace, tstamp, fp); printed += fprintf_duration(duration, fp); - if (trace->multiple_threads) - printed += fprintf(fp, "%d ", thread->pid); + if (trace->multiple_threads) { + if (trace->show_comm) + printed += fprintf(fp, "%.14s/", thread__comm_str(thread)); + printed += fprintf(fp, "%d ", thread->tid); + } return printed; } -static int trace__process_event(struct machine *machine, union perf_event *event) +static int trace__process_event(struct trace *trace, struct machine *machine, + union perf_event *event, struct perf_sample *sample) { int ret = 0; switch (event->header.type) { case PERF_RECORD_LOST: - color_fprintf(stdout, PERF_COLOR_RED, + color_fprintf(trace->output, PERF_COLOR_RED, "LOST %" PRIu64 " events!\n", event->lost.lost); - ret = machine__process_lost_event(machine, event); + ret = machine__process_lost_event(machine, event, sample); default: - ret = machine__process_event(machine, event); + ret = machine__process_event(machine, event, sample); break; } return ret; } -static int trace__tool_process(struct perf_tool *tool __maybe_unused, +static int trace__tool_process(struct perf_tool *tool, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return trace__process_event(machine, event); + struct trace *trace = container_of(tool, struct trace, tool); + return trace__process_event(trace, machine, event, sample); } static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) @@ -179,16 +1338,17 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) if (err) return err; - machine__init(&trace->host, "", HOST_KERNEL_ID); - machine__create_kernel_maps(&trace->host); + trace->host = machine__new_host(); + if (trace->host == NULL) + return -ENOMEM; if (perf_target__has_task(&trace->opts.target)) { - err = perf_event__synthesize_thread_map(NULL, evlist->threads, + err = perf_event__synthesize_thread_map(&trace->tool, evlist->threads, trace__tool_process, - &trace->host); + trace->host); } else { - err = perf_event__synthesize_threads(NULL, trace__tool_process, - &trace->host); + err = perf_event__synthesize_threads(&trace->tool, trace__tool_process, + trace->host); } if (err) @@ -197,11 +1357,34 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist) return err; } +static int syscall__set_arg_fmts(struct syscall *sc) +{ + struct format_field *field; + int idx = 0; + + sc->arg_scnprintf = calloc(sc->tp_format->format.nr_fields - 1, sizeof(void *)); + if (sc->arg_scnprintf == NULL) + return -1; + + if (sc->fmt) + sc->arg_parm = sc->fmt->arg_parm; + + for (field = sc->tp_format->format.fields->next; field; field = field->next) { + if (sc->fmt && sc->fmt->arg_scnprintf[idx]) + sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx]; + else if (field->flags & FIELD_IS_POINTER) + sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex; + ++idx; + } + + return 0; +} + static int trace__read_syscall_info(struct trace *trace, int id) { char tp_name[128]; struct syscall *sc; - const char *name = audit_syscall_to_name(id, trace->audit_machine); + const char *name = audit_syscall_to_name(id, trace->audit.machine); if (name == NULL) return -1; @@ -225,6 +1408,20 @@ static int trace__read_syscall_info(struct trace *trace, int id) sc = trace->syscalls.table + id; sc->name = name; + + if (trace->ev_qualifier) { + bool in = strlist__find(trace->ev_qualifier, name) != NULL; + + if (!(in ^ trace->not_ev_qualifier)) { + sc->filtered = true; + /* + * No need to do read tracepoint information since this will be + * filtered out. + */ + return 0; + } + } + sc->fmt = syscall_fmt__find(sc->name); snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name); @@ -235,24 +1432,59 @@ static int trace__read_syscall_info(struct trace *trace, int id) sc->tp_format = event_format__new("syscalls", tp_name); } - return sc->tp_format != NULL ? 0 : -1; + if (sc->tp_format == NULL) + return -1; + + return syscall__set_arg_fmts(sc); } static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size, - unsigned long *args) + unsigned long *args, struct trace *trace, + struct thread *thread) { - int i = 0; size_t printed = 0; if (sc->tp_format != NULL) { struct format_field *field; + u8 bit = 1; + struct syscall_arg arg = { + .idx = 0, + .mask = 0, + .trace = trace, + .thread = thread, + }; + + for (field = sc->tp_format->format.fields->next; field; + field = field->next, ++arg.idx, bit <<= 1) { + if (arg.mask & bit) + continue; + /* + * Suppress this argument if its value is zero and + * and we don't have a string associated in an + * strarray for it. + */ + if (args[arg.idx] == 0 && + !(sc->arg_scnprintf && + sc->arg_scnprintf[arg.idx] == SCA_STRARRAY && + sc->arg_parm[arg.idx])) + continue; - for (field = sc->tp_format->format.fields->next; field; field = field->next) { printed += scnprintf(bf + printed, size - printed, - "%s%s: %ld", printed ? ", " : "", - field->name, args[i++]); + "%s%s: ", printed ? ", " : "", field->name); + if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) { + arg.val = args[arg.idx]; + if (sc->arg_parm) + arg.parm = sc->arg_parm[arg.idx]; + printed += sc->arg_scnprintf[arg.idx](bf + printed, + size - printed, &arg); + } else { + printed += scnprintf(bf + printed, size - printed, + "%ld", args[arg.idx]); + } } } else { + int i = 0; + while (i < 6) { printed += scnprintf(bf + printed, size - printed, "%sarg%d: %ld", @@ -268,13 +1500,26 @@ typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel, struct perf_sample *sample); static struct syscall *trace__syscall_info(struct trace *trace, - struct perf_evsel *evsel, - struct perf_sample *sample) + struct perf_evsel *evsel, int id) { - int id = perf_evsel__intval(evsel, sample, "id"); if (id < 0) { - printf("Invalid syscall %d id, skipping...\n", id); + + /* + * XXX: Noticed on x86_64, reproduced as far back as 3.0.36, haven't tried + * before that, leaving at a higher verbosity level till that is + * explained. Reproduced with plain ftrace with: + * + * echo 1 > /t/events/raw_syscalls/sys_exit/enable + * grep "NR -1 " /t/trace_pipe + * + * After generating some load on the machine. + */ + if (verbose > 1) { + static u64 n; + fprintf(trace->output, "Invalid syscall %d id, skipping (%s, %" PRIu64 ") ...\n", + id, perf_evsel__name(evsel), ++n); + } return NULL; } @@ -288,32 +1533,64 @@ static struct syscall *trace__syscall_info(struct trace *trace, return &trace->syscalls.table[id]; out_cant_read: - printf("Problems reading syscall %d", id); - if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL) - printf("(%s)", trace->syscalls.table[id].name); - puts(" information"); + if (verbose) { + fprintf(trace->output, "Problems reading syscall %d", id); + if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL) + fprintf(trace->output, "(%s)", trace->syscalls.table[id].name); + fputs(" information\n", trace->output); + } return NULL; } +static void thread__update_stats(struct thread_trace *ttrace, + int id, struct perf_sample *sample) +{ + struct int_node *inode; + struct stats *stats; + u64 duration = 0; + + inode = intlist__findnew(ttrace->syscall_stats, id); + if (inode == NULL) + return; + + stats = inode->priv; + if (stats == NULL) { + stats = malloc(sizeof(struct stats)); + if (stats == NULL) + return; + init_stats(stats); + inode->priv = stats; + } + + if (ttrace->entry_time && sample->time > ttrace->entry_time) + duration = sample->time - ttrace->entry_time; + + update_stats(stats, duration); +} + static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, struct perf_sample *sample) { char *msg; void *args; size_t printed = 0; - struct thread *thread = machine__findnew_thread(&trace->host, sample->tid); - struct syscall *sc = trace__syscall_info(trace, evsel, sample); - struct thread_trace *ttrace = thread__trace(thread); + struct thread *thread; + int id = perf_evsel__sc_tp_uint(evsel, id, sample); + struct syscall *sc = trace__syscall_info(trace, evsel, id); + struct thread_trace *ttrace; - if (ttrace == NULL || sc == NULL) + if (sc == NULL) return -1; - args = perf_evsel__rawptr(evsel, sample, "args"); - if (args == NULL) { - printf("Problems reading syscall arguments\n"); + if (sc->filtered) + return 0; + + thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); + ttrace = thread__trace(thread, trace->output); + if (ttrace == NULL) return -1; - } + args = perf_evsel__sc_tp_ptr(evsel, args, sample); ttrace = thread->priv; if (ttrace->entry_str == NULL) { @@ -326,12 +1603,13 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, msg = ttrace->entry_str; printed += scnprintf(msg + printed, 1024 - printed, "%s(", sc->name); - printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed, args); + printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed, + args, trace, thread); if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) { if (!trace->duration_filter) { - trace__fprintf_entry_head(trace, thread, 1, sample->time, stdout); - printf("%-70s\n", ttrace->entry_str); + trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output); + fprintf(trace->output, "%-70s\n", ttrace->entry_str); } } else ttrace->entry_pending = true; @@ -344,14 +1622,32 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, { int ret; u64 duration = 0; - struct thread *thread = machine__findnew_thread(&trace->host, sample->tid); - struct thread_trace *ttrace = thread__trace(thread); - struct syscall *sc = trace__syscall_info(trace, evsel, sample); + struct thread *thread; + int id = perf_evsel__sc_tp_uint(evsel, id, sample); + struct syscall *sc = trace__syscall_info(trace, evsel, id); + struct thread_trace *ttrace; - if (ttrace == NULL || sc == NULL) + if (sc == NULL) return -1; - ret = perf_evsel__intval(evsel, sample, "ret"); + if (sc->filtered) + return 0; + + thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); + ttrace = thread__trace(thread, trace->output); + if (ttrace == NULL) + return -1; + + if (trace->summary) + thread__update_stats(ttrace, id, sample); + + ret = perf_evsel__sc_tp_uint(evsel, ret, sample); + + if (id == trace->audit.open_id && ret >= 0 && trace->last_vfs_getname) { + trace__set_fd_pathname(thread, ret, trace->last_vfs_getname); + trace->last_vfs_getname = NULL; + ++trace->stats.vfs_getname; + } ttrace = thread->priv; @@ -364,41 +1660,55 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, } else if (trace->duration_filter) goto out; - trace__fprintf_entry_head(trace, thread, duration, sample->time, stdout); + trace__fprintf_entry_head(trace, thread, duration, sample->time, trace->output); if (ttrace->entry_pending) { - printf("%-70s", ttrace->entry_str); + fprintf(trace->output, "%-70s", ttrace->entry_str); } else { - printf(" ... ["); - color_fprintf(stdout, PERF_COLOR_YELLOW, "continued"); - printf("]: %s()", sc->name); + fprintf(trace->output, " ... ["); + color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued"); + fprintf(trace->output, "]: %s()", sc->name); } - if (ret < 0 && sc->fmt && sc->fmt->errmsg) { + if (sc->fmt == NULL) { +signed_print: + fprintf(trace->output, ") = %d", ret); + } else if (ret < 0 && sc->fmt->errmsg) { char bf[256]; const char *emsg = strerror_r(-ret, bf, sizeof(bf)), *e = audit_errno_to_name(-ret); - printf(") = -1 %s %s", e, emsg); - } else if (ret == 0 && sc->fmt && sc->fmt->timeout) - printf(") = 0 Timeout"); + fprintf(trace->output, ") = -1 %s %s", e, emsg); + } else if (ret == 0 && sc->fmt->timeout) + fprintf(trace->output, ") = 0 Timeout"); + else if (sc->fmt->hexret) + fprintf(trace->output, ") = %#x", ret); else - printf(") = %d", ret); + goto signed_print; - putchar('\n'); + fputc('\n', trace->output); out: ttrace->entry_pending = false; return 0; } +static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel, + struct perf_sample *sample) +{ + trace->last_vfs_getname = perf_evsel__rawptr(evsel, sample, "pathname"); + return 0; +} + static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel, struct perf_sample *sample) { u64 runtime = perf_evsel__intval(evsel, sample, "runtime"); double runtime_ms = (double)runtime / NSEC_PER_MSEC; - struct thread *thread = machine__findnew_thread(&trace->host, sample->tid); - struct thread_trace *ttrace = thread__trace(thread); + struct thread *thread = machine__findnew_thread(trace->host, + sample->pid, + sample->tid); + struct thread_trace *ttrace = thread__trace(thread, trace->output); if (ttrace == NULL) goto out_dump; @@ -408,7 +1718,7 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs return 0; out_dump: - printf("%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n", + fprintf(trace->output, "%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n", evsel->name, perf_evsel__strval(evsel, sample, "comm"), (pid_t)perf_evsel__intval(evsel, sample, "pid"), @@ -417,6 +1727,117 @@ out_dump: return 0; } +static bool skip_sample(struct trace *trace, struct perf_sample *sample) +{ + if ((trace->pid_list && intlist__find(trace->pid_list, sample->pid)) || + (trace->tid_list && intlist__find(trace->tid_list, sample->tid))) + return false; + + if (trace->pid_list || trace->tid_list) + return true; + + return false; +} + +static int trace__process_sample(struct perf_tool *tool, + union perf_event *event __maybe_unused, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine __maybe_unused) +{ + struct trace *trace = container_of(tool, struct trace, tool); + int err = 0; + + tracepoint_handler handler = evsel->handler; + + if (skip_sample(trace, sample)) + return 0; + + if (!trace->full_time && trace->base_time == 0) + trace->base_time = sample->time; + + if (handler) + handler(trace, evsel, sample); + + return err; +} + +static bool +perf_session__has_tp(struct perf_session *session, const char *name) +{ + struct perf_evsel *evsel; + + evsel = perf_evlist__find_tracepoint_by_name(session->evlist, name); + + return evsel != NULL; +} + +static int parse_target_str(struct trace *trace) +{ + if (trace->opts.target.pid) { + trace->pid_list = intlist__new(trace->opts.target.pid); + if (trace->pid_list == NULL) { + pr_err("Error parsing process id string\n"); + return -EINVAL; + } + } + + if (trace->opts.target.tid) { + trace->tid_list = intlist__new(trace->opts.target.tid); + if (trace->tid_list == NULL) { + pr_err("Error parsing thread id string\n"); + return -EINVAL; + } + } + + return 0; +} + +static int trace__record(int argc, const char **argv) +{ + unsigned int rec_argc, i, j; + const char **rec_argv; + const char * const record_args[] = { + "record", + "-R", + "-m", "1024", + "-c", "1", + "-e", "raw_syscalls:sys_enter,raw_syscalls:sys_exit", + }; + + rec_argc = ARRAY_SIZE(record_args) + argc; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); + + if (rec_argv == NULL) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(record_args); i++) + rec_argv[i] = record_args[i]; + + for (j = 0; j < (unsigned int)argc; j++, i++) + rec_argv[i] = argv[j]; + + return cmd_record(i, rec_argv, NULL); +} + +static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); + +static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname", + evlist->nr_entries); + if (evsel == NULL) + return; + + if (perf_evsel__field(evsel, "pathname") == NULL) { + perf_evsel__delete(evsel); + return; + } + + evsel->handler = trace__vfs_getname; + perf_evlist__add(evlist, evsel); +} + static int trace__run(struct trace *trace, int argc, const char **argv) { struct perf_evlist *evlist = perf_evlist__new(); @@ -425,33 +1846,32 @@ static int trace__run(struct trace *trace, int argc, const char **argv) unsigned long before; const bool forks = argc > 0; + trace->live = true; + if (evlist == NULL) { - printf("Not enough memory to run!\n"); + fprintf(trace->output, "Not enough memory to run!\n"); goto out; } - if (perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_enter", trace__sys_enter) || - perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_exit", trace__sys_exit)) { - printf("Couldn't read the raw_syscalls tracepoints information!\n"); - goto out_delete_evlist; - } + if (perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit)) + goto out_error_tp; + + perf_evlist__add_vfs_getname(evlist); if (trace->sched && - perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime", - trace__sched_stat_runtime)) { - printf("Couldn't read the sched_stat_runtime tracepoint information!\n"); - goto out_delete_evlist; - } + perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime", + trace__sched_stat_runtime)) + goto out_error_tp; err = perf_evlist__create_maps(evlist, &trace->opts.target); if (err < 0) { - printf("Problems parsing the target to trace, check your options!\n"); + fprintf(trace->output, "Problems parsing the target to trace, check your options!\n"); goto out_delete_evlist; } err = trace__symbols_init(trace, evlist); if (err < 0) { - printf("Problems initializing symbol libraries!\n"); + fprintf(trace->output, "Problems initializing symbol libraries!\n"); goto out_delete_maps; } @@ -464,20 +1884,18 @@ static int trace__run(struct trace *trace, int argc, const char **argv) err = perf_evlist__prepare_workload(evlist, &trace->opts.target, argv, false, false); if (err < 0) { - printf("Couldn't run the workload!\n"); + fprintf(trace->output, "Couldn't run the workload!\n"); goto out_delete_maps; } } err = perf_evlist__open(evlist); - if (err < 0) { - printf("Couldn't create the events: %s\n", strerror(errno)); - goto out_delete_maps; - } + if (err < 0) + goto out_error_open; err = perf_evlist__mmap(evlist, UINT_MAX, false); if (err < 0) { - printf("Couldn't mmap the events: %s\n", strerror(errno)); + fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno)); goto out_close_evlist; } @@ -502,49 +1920,66 @@ again: err = perf_evlist__parse_sample(evlist, event, &sample); if (err) { - printf("Can't parse sample, err = %d, skipping...\n", err); - continue; + fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err); + goto next_event; } - if (trace->base_time == 0) + if (!trace->full_time && trace->base_time == 0) trace->base_time = sample.time; if (type != PERF_RECORD_SAMPLE) { - trace__process_event(&trace->host, event); + trace__process_event(trace, trace->host, event, &sample); continue; } evsel = perf_evlist__id2evsel(evlist, sample.id); if (evsel == NULL) { - printf("Unknown tp ID %" PRIu64 ", skipping...\n", sample.id); - continue; + fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id); + goto next_event; } if (sample.raw_data == NULL) { - printf("%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", + fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", perf_evsel__name(evsel), sample.tid, sample.cpu, sample.raw_size); - continue; + goto next_event; } - handler = evsel->handler.func; + handler = evsel->handler; handler(trace, evsel, &sample); +next_event: + perf_evlist__mmap_consume(evlist, i); + + if (interrupted) + goto out_disable; } } if (trace->nr_events == before) { - if (done) - goto out_unmap_evlist; + int timeout = done ? 100 : -1; - poll(evlist->pollfd, evlist->nr_fds, -1); + if (poll(evlist->pollfd, evlist->nr_fds, timeout) > 0) + goto again; + } else { + goto again; } - if (done) - perf_evlist__disable(evlist); +out_disable: + perf_evlist__disable(evlist); - goto again; + if (!err) { + if (trace->summary) + trace__fprintf_thread_summary(trace, trace->output); + + if (trace->show_tool_stats) { + fprintf(trace->output, "Stats:\n " + " vfs_getname : %" PRIu64 "\n" + " proc_getname: %" PRIu64 "\n", + trace->stats.vfs_getname, + trace->stats.proc_getname); + } + } -out_unmap_evlist: perf_evlist__munmap(evlist); out_close_evlist: perf_evlist__close(evlist); @@ -553,6 +1988,93 @@ out_delete_maps: out_delete_evlist: perf_evlist__delete(evlist); out: + trace->live = false; + return err; +{ + char errbuf[BUFSIZ]; + +out_error_tp: + perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf)); + goto out_error; + +out_error_open: + perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf)); + +out_error: + fprintf(trace->output, "%s\n", errbuf); + goto out_delete_evlist; +} +} + +static int trace__replay(struct trace *trace) +{ + const struct perf_evsel_str_handler handlers[] = { + { "raw_syscalls:sys_enter", trace__sys_enter, }, + { "raw_syscalls:sys_exit", trace__sys_exit, }, + { "probe:vfs_getname", trace__vfs_getname, }, + }; + struct perf_data_file file = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + }; + struct perf_session *session; + int err = -1; + + trace->tool.sample = trace__process_sample; + trace->tool.mmap = perf_event__process_mmap; + trace->tool.mmap2 = perf_event__process_mmap2; + trace->tool.comm = perf_event__process_comm; + trace->tool.exit = perf_event__process_exit; + trace->tool.fork = perf_event__process_fork; + trace->tool.attr = perf_event__process_attr; + trace->tool.tracing_data = perf_event__process_tracing_data; + trace->tool.build_id = perf_event__process_build_id; + + trace->tool.ordered_samples = true; + trace->tool.ordering_requires_timestamps = true; + + /* add tid to output */ + trace->multiple_threads = true; + + if (symbol__init() < 0) + return -1; + + session = perf_session__new(&file, false, &trace->tool); + if (session == NULL) + return -ENOMEM; + + trace->host = &session->machines.host; + + err = perf_session__set_tracepoints_handlers(session, handlers); + if (err) + goto out; + + if (!perf_session__has_tp(session, "raw_syscalls:sys_enter")) { + pr_err("Data file does not have raw_syscalls:sys_enter events\n"); + goto out; + } + + if (!perf_session__has_tp(session, "raw_syscalls:sys_exit")) { + pr_err("Data file does not have raw_syscalls:sys_exit events\n"); + goto out; + } + + err = parse_target_str(trace); + if (err != 0) + goto out; + + setup_pager(); + + err = perf_session__process_events(session, &trace->tool); + if (err) + pr_err("Failed to process events, error %d", err); + + else if (trace->summary) + trace__fprintf_thread_summary(trace, trace->output); + +out: + perf_session__delete(session); + return err; } @@ -560,45 +2082,109 @@ static size_t trace__fprintf_threads_header(FILE *fp) { size_t printed; - printed = fprintf(fp, "\n _____________________________________________________________________\n"); - printed += fprintf(fp," __) Summary of events (__\n\n"); - printed += fprintf(fp," [ task - pid ] [ events ] [ ratio ] [ runtime ]\n"); - printed += fprintf(fp," _____________________________________________________________________\n\n"); + printed = fprintf(fp, "\n _____________________________________________________________________________\n"); + printed += fprintf(fp, " __) Summary of events (__\n\n"); + printed += fprintf(fp, " [ task - pid ] [ events ] [ ratio ] [ runtime ]\n"); + printed += fprintf(fp, " syscall count min max avg stddev\n"); + printed += fprintf(fp, " msec msec msec %%\n"); + printed += fprintf(fp, " _____________________________________________________________________________\n\n"); return printed; } -static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp) +static size_t thread__dump_stats(struct thread_trace *ttrace, + struct trace *trace, FILE *fp) { - size_t printed = trace__fprintf_threads_header(fp); - struct rb_node *nd; + struct stats *stats; + size_t printed = 0; + struct syscall *sc; + struct int_node *inode = intlist__first(ttrace->syscall_stats); + + if (inode == NULL) + return 0; + + printed += fprintf(fp, "\n"); + + /* each int_node is a syscall */ + while (inode) { + stats = inode->priv; + if (stats) { + double min = (double)(stats->min) / NSEC_PER_MSEC; + double max = (double)(stats->max) / NSEC_PER_MSEC; + double avg = avg_stats(stats); + double pct; + u64 n = (u64) stats->n; + + pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0; + avg /= NSEC_PER_MSEC; + + sc = &trace->syscalls.table[inode->i]; + printed += fprintf(fp, "%24s %14s : ", "", sc->name); + printed += fprintf(fp, "%5" PRIu64 " %8.3f %8.3f", + n, min, max); + printed += fprintf(fp, " %8.3f %6.2f\n", avg, pct); + } - for (nd = rb_first(&trace->host.threads); nd; nd = rb_next(nd)) { - struct thread *thread = rb_entry(nd, struct thread, rb_node); - struct thread_trace *ttrace = thread->priv; - const char *color; - double ratio; + inode = intlist__next(inode); + } - if (ttrace == NULL) - continue; + printed += fprintf(fp, "\n\n"); - ratio = (double)ttrace->nr_events / trace->nr_events * 100.0; + return printed; +} - color = PERF_COLOR_NORMAL; - if (ratio > 50.0) - color = PERF_COLOR_RED; - else if (ratio > 25.0) - color = PERF_COLOR_GREEN; - else if (ratio > 5.0) - color = PERF_COLOR_YELLOW; +/* struct used to pass data to per-thread function */ +struct summary_data { + FILE *fp; + struct trace *trace; + size_t printed; +}; - printed += color_fprintf(fp, color, "%20s", thread->comm); - printed += fprintf(fp, " - %-5d :%11lu [", thread->pid, ttrace->nr_events); - printed += color_fprintf(fp, color, "%5.1f%%", ratio); - printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms); - } +static int trace__fprintf_one_thread(struct thread *thread, void *priv) +{ + struct summary_data *data = priv; + FILE *fp = data->fp; + size_t printed = data->printed; + struct trace *trace = data->trace; + struct thread_trace *ttrace = thread->priv; + const char *color; + double ratio; - return printed; + if (ttrace == NULL) + return 0; + + ratio = (double)ttrace->nr_events / trace->nr_events * 100.0; + + color = PERF_COLOR_NORMAL; + if (ratio > 50.0) + color = PERF_COLOR_RED; + else if (ratio > 25.0) + color = PERF_COLOR_GREEN; + else if (ratio > 5.0) + color = PERF_COLOR_YELLOW; + + printed += color_fprintf(fp, color, "%20s", thread__comm_str(thread)); + printed += fprintf(fp, " - %-5d :%11lu [", thread->tid, ttrace->nr_events); + printed += color_fprintf(fp, color, "%5.1f%%", ratio); + printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms); + printed += thread__dump_stats(ttrace, trace, fp); + + data->printed += printed; + + return 0; +} + +static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp) +{ + struct summary_data data = { + .fp = fp, + .trace = trace + }; + data.printed = trace__fprintf_threads_header(fp); + + machine__for_each_thread(trace->host, trace__fprintf_one_thread, &data); + + return data.printed; } static int trace__set_duration(const struct option *opt, const char *str, @@ -610,15 +2196,37 @@ static int trace__set_duration(const struct option *opt, const char *str, return 0; } +static int trace__open_output(struct trace *trace, const char *filename) +{ + struct stat st; + + if (!stat(filename, &st) && st.st_size) { + char oldname[PATH_MAX]; + + scnprintf(oldname, sizeof(oldname), "%s.old", filename); + unlink(oldname); + rename(filename, oldname); + } + + trace->output = fopen(filename, "w"); + + return trace->output == NULL ? -errno : 0; +} + int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) { const char * const trace_usage[] = { "perf trace [<options>] [<command>]", "perf trace [<options>] -- <command> [<options>]", + "perf trace record [<options>] [<command>]", + "perf trace record [<options>] -- <command> [<options>]", NULL }; struct trace trace = { - .audit_machine = audit_detect_machine(), + .audit = { + .machine = audit_detect_machine(), + .open_id = audit_name_to_syscall("open", trace.audit.machine), + }, .syscalls = { . max = -1, }, @@ -632,54 +2240,101 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) .no_delay = true, .mmap_pages = 1024, }, + .output = stdout, + .show_comm = true, }; + const char *output_name = NULL; + const char *ev_qualifier_str = NULL; const struct option trace_options[] = { + OPT_BOOLEAN(0, "comm", &trace.show_comm, + "show the thread COMM next to its id"), + OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"), + OPT_STRING('e', "expr", &ev_qualifier_str, "expr", + "list of events to trace"), + OPT_STRING('o', "output", &output_name, "file", "output file name"), + OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"), OPT_STRING('p', "pid", &trace.opts.target.pid, "pid", "trace events on existing process id"), - OPT_STRING(0, "tid", &trace.opts.target.tid, "tid", + OPT_STRING('t', "tid", &trace.opts.target.tid, "tid", "trace events on existing thread id"), - OPT_BOOLEAN(0, "all-cpus", &trace.opts.target.system_wide, + OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide, "system-wide collection from all CPUs"), - OPT_STRING(0, "cpu", &trace.opts.target.cpu_list, "cpu", + OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu", "list of cpus to monitor"), OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit, "child tasks do not inherit counters"), - OPT_UINTEGER(0, "mmap-pages", &trace.opts.mmap_pages, - "number of mmap data pages"), - OPT_STRING(0, "uid", &trace.opts.target.uid_str, "user", + OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages", + "number of mmap data pages", + perf_evlist__parse_mmap_pages), + OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user", "user to profile"), OPT_CALLBACK(0, "duration", &trace, "float", "show only events with duration > N.M ms", trace__set_duration), OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"), + 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, "summary", &trace.summary, + "Show syscall summary with statistics"), OPT_END() }; int err; char bf[BUFSIZ]; + if ((argc > 1) && (strcmp(argv[1], "record") == 0)) + return trace__record(argc-2, &argv[2]); + argc = parse_options(argc, argv, trace_options, trace_usage, 0); + if (output_name != NULL) { + err = trace__open_output(&trace, output_name); + if (err < 0) { + perror("failed to create output file"); + goto out; + } + } + + if (ev_qualifier_str != NULL) { + const char *s = ev_qualifier_str; + + trace.not_ev_qualifier = *s == '!'; + if (trace.not_ev_qualifier) + ++s; + trace.ev_qualifier = strlist__new(true, s); + if (trace.ev_qualifier == NULL) { + fputs("Not enough memory to parse event qualifier", + trace.output); + err = -ENOMEM; + goto out_close; + } + } + err = perf_target__validate(&trace.opts.target); if (err) { perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf)); - printf("%s", bf); - return err; + fprintf(trace.output, "%s", bf); + goto out_close; } err = perf_target__parse_uid(&trace.opts.target); if (err) { perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf)); - printf("%s", bf); - return err; + fprintf(trace.output, "%s", bf); + goto out_close; } if (!argc && perf_target__none(&trace.opts.target)) trace.opts.target.system_wide = true; - err = trace__run(&trace, argc, argv); - - if (trace.sched && !err) - trace__fprintf_thread_summary(&trace, stdout); + if (input_name) + err = trace__replay(&trace); + else + err = trace__run(&trace, argc, argv); +out_close: + if (output_name != NULL) + fclose(trace.output); +out: return err; } diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index b5d9238cb18..58b2d37ae23 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -23,15 +23,17 @@ ifeq ($(ARCH),x86_64) endif ifeq (${IS_X86_64}, 1) RAW_ARCH := x86_64 - CFLAGS += -DARCH_X86_64 + CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S + LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 + else + LIBUNWIND_LIBS = -lunwind -lunwind-x86 endif NO_PERF_REGS := 0 - LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 endif ifeq ($(NO_PERF_REGS),0) - CFLAGS += -DHAVE_PERF_REGS + CFLAGS += -DHAVE_PERF_REGS_SUPPORT endif ifeq ($(src-perf),) @@ -46,10 +48,11 @@ ifneq ($(obj-perf),) obj-perf := $(abspath $(obj-perf))/ endif +LIB_INCLUDE := $(srctree)/tools/lib/ + # include ARCH specific config -include $(src-perf)/arch/$(ARCH)/Makefile -include $(src-perf)/config/feature-tests.mak include $(src-perf)/config/utilities.mak ifeq ($(call get-executable,$(FLEX)),) @@ -65,10 +68,11 @@ ifneq ($(WERROR),0) CFLAGS += -Werror endif -ifeq ("$(origin DEBUG)", "command line") - PERF_DEBUG = $(DEBUG) +ifndef DEBUG + DEBUG := 0 endif -ifndef PERF_DEBUG + +ifeq ($(DEBUG),0) CFLAGS += -O6 endif @@ -85,22 +89,127 @@ CFLAGS += -Wall CFLAGS += -Wextra CFLAGS += -std=gnu99 -EXTLIBS = -lelf -lpthread -lrt -lm +EXTLIBS = -lelf -lpthread -lrt -lm -ldl -ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y) - CFLAGS += -fstack-protector-all +ifneq ($(OUTPUT),) + OUTPUT_FEATURES = $(OUTPUT)config/feature-checks/ + $(shell mkdir -p $(OUTPUT_FEATURES)) endif -ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wstack-protector,-Wstack-protector),y) - CFLAGS += -Wstack-protector +feature_check = $(eval $(feature_check_code)) +define feature_check_code + feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS="$(LDFLAGS)" LIBUNWIND_LIBS="$(LIBUNWIND_LIBS)" -C config/feature-checks test-$1 >/dev/null 2>/dev/null && echo 1 || echo 0) +endef + +feature_set = $(eval $(feature_set_code)) +define feature_set_code + feature-$(1) := 1 +endef + +# +# Build the feature check binaries in parallel, ignore errors, ignore return value and suppress output: +# + +# +# Note that this is not a complete list of all feature tests, just +# those that are typically built on a fully configured system. +# +# [ Feature tests not mentioned here have to be built explicitly in +# the rule that uses them - an example for that is the 'bionic' +# feature check. ] +# +CORE_FEATURE_TESTS = \ + backtrace \ + dwarf \ + fortify-source \ + glibc \ + gtk2 \ + gtk2-infobar \ + libaudit \ + libbfd \ + libelf \ + libelf-getphdrnum \ + libelf-mmap \ + libnuma \ + libperl \ + libpython \ + libpython-version \ + libslang \ + libunwind \ + on-exit \ + stackprotector \ + stackprotector-all + +# +# So here we detect whether test-all was rebuilt, to be able +# to skip the print-out of the long features list if the file +# existed before and after it was built: +# +ifeq ($(wildcard $(OUTPUT)config/feature-checks/test-all),) + test-all-failed := 1 +else + test-all-failed := 0 +endif + +# +# Special fast-path for the 'all features are available' case: +# +$(call feature_check,all,$(MSG)) + +# +# Just in case the build freshly failed, make sure we print the +# feature matrix: +# +ifeq ($(feature-all), 0) + test-all-failed := 1 +endif + +ifeq ($(test-all-failed),1) + $(info ) + $(info Auto-detecting system features:) endif -ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -Wvolatile-register-var,-Wvolatile-register-var),y) - CFLAGS += -Wvolatile-register-var +ifeq ($(feature-all), 1) + # + # test-all.c passed - just set all the core feature flags to 1: + # + $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_set,$(feat))) +else + $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) -i -j -C config/feature-checks $(CORE_FEATURE_TESTS) >/dev/null 2>&1) + $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_check,$(feat))) endif -ifndef PERF_DEBUG - ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -D_FORTIFY_SOURCE=2,-D_FORTIFY_SOURCE=2),y) +# +# Print the result of the feature test: +# +feature_print = $(eval $(feature_print_code)) $(info $(MSG)) + +define feature_print_code + ifeq ($(feature-$(1)), 1) + MSG = $(shell printf '...%30s: [ \033[32mon\033[m ]' $(1)) + else + MSG = $(shell printf '...%30s: [ \033[31mOFF\033[m ]' $(1)) + endif +endef + +# +# Only print out our features if we rebuilt the testcases or if a test failed: +# +ifeq ($(test-all-failed), 1) + $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_print,$(feat))) + $(info ) +endif + +ifeq ($(feature-stackprotector-all), 1) + CFLAGS += -fstack-protector-all +endif + +ifeq ($(feature-stackprotector), 1) + CFLAGS += -Wstack-protector +endif + +ifeq ($(DEBUG),0) + ifeq ($(feature-fortify-source), 1) CFLAGS += -D_FORTIFY_SOURCE=2 endif endif @@ -121,87 +230,79 @@ endif CFLAGS += -I$(src-perf)/util CFLAGS += -I$(src-perf) -CFLAGS += -I$(TRACE_EVENT_DIR) -CFLAGS += -I$(srctree)/tools/lib/ +CFLAGS += -I$(LIB_INCLUDE) CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE ifndef NO_BIONIC -ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS),bionic),y) - BIONIC := 1 - EXTLIBS := $(filter-out -lrt,$(EXTLIBS)) - EXTLIBS := $(filter-out -lpthread,$(EXTLIBS)) + $(call feature_check,bionic) + ifeq ($(feature-bionic), 1) + BIONIC := 1 + EXTLIBS := $(filter-out -lrt,$(EXTLIBS)) + EXTLIBS := $(filter-out -lpthread,$(EXTLIBS)) + endif endif -endif # NO_BIONIC ifdef NO_LIBELF NO_DWARF := 1 NO_DEMANGLE := 1 NO_LIBUNWIND := 1 else -FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF),libelf),y) - FLAGS_GLIBC=$(CFLAGS) $(LDFLAGS) - ifeq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC),glibc),y) - LIBC_SUPPORT := 1 - endif - ifeq ($(BIONIC),1) - LIBC_SUPPORT := 1 - endif - ifeq ($(LIBC_SUPPORT),1) - msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev); + ifeq ($(feature-libelf), 0) + ifeq ($(feature-glibc), 1) + LIBC_SUPPORT := 1 + endif + ifeq ($(BIONIC),1) + LIBC_SUPPORT := 1 + endif + ifeq ($(LIBC_SUPPORT),1) + msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev); - NO_LIBELF := 1 - NO_DWARF := 1 - NO_DEMANGLE := 1 + NO_LIBELF := 1 + NO_DWARF := 1 + NO_DEMANGLE := 1 + else + msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); + endif else - msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); - endif -else - # for linking with debug library, run like: - # make DEBUG=1 LIBDW_DIR=/opt/libdw/ - ifdef LIBDW_DIR - LIBDW_CFLAGS := -I$(LIBDW_DIR)/include - LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib - endif + # for linking with debug library, run like: + # make DEBUG=1 LIBDW_DIR=/opt/libdw/ + ifdef LIBDW_DIR + LIBDW_CFLAGS := -I$(LIBDW_DIR)/include + LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib + endif - FLAGS_DWARF=$(CFLAGS) $(LIBDW_CFLAGS) -ldw -lz -lelf $(LIBDW_LDFLAGS) $(LDFLAGS) $(EXTLIBS) - ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF),libdw),y) - msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); - NO_DWARF := 1 - endif # Dwarf support -endif # SOURCE_LIBELF + ifneq ($(feature-dwarf), 1) + msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); + NO_DWARF := 1 + endif # Dwarf support + endif # libelf support endif # NO_LIBELF ifndef NO_LIBELF -CFLAGS += -DLIBELF_SUPPORT -FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y) - CFLAGS += -DLIBELF_MMAP -endif + CFLAGS += -DHAVE_LIBELF_SUPPORT -# include ARCH specific config --include $(src-perf)/arch/$(ARCH)/Makefile + ifeq ($(feature-libelf-mmap), 1) + CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT + endif -ifndef NO_DWARF -ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined) - msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled); - NO_DWARF := 1 -else - CFLAGS += -DDWARF_SUPPORT $(LIBDW_CFLAGS) - LDFLAGS += $(LIBDW_LDFLAGS) - EXTLIBS += -lelf -ldw -endif # PERF_HAVE_DWARF_REGS -endif # NO_DWARF + ifeq ($(feature-libelf-getphdrnum), 1) + CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT + endif -endif # NO_LIBELF + # include ARCH specific config + -include $(src-perf)/arch/$(ARCH)/Makefile -ifndef NO_LIBELF -CFLAGS += -DLIBELF_SUPPORT -FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y) - CFLAGS += -DLIBELF_MMAP -endif # try-cc + ifndef NO_DWARF + ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined) + msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled); + NO_DWARF := 1 + else + CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS) + LDFLAGS += $(LIBDW_LDFLAGS) + EXTLIBS += -lelf -ldw + endif # PERF_HAVE_DWARF_REGS + endif # NO_DWARF endif # NO_LIBELF # There's only x86 (both 32 and 64) support for CFI unwind so far @@ -210,34 +311,35 @@ ifneq ($(ARCH),x86) endif ifndef NO_LIBUNWIND -# for linking with debug library, run like: -# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/ -ifdef LIBUNWIND_DIR - LIBUNWIND_CFLAGS := -I$(LIBUNWIND_DIR)/include - LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib -endif + # + # For linking with debug library, run like: + # + # make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/ + # + ifdef LIBUNWIND_DIR + LIBUNWIND_CFLAGS := -I$(LIBUNWIND_DIR)/include + LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib + endif -FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(CFLAGS) $(LIBUNWIND_LDFLAGS) $(LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS) -ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND),libunwind),y) - msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99); - NO_LIBUNWIND := 1 -endif # Libunwind support -endif # NO_LIBUNWIND + ifneq ($(feature-libunwind), 1) + msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99); + NO_LIBUNWIND := 1 + endif +endif ifndef NO_LIBUNWIND - CFLAGS += -DLIBUNWIND_SUPPORT + CFLAGS += -DHAVE_LIBUNWIND_SUPPORT EXTLIBS += $(LIBUNWIND_LIBS) CFLAGS += $(LIBUNWIND_CFLAGS) LDFLAGS += $(LIBUNWIND_LDFLAGS) -endif # NO_LIBUNWIND +endif ifndef NO_LIBAUDIT - FLAGS_LIBAUDIT = $(CFLAGS) $(LDFLAGS) -laudit - ifneq ($(call try-cc,$(SOURCE_LIBAUDIT),$(FLAGS_LIBAUDIT),libaudit),y) + ifneq ($(feature-libaudit), 1) msg := $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev); NO_LIBAUDIT := 1 else - CFLAGS += -DLIBAUDIT_SUPPORT + CFLAGS += -DHAVE_LIBAUDIT_SUPPORT EXTLIBS += -laudit endif endif @@ -247,30 +349,30 @@ ifdef NO_NEWT endif ifndef NO_SLANG - FLAGS_SLANG=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -I/usr/include/slang -lslang - ifneq ($(call try-cc,$(SOURCE_SLANG),$(FLAGS_SLANG),libslang),y) + ifneq ($(feature-libslang), 1) msg := $(warning slang not found, disables TUI support. Please install slang-devel or libslang-dev); NO_SLANG := 1 else # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h CFLAGS += -I/usr/include/slang - CFLAGS += -DSLANG_SUPPORT + CFLAGS += -DHAVE_SLANG_SUPPORT EXTLIBS += -lslang endif endif ifndef NO_GTK2 FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) - ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2),gtk2),y) + ifneq ($(feature-gtk2), 1) msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev); NO_GTK2 := 1 else - ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2),-DHAVE_GTK_INFO_BAR),y) - CFLAGS += -DHAVE_GTK_INFO_BAR + ifeq ($(feature-gtk2-infobar), 1) + GTK_CFLAGS := -DHAVE_GTK_INFO_BAR_SUPPORT endif - CFLAGS += -DGTK2_SUPPORT - CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null) - EXTLIBS += $(shell pkg-config --libs gtk+-2.0 2>/dev/null) + CFLAGS += -DHAVE_GTK2_SUPPORT + GTK_CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null) + GTK_LIBS := $(shell pkg-config --libs gtk+-2.0 2>/dev/null) + EXTLIBS += -ldl endif endif @@ -286,7 +388,7 @@ else PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) - ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED),perl),y) + ifneq ($(feature-libperl), 1) CFLAGS += -DNO_LIBPERL NO_LIBPERL := 1 else @@ -295,6 +397,13 @@ else endif endif +$(call feature_check,timerfd) +ifeq ($(feature-timerfd), 1) + CFLAGS += -DHAVE_TIMERFD_SUPPORT +else + msg := $(warning No timerfd support. Disables 'perf kvm stat live'); +endif + disable-python = $(eval $(disable-python_code)) define disable-python_code CFLAGS += -DNO_LIBPYTHON @@ -331,11 +440,11 @@ else PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) - ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED),python),y) + ifneq ($(feature-libpython), 1) $(call disable-python,Python.h (for Python 2.x)) else - ifneq ($(call try-cc,$(SOURCE_PYTHON_VERSION),$(FLAGS_PYTHON_EMBED),python version),y) + 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) @@ -358,33 +467,30 @@ else endif endif +ifeq ($(feature-libbfd), 1) + EXTLIBS += -lbfd +endif + ifdef NO_DEMANGLE CFLAGS += -DNO_DEMANGLE else - ifdef HAVE_CPLUS_DEMANGLE + ifdef HAVE_CPLUS_DEMANGLE_SUPPORT EXTLIBS += -liberty - CFLAGS += -DHAVE_CPLUS_DEMANGLE + CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT else - FLAGS_BFD=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -DPACKAGE='perf' -lbfd - has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD),libbfd) - ifeq ($(has_bfd),y) - EXTLIBS += -lbfd - else - FLAGS_BFD_IBERTY=$(FLAGS_BFD) -liberty - has_bfd_iberty := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY),liberty) - ifeq ($(has_bfd_iberty),y) + ifneq ($(feature-libbfd), 1) + $(call feature_check,liberty) + ifeq ($(feature-liberty), 1) EXTLIBS += -lbfd -liberty else - FLAGS_BFD_IBERTY_Z=$(FLAGS_BFD_IBERTY) -lz - has_bfd_iberty_z := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY_Z),libz) - ifeq ($(has_bfd_iberty_z),y) + $(call feature_check,liberty-z) + ifeq ($(feature-liberty-z), 1) EXTLIBS += -lbfd -liberty -lz else - FLAGS_CPLUS_DEMANGLE=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) -liberty - has_cplus_demangle := $(call try-cc,$(SOURCE_CPLUS_DEMANGLE),$(FLAGS_CPLUS_DEMANGLE),demangle) - ifeq ($(has_cplus_demangle),y) + $(call feature_check,cplus-demangle) + ifeq ($(feature-cplus-demangle), 1) EXTLIBS += -liberty - CFLAGS += -DHAVE_CPLUS_DEMANGLE + CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT else msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling) CFLAGS += -DNO_DEMANGLE @@ -395,31 +501,28 @@ else endif endif -ifndef NO_STRLCPY - ifeq ($(call try-cc,$(SOURCE_STRLCPY),,-DHAVE_STRLCPY),y) - CFLAGS += -DHAVE_STRLCPY - endif +ifneq ($(filter -lbfd,$(EXTLIBS)),) + CFLAGS += -DHAVE_LIBBFD_SUPPORT endif ifndef NO_ON_EXIT - ifeq ($(call try-cc,$(SOURCE_ON_EXIT),,-DHAVE_ON_EXIT),y) - CFLAGS += -DHAVE_ON_EXIT + ifeq ($(feature-on-exit), 1) + CFLAGS += -DHAVE_ON_EXIT_SUPPORT endif endif ifndef NO_BACKTRACE - ifeq ($(call try-cc,$(SOURCE_BACKTRACE),,-DBACKTRACE_SUPPORT),y) - CFLAGS += -DBACKTRACE_SUPPORT + ifeq ($(feature-backtrace), 1) + CFLAGS += -DHAVE_BACKTRACE_SUPPORT endif endif ifndef NO_LIBNUMA - FLAGS_LIBNUMA = $(CFLAGS) $(LDFLAGS) -lnuma - ifneq ($(call try-cc,$(SOURCE_LIBNUMA),$(FLAGS_LIBNUMA),libnuma),y) + ifeq ($(feature-libnuma), 0) msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev); NO_LIBNUMA := 1 else - CFLAGS += -DLIBNUMA_SUPPORT + CFLAGS += -DHAVE_LIBNUMA_SUPPORT EXTLIBS += -lnuma endif endif @@ -455,7 +558,12 @@ else sysconfdir = $(prefix)/etc ETC_PERFCONFIG = etc/perfconfig endif +ifeq ($(IS_X86_64),1) +lib = lib64 +else lib = lib +endif +libdir = $(prefix)/$(lib) # Shell quote (do not use $(call) to accommodate ancient setups); ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG)) @@ -468,6 +576,7 @@ template_dir_SQ = $(subst ','\'',$(template_dir)) htmldir_SQ = $(subst ','\'',$(htmldir)) prefix_SQ = $(subst ','\'',$(prefix)) sysconfdir_SQ = $(subst ','\'',$(sysconfdir)) +libdir_SQ = $(subst ','\'',$(libdir)) ifneq ($(filter /%,$(firstword $(perfexecdir))),) perfexec_instdir = $(perfexecdir) diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile new file mode 100644 index 00000000000..c803f17fb98 --- /dev/null +++ b/tools/perf/config/feature-checks/Makefile @@ -0,0 +1,148 @@ + +FILES= \ + test-all \ + test-backtrace \ + test-bionic \ + test-dwarf \ + test-fortify-source \ + test-glibc \ + test-gtk2 \ + test-gtk2-infobar \ + test-hello \ + test-libaudit \ + test-libbfd \ + test-liberty \ + test-liberty-z \ + test-cplus-demangle \ + test-libelf \ + test-libelf-getphdrnum \ + test-libelf-mmap \ + test-libnuma \ + test-libperl \ + test-libpython \ + test-libpython-version \ + test-libslang \ + test-libunwind \ + test-on-exit \ + test-stackprotector-all \ + test-stackprotector \ + test-timerfd + +CC := $(CC) -MD + +all: $(FILES) + +BUILD = $(CC) $(CFLAGS) $(LDFLAGS) -o $(OUTPUT)$@ $@.c + +############################### + +test-all: + $(BUILD) -Werror -fstack-protector -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma $(LIBUNWIND_LIBS) -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl + +test-hello: + $(BUILD) + +test-stackprotector-all: + $(BUILD) -Werror -fstack-protector-all + +test-stackprotector: + $(BUILD) -Werror -fstack-protector -Wstack-protector + +test-fortify-source: + $(BUILD) -O2 -Werror -D_FORTIFY_SOURCE=2 + +test-bionic: + $(BUILD) + +test-libelf: + $(BUILD) -lelf + +test-glibc: + $(BUILD) + +test-dwarf: + $(BUILD) -ldw + +test-libelf-mmap: + $(BUILD) -lelf + +test-libelf-getphdrnum: + $(BUILD) -lelf + +test-libnuma: + $(BUILD) -lnuma + +test-libunwind: + $(BUILD) $(LIBUNWIND_LIBS) -lelf + +test-libaudit: + $(BUILD) -laudit + +test-libslang: + $(BUILD) -I/usr/include/slang -lslang + +test-gtk2: + $(BUILD) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) + +test-gtk2-infobar: + $(BUILD) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) + +grep-libs = $(filter -l%,$(1)) +strip-libs = $(filter-out -l%,$(1)) + +PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null) +PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) +PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) +PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` +FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) + +test-libperl: + $(BUILD) $(FLAGS_PERL_EMBED) + +override PYTHON := python +override PYTHON_CONFIG := python-config + +escape-for-shell-sq = $(subst ','\'',$(1)) +shell-sq = '$(escape-for-shell-sq)' + +PYTHON_CONFIG_SQ = $(call shell-sq,$(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)) +PYTHON_EMBED_CCOPTS = $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) +FLAGS_PYTHON_EMBED = $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) + +test-libpython: + $(BUILD) $(FLAGS_PYTHON_EMBED) + +test-libpython-version: + $(BUILD) $(FLAGS_PYTHON_EMBED) + +test-libbfd: + $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl + +test-liberty: + $(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty + +test-liberty-z: + $(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty -lz + +test-cplus-demangle: + $(BUILD) -liberty + +test-on-exit: + $(BUILD) + +test-backtrace: + $(BUILD) + +test-timerfd: + $(BUILD) + +-include *.d + +############################### + +clean: + rm -f $(FILES) *.d diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c new file mode 100644 index 00000000000..59e7a705e14 --- /dev/null +++ b/tools/perf/config/feature-checks/test-all.c @@ -0,0 +1,111 @@ +/* + * test-all.c: Try to build all the main testcases at once. + * + * A well-configured system will have all the prereqs installed, so we can speed + * up auto-detection on such systems. + */ + +/* + * Quirk: Python and Perl headers cannot be in arbitrary places, so keep + * these 3 testcases at the top: + */ +#define main main_test_libpython +# include "test-libpython.c" +#undef main + +#define main main_test_libpython_version +# include "test-libpython-version.c" +#undef main + +#define main main_test_libperl +# include "test-libperl.c" +#undef main + +#define main main_test_hello +# include "test-hello.c" +#undef main + +#define main main_test_libelf +# include "test-libelf.c" +#undef main + +#define main main_test_libelf_mmap +# include "test-libelf-mmap.c" +#undef main + +#define main main_test_glibc +# include "test-glibc.c" +#undef main + +#define main main_test_dwarf +# include "test-dwarf.c" +#undef main + +#define main main_test_libelf_getphdrnum +# include "test-libelf-getphdrnum.c" +#undef main + +#define main main_test_libunwind +# include "test-libunwind.c" +#undef main + +#define main main_test_libaudit +# include "test-libaudit.c" +#undef main + +#define main main_test_libslang +# include "test-libslang.c" +#undef main + +#define main main_test_gtk2 +# include "test-gtk2.c" +#undef main + +#define main main_test_gtk2_infobar +# include "test-gtk2-infobar.c" +#undef main + +#define main main_test_libbfd +# include "test-libbfd.c" +#undef main + +#define main main_test_on_exit +# include "test-on-exit.c" +#undef main + +#define main main_test_backtrace +# include "test-backtrace.c" +#undef main + +#define main main_test_libnuma +# include "test-libnuma.c" +#undef main + +#define main main_test_timerfd +# include "test-timerfd.c" +#undef main + +int main(int argc, char *argv[]) +{ + main_test_libpython(); + main_test_libpython_version(); + main_test_libperl(); + main_test_hello(); + main_test_libelf(); + main_test_libelf_mmap(); + main_test_glibc(); + main_test_dwarf(); + main_test_libelf_getphdrnum(); + main_test_libunwind(); + main_test_libaudit(); + main_test_libslang(); + main_test_gtk2(argc, argv); + main_test_gtk2_infobar(argc, argv); + main_test_libbfd(); + main_test_on_exit(); + main_test_backtrace(); + main_test_libnuma(); + main_test_timerfd(); + + return 0; +} diff --git a/tools/perf/config/feature-checks/test-backtrace.c b/tools/perf/config/feature-checks/test-backtrace.c new file mode 100644 index 00000000000..7124aa1dc8f --- /dev/null +++ b/tools/perf/config/feature-checks/test-backtrace.c @@ -0,0 +1,13 @@ +#include <execinfo.h> +#include <stdio.h> + +int main(void) +{ + void *backtrace_fns[10]; + size_t entries; + + entries = backtrace(backtrace_fns, 10); + backtrace_symbols_fd(backtrace_fns, entries, 1); + + return 0; +} diff --git a/tools/perf/config/feature-checks/test-bionic.c b/tools/perf/config/feature-checks/test-bionic.c new file mode 100644 index 00000000000..eac24e9513e --- /dev/null +++ b/tools/perf/config/feature-checks/test-bionic.c @@ -0,0 +1,6 @@ +#include <android/api-level.h> + +int main(void) +{ + return __ANDROID_API__; +} diff --git a/tools/perf/config/feature-checks/test-cplus-demangle.c b/tools/perf/config/feature-checks/test-cplus-demangle.c new file mode 100644 index 00000000000..610c686e000 --- /dev/null +++ b/tools/perf/config/feature-checks/test-cplus-demangle.c @@ -0,0 +1,14 @@ +extern int printf(const char *format, ...); +extern char *cplus_demangle(const char *, int); + +int main(void) +{ + char symbol[4096] = "FieldName__9ClassNameFd"; + char *tmp; + + tmp = cplus_demangle(symbol, 0); + + printf("demangled symbol: {%s}\n", tmp); + + return 0; +} diff --git a/tools/perf/config/feature-checks/test-dwarf.c b/tools/perf/config/feature-checks/test-dwarf.c new file mode 100644 index 00000000000..3fc1801ce4a --- /dev/null +++ b/tools/perf/config/feature-checks/test-dwarf.c @@ -0,0 +1,10 @@ +#include <dwarf.h> +#include <elfutils/libdw.h> +#include <elfutils/version.h> + +int main(void) +{ + Dwarf *dbg = dwarf_begin(0, DWARF_C_READ); + + return (long)dbg; +} diff --git a/tools/perf/config/feature-checks/test-fortify-source.c b/tools/perf/config/feature-checks/test-fortify-source.c new file mode 100644 index 00000000000..c9f398d8786 --- /dev/null +++ b/tools/perf/config/feature-checks/test-fortify-source.c @@ -0,0 +1,6 @@ +#include <stdio.h> + +int main(void) +{ + return puts("hi"); +} diff --git a/tools/perf/config/feature-checks/test-glibc.c b/tools/perf/config/feature-checks/test-glibc.c new file mode 100644 index 00000000000..b0820345cd9 --- /dev/null +++ b/tools/perf/config/feature-checks/test-glibc.c @@ -0,0 +1,8 @@ +#include <gnu/libc-version.h> + +int main(void) +{ + const char *version = gnu_get_libc_version(); + + return (long)version; +} diff --git a/tools/perf/config/feature-checks/test-gtk2-infobar.c b/tools/perf/config/feature-checks/test-gtk2-infobar.c new file mode 100644 index 00000000000..397b4646d06 --- /dev/null +++ b/tools/perf/config/feature-checks/test-gtk2-infobar.c @@ -0,0 +1,11 @@ +#pragma GCC diagnostic ignored "-Wstrict-prototypes" +#include <gtk/gtk.h> +#pragma GCC diagnostic error "-Wstrict-prototypes" + +int main(int argc, char *argv[]) +{ + gtk_init(&argc, &argv); + gtk_info_bar_new(); + + return 0; +} diff --git a/tools/perf/config/feature-checks/test-gtk2.c b/tools/perf/config/feature-checks/test-gtk2.c new file mode 100644 index 00000000000..6bd80e50943 --- /dev/null +++ b/tools/perf/config/feature-checks/test-gtk2.c @@ -0,0 +1,10 @@ +#pragma GCC diagnostic ignored "-Wstrict-prototypes" +#include <gtk/gtk.h> +#pragma GCC diagnostic error "-Wstrict-prototypes" + +int main(int argc, char *argv[]) +{ + gtk_init(&argc, &argv); + + return 0; +} diff --git a/tools/perf/config/feature-checks/test-hello.c b/tools/perf/config/feature-checks/test-hello.c new file mode 100644 index 00000000000..c9f398d8786 --- /dev/null +++ b/tools/perf/config/feature-checks/test-hello.c @@ -0,0 +1,6 @@ +#include <stdio.h> + +int main(void) +{ + return puts("hi"); +} diff --git a/tools/perf/config/feature-checks/test-libaudit.c b/tools/perf/config/feature-checks/test-libaudit.c new file mode 100644 index 00000000000..afc019f0864 --- /dev/null +++ b/tools/perf/config/feature-checks/test-libaudit.c @@ -0,0 +1,10 @@ +#include <libaudit.h> + +extern int printf(const char *format, ...); + +int main(void) +{ + printf("error message: %s\n", audit_errno_to_name(0)); + + return audit_open(); +} diff --git a/tools/perf/config/feature-checks/test-libbfd.c b/tools/perf/config/feature-checks/test-libbfd.c new file mode 100644 index 00000000000..24059907e99 --- /dev/null +++ b/tools/perf/config/feature-checks/test-libbfd.c @@ -0,0 +1,15 @@ +#include <bfd.h> + +extern int printf(const char *format, ...); + +int main(void) +{ + char symbol[4096] = "FieldName__9ClassNameFd"; + char *tmp; + + tmp = bfd_demangle(0, symbol, 0); + + printf("demangled symbol: {%s}\n", tmp); + + return 0; +} diff --git a/tools/perf/config/feature-checks/test-libelf-getphdrnum.c b/tools/perf/config/feature-checks/test-libelf-getphdrnum.c new file mode 100644 index 00000000000..d710459306c --- /dev/null +++ b/tools/perf/config/feature-checks/test-libelf-getphdrnum.c @@ -0,0 +1,8 @@ +#include <libelf.h> + +int main(void) +{ + size_t dst; + + return elf_getphdrnum(0, &dst); +} diff --git a/tools/perf/config/feature-checks/test-libelf-mmap.c b/tools/perf/config/feature-checks/test-libelf-mmap.c new file mode 100644 index 00000000000..564427d7ef1 --- /dev/null +++ b/tools/perf/config/feature-checks/test-libelf-mmap.c @@ -0,0 +1,8 @@ +#include <libelf.h> + +int main(void) +{ + Elf *elf = elf_begin(0, ELF_C_READ_MMAP, 0); + + return (long)elf; +} diff --git a/tools/perf/config/feature-checks/test-libelf.c b/tools/perf/config/feature-checks/test-libelf.c new file mode 100644 index 00000000000..08db322d895 --- /dev/null +++ b/tools/perf/config/feature-checks/test-libelf.c @@ -0,0 +1,8 @@ +#include <libelf.h> + +int main(void) +{ + Elf *elf = elf_begin(0, ELF_C_READ, 0); + + return (long)elf; +} diff --git a/tools/perf/config/feature-checks/test-libnuma.c b/tools/perf/config/feature-checks/test-libnuma.c new file mode 100644 index 00000000000..4763d9cd587 --- /dev/null +++ b/tools/perf/config/feature-checks/test-libnuma.c @@ -0,0 +1,9 @@ +#include <numa.h> +#include <numaif.h> + +int main(void) +{ + numa_available(); + + return 0; +} diff --git a/tools/perf/config/feature-checks/test-libperl.c b/tools/perf/config/feature-checks/test-libperl.c new file mode 100644 index 00000000000..8871f6a0fdb --- /dev/null +++ b/tools/perf/config/feature-checks/test-libperl.c @@ -0,0 +1,9 @@ +#include <EXTERN.h> +#include <perl.h> + +int main(void) +{ + perl_alloc(); + + return 0; +} diff --git a/tools/perf/config/feature-checks/test-libpython-version.c b/tools/perf/config/feature-checks/test-libpython-version.c new file mode 100644 index 00000000000..facea122d81 --- /dev/null +++ b/tools/perf/config/feature-checks/test-libpython-version.c @@ -0,0 +1,10 @@ +#include <Python.h> + +#if PY_VERSION_HEX >= 0x03000000 + #error +#endif + +int main(void) +{ + return 0; +} diff --git a/tools/perf/config/feature-checks/test-libpython.c b/tools/perf/config/feature-checks/test-libpython.c new file mode 100644 index 00000000000..b24b28ad632 --- /dev/null +++ b/tools/perf/config/feature-checks/test-libpython.c @@ -0,0 +1,8 @@ +#include <Python.h> + +int main(void) +{ + Py_Initialize(); + + return 0; +} diff --git a/tools/perf/config/feature-checks/test-libslang.c b/tools/perf/config/feature-checks/test-libslang.c new file mode 100644 index 00000000000..22ff22ed94d --- /dev/null +++ b/tools/perf/config/feature-checks/test-libslang.c @@ -0,0 +1,6 @@ +#include <slang.h> + +int main(void) +{ + return SLsmg_init_smg(); +} diff --git a/tools/perf/config/feature-checks/test-libunwind.c b/tools/perf/config/feature-checks/test-libunwind.c new file mode 100644 index 00000000000..43b9369bcab --- /dev/null +++ b/tools/perf/config/feature-checks/test-libunwind.c @@ -0,0 +1,27 @@ +#include <libunwind.h> +#include <stdlib.h> + +extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, + unw_word_t ip, + unw_dyn_info_t *di, + unw_proc_info_t *pi, + int need_unwind_info, void *arg); + + +#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) + +static unw_accessors_t accessors; + +int main(void) +{ + unw_addr_space_t addr_space; + + addr_space = unw_create_addr_space(&accessors, 0); + if (addr_space) + return 0; + + unw_init_remote(NULL, addr_space, NULL); + dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL); + + return 0; +} diff --git a/tools/perf/config/feature-checks/test-on-exit.c b/tools/perf/config/feature-checks/test-on-exit.c new file mode 100644 index 00000000000..8e88b16e6de --- /dev/null +++ b/tools/perf/config/feature-checks/test-on-exit.c @@ -0,0 +1,16 @@ +#include <stdio.h> +#include <stdlib.h> + +static void exit_fn(int status, void *__data) +{ + printf("exit status: %d, data: %d\n", status, *(int *)__data); +} + +static int data = 123; + +int main(void) +{ + on_exit(exit_fn, &data); + + return 321; +} diff --git a/tools/perf/config/feature-checks/test-stackprotector-all.c b/tools/perf/config/feature-checks/test-stackprotector-all.c new file mode 100644 index 00000000000..c9f398d8786 --- /dev/null +++ b/tools/perf/config/feature-checks/test-stackprotector-all.c @@ -0,0 +1,6 @@ +#include <stdio.h> + +int main(void) +{ + return puts("hi"); +} diff --git a/tools/perf/config/feature-checks/test-stackprotector.c b/tools/perf/config/feature-checks/test-stackprotector.c new file mode 100644 index 00000000000..c9f398d8786 --- /dev/null +++ b/tools/perf/config/feature-checks/test-stackprotector.c @@ -0,0 +1,6 @@ +#include <stdio.h> + +int main(void) +{ + return puts("hi"); +} diff --git a/tools/perf/config/feature-checks/test-timerfd.c b/tools/perf/config/feature-checks/test-timerfd.c new file mode 100644 index 00000000000..8c5c083b4d3 --- /dev/null +++ b/tools/perf/config/feature-checks/test-timerfd.c @@ -0,0 +1,18 @@ +/* + * test for timerfd functions used by perf-kvm-stat-live + */ +#include <sys/timerfd.h> + +int main(void) +{ + struct itimerspec new_value; + + int fd = timerfd_create(CLOCK_MONOTONIC, TFD_NONBLOCK); + if (fd < 0) + return 1; + + if (timerfd_settime(fd, 0, &new_value, NULL) != 0) + return 1; + + return 0; +} diff --git a/tools/perf/config/feature-checks/test-volatile-register-var.c b/tools/perf/config/feature-checks/test-volatile-register-var.c new file mode 100644 index 00000000000..c9f398d8786 --- /dev/null +++ b/tools/perf/config/feature-checks/test-volatile-register-var.c @@ -0,0 +1,6 @@ +#include <stdio.h> + +int main(void) +{ + return puts("hi"); +} diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak deleted file mode 100644 index 708fb8e9822..00000000000 --- a/tools/perf/config/feature-tests.mak +++ /dev/null @@ -1,236 +0,0 @@ -define SOURCE_HELLO -#include <stdio.h> -int main(void) -{ - return puts(\"hi\"); -} -endef - -ifndef NO_DWARF -define SOURCE_DWARF -#include <dwarf.h> -#include <elfutils/libdw.h> -#include <elfutils/version.h> -#ifndef _ELFUTILS_PREREQ -#error -#endif - -int main(void) -{ - Dwarf *dbg = dwarf_begin(0, DWARF_C_READ); - return (long)dbg; -} -endef -endif - -define SOURCE_LIBELF -#include <libelf.h> - -int main(void) -{ - Elf *elf = elf_begin(0, ELF_C_READ, 0); - return (long)elf; -} -endef - -define SOURCE_GLIBC -#include <gnu/libc-version.h> - -int main(void) -{ - const char *version = gnu_get_libc_version(); - return (long)version; -} -endef - -define SOURCE_BIONIC -#include <android/api-level.h> - -int main(void) -{ - return __ANDROID_API__; -} -endef - -define SOURCE_ELF_MMAP -#include <libelf.h> -int main(void) -{ - Elf *elf = elf_begin(0, ELF_C_READ_MMAP, 0); - return (long)elf; -} -endef - -ifndef NO_SLANG -define SOURCE_SLANG -#include <slang.h> - -int main(void) -{ - return SLsmg_init_smg(); -} -endef -endif - -ifndef NO_GTK2 -define SOURCE_GTK2 -#pragma GCC diagnostic ignored \"-Wstrict-prototypes\" -#include <gtk/gtk.h> -#pragma GCC diagnostic error \"-Wstrict-prototypes\" - -int main(int argc, char *argv[]) -{ - gtk_init(&argc, &argv); - - return 0; -} -endef - -define SOURCE_GTK2_INFOBAR -#pragma GCC diagnostic ignored \"-Wstrict-prototypes\" -#include <gtk/gtk.h> -#pragma GCC diagnostic error \"-Wstrict-prototypes\" - -int main(void) -{ - gtk_info_bar_new(); - - return 0; -} -endef -endif - -ifndef NO_LIBPERL -define SOURCE_PERL_EMBED -#include <EXTERN.h> -#include <perl.h> - -int main(void) -{ -perl_alloc(); -return 0; -} -endef -endif - -ifndef NO_LIBPYTHON -define SOURCE_PYTHON_VERSION -#include <Python.h> -#if PY_VERSION_HEX >= 0x03000000 - #error -#endif -int main(void) -{ - return 0; -} -endef -define SOURCE_PYTHON_EMBED -#include <Python.h> -int main(void) -{ - Py_Initialize(); - return 0; -} -endef -endif - -define SOURCE_BFD -#include <bfd.h> - -int main(void) -{ - bfd_demangle(0, 0, 0); - return 0; -} -endef - -define SOURCE_CPLUS_DEMANGLE -extern char *cplus_demangle(const char *, int); - -int main(void) -{ - cplus_demangle(0, 0); - return 0; -} -endef - -define SOURCE_STRLCPY -#include <stdlib.h> -extern size_t strlcpy(char *dest, const char *src, size_t size); - -int main(void) -{ - strlcpy(NULL, NULL, 0); - return 0; -} -endef - -ifndef NO_LIBUNWIND -define SOURCE_LIBUNWIND -#include <libunwind.h> -#include <stdlib.h> - -extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, - unw_word_t ip, - unw_dyn_info_t *di, - unw_proc_info_t *pi, - int need_unwind_info, void *arg); - - -#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) - -int main(void) -{ - unw_addr_space_t addr_space; - addr_space = unw_create_addr_space(NULL, 0); - unw_init_remote(NULL, addr_space, NULL); - dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL); - return 0; -} -endef -endif - -ifndef NO_BACKTRACE -define SOURCE_BACKTRACE -#include <execinfo.h> -#include <stdio.h> - -int main(void) -{ - backtrace(NULL, 0); - backtrace_symbols(NULL, 0); - return 0; -} -endef -endif - -ifndef NO_LIBAUDIT -define SOURCE_LIBAUDIT -#include <libaudit.h> - -int main(void) -{ - return audit_open(); -} -endef -endif - -define SOURCE_ON_EXIT -#include <stdio.h> - -int main(void) -{ - return on_exit(NULL, NULL); -} -endef - -define SOURCE_LIBNUMA -#include <numa.h> -#include <numaif.h> - -int main(void) -{ - numa_available(); - return 0; -} -endef diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak index 94d2d4f9c35..f168debc5be 100644 --- a/tools/perf/config/utilities.mak +++ b/tools/perf/config/utilities.mak @@ -179,16 +179,9 @@ _ge_attempt = $(if $(get-executable),$(get-executable),$(_gea_warn)$(call _gea_e _gea_warn = $(warning The path '$(1)' is not executable.) _gea_err = $(if $(1),$(error Please set '$(1)' appropriately)) -# try-cc -# Usage: option = $(call try-cc, source-to-build, cc-options, msg) -ifneq ($(V),1) -TRY_CC_OUTPUT= > /dev/null 2>&1 +ifneq ($(findstring $(MAKEFLAGS),s),s) + ifneq ($(V),1) + QUIET_CLEAN = @printf ' CLEAN %s\n' $1; + QUIET_INSTALL = @printf ' INSTALL %s\n' $1; + endif endif -TRY_CC_MSG=echo " CHK $(3)" 1>&2; - -try-cc = $(shell sh -c \ - 'TMP="$(OUTPUT)$(TMPOUT).$$$$"; \ - $(TRY_CC_MSG) \ - echo "$(1)" | \ - $(CC) -x c - $(2) -o "$$TMP" $(TRY_CC_OUTPUT) && echo y; \ - rm -f "$$TMP"') diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 85e1aed9520..8b38b4e80ec 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -49,14 +49,14 @@ static struct cmd_struct commands[] = { { "version", cmd_version, 0 }, { "script", cmd_script, 0 }, { "sched", cmd_sched, 0 }, -#ifdef LIBELF_SUPPORT +#ifdef HAVE_LIBELF_SUPPORT { "probe", cmd_probe, 0 }, #endif { "kmem", cmd_kmem, 0 }, { "lock", cmd_lock, 0 }, { "kvm", cmd_kvm, 0 }, { "test", cmd_test, 0 }, -#ifdef LIBAUDIT_SUPPORT +#ifdef HAVE_LIBAUDIT_SUPPORT { "trace", cmd_trace, 0 }, #endif { "inject", cmd_inject, 0 }, @@ -456,6 +456,7 @@ int main(int argc, const char **argv) { const char *cmd; + /* The page_size is placed in util object. */ page_size = sysconf(_SC_PAGE_SIZE); cmd = perf_extract_argv0_path(argv[0]); @@ -480,7 +481,14 @@ int main(int argc, const char **argv) fprintf(stderr, "cannot handle %s internally", cmd); goto out; } - +#ifdef HAVE_LIBAUDIT_SUPPORT + if (!prefixcmp(cmd, "trace")) { + set_buildid_dir(); + setup_path(); + argv[0] = "trace"; + return cmd_trace(argc, argv, NULL); + } +#endif /* Look for flags.. */ argv++; argc--; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 32bd102c32b..6a587e84fdf 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -4,6 +4,8 @@ #include <asm/unistd.h> #if defined(__i386__) +#define mb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") +#define wmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") #define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") #define cpu_relax() asm volatile("rep; nop" ::: "memory"); #define CPUINFO_PROC "model name" @@ -13,6 +15,8 @@ #endif #if defined(__x86_64__) +#define mb() asm volatile("mfence" ::: "memory") +#define wmb() asm volatile("sfence" ::: "memory") #define rmb() asm volatile("lfence" ::: "memory") #define cpu_relax() asm volatile("rep; nop" ::: "memory"); #define CPUINFO_PROC "model name" @@ -23,45 +27,61 @@ #ifdef __powerpc__ #include "../../arch/powerpc/include/uapi/asm/unistd.h" +#define mb() asm volatile ("sync" ::: "memory") +#define wmb() asm volatile ("sync" ::: "memory") #define rmb() asm volatile ("sync" ::: "memory") -#define cpu_relax() asm volatile ("" ::: "memory"); #define CPUINFO_PROC "cpu" #endif #ifdef __s390__ +#define mb() asm volatile("bcr 15,0" ::: "memory") +#define wmb() asm volatile("bcr 15,0" ::: "memory") #define rmb() asm volatile("bcr 15,0" ::: "memory") -#define cpu_relax() asm volatile("" ::: "memory"); #endif #ifdef __sh__ #if defined(__SH4A__) || defined(__SH5__) +# define mb() asm volatile("synco" ::: "memory") +# define wmb() asm volatile("synco" ::: "memory") # define rmb() asm volatile("synco" ::: "memory") #else +# define mb() asm volatile("" ::: "memory") +# define wmb() asm volatile("" ::: "memory") # define rmb() asm volatile("" ::: "memory") #endif -#define cpu_relax() asm volatile("" ::: "memory") #define CPUINFO_PROC "cpu type" #endif #ifdef __hppa__ +#define mb() asm volatile("" ::: "memory") +#define wmb() asm volatile("" ::: "memory") #define rmb() asm volatile("" ::: "memory") -#define cpu_relax() asm volatile("" ::: "memory"); #define CPUINFO_PROC "cpu" #endif #ifdef __sparc__ +#ifdef __LP64__ +#define mb() asm volatile("ba,pt %%xcc, 1f\n" \ + "membar #StoreLoad\n" \ + "1:\n":::"memory") +#else +#define mb() asm volatile("":::"memory") +#endif +#define wmb() asm volatile("":::"memory") #define rmb() asm volatile("":::"memory") -#define cpu_relax() asm volatile("":::"memory") #define CPUINFO_PROC "cpu" #endif #ifdef __alpha__ +#define mb() asm volatile("mb" ::: "memory") +#define wmb() asm volatile("wmb" ::: "memory") #define rmb() asm volatile("mb" ::: "memory") -#define cpu_relax() asm volatile("" ::: "memory") #define CPUINFO_PROC "cpu model" #endif #ifdef __ia64__ +#define mb() asm volatile ("mf" ::: "memory") +#define wmb() asm volatile ("mf" ::: "memory") #define rmb() asm volatile ("mf" ::: "memory") #define cpu_relax() asm volatile ("hint @pause" ::: "memory") #define CPUINFO_PROC "model name" @@ -72,40 +92,55 @@ * Use the __kuser_memory_barrier helper in the CPU helper page. See * arch/arm/kernel/entry-armv.S in the kernel source for details. */ +#define mb() ((void(*)(void))0xffff0fa0)() +#define wmb() ((void(*)(void))0xffff0fa0)() #define rmb() ((void(*)(void))0xffff0fa0)() -#define cpu_relax() asm volatile("":::"memory") #define CPUINFO_PROC "Processor" #endif #ifdef __aarch64__ -#define rmb() asm volatile("dmb ld" ::: "memory") +#define mb() asm volatile("dmb ish" ::: "memory") +#define wmb() asm volatile("dmb ishld" ::: "memory") +#define rmb() asm volatile("dmb ishst" ::: "memory") #define cpu_relax() asm volatile("yield" ::: "memory") #endif #ifdef __mips__ -#define rmb() asm volatile( \ +#define mb() asm volatile( \ ".set mips2\n\t" \ "sync\n\t" \ ".set mips0" \ : /* no output */ \ : /* no input */ \ : "memory") -#define cpu_relax() asm volatile("" ::: "memory") +#define wmb() mb() +#define rmb() mb() #define CPUINFO_PROC "cpu model" #endif #ifdef __arc__ +#define mb() asm volatile("" ::: "memory") +#define wmb() asm volatile("" ::: "memory") #define rmb() asm volatile("" ::: "memory") -#define cpu_relax() rmb() #define CPUINFO_PROC "Processor" #endif #ifdef __metag__ +#define mb() asm volatile("" ::: "memory") +#define wmb() asm volatile("" ::: "memory") #define rmb() asm volatile("" ::: "memory") -#define cpu_relax() asm volatile("" ::: "memory") #define CPUINFO_PROC "CPU" #endif +#define barrier() asm volatile ("" ::: "memory") + +#ifndef cpu_relax +#define cpu_relax() barrier() +#endif + +#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x)) + + #include <time.h> #include <unistd.h> #include <sys/types.h> @@ -125,6 +160,9 @@ #ifndef NSEC_PER_SEC # define NSEC_PER_SEC 1000000000ULL #endif +#ifndef NSEC_PER_USEC +# define NSEC_PER_USEC 1000ULL +#endif static inline unsigned long long rdclock(void) { @@ -179,7 +217,9 @@ struct ip_callchain { struct branch_flags { u64 mispred:1; u64 predicted:1; - u64 reserved:62; + u64 in_tx:1; + u64 abort:1; + u64 reserved:60; }; struct branch_entry { @@ -215,7 +255,6 @@ struct perf_record_opts { bool no_delay; bool no_inherit; bool no_samples; - bool pipe_output; bool raw_samples; bool sample_address; bool sample_weight; @@ -228,6 +267,7 @@ struct perf_record_opts { u64 default_interval; u64 user_interval; u16 stack_dump_size; + bool sample_transaction; }; #endif diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py index b11cca58423..2225162ee1f 100755 --- a/tools/perf/python/twatch.py +++ b/tools/perf/python/twatch.py @@ -21,7 +21,7 @@ def main(): evsel = perf.evsel(task = 1, comm = 1, mmap = 0, wakeup_events = 1, watermark = 1, sample_id_all = 1, - sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU | perf.SAMPLE_TID) + sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU) evsel.open(cpus = cpus, threads = threads); evlist = perf.evlist(cpus, threads) evlist.add(evsel) diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c index 315067b8f55..fcd1dd66790 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c +++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c @@ -25,7 +25,7 @@ PyMODINIT_FUNC initperf_trace_context(void); -static PyObject *perf_trace_context_common_pc(PyObject *self, PyObject *args) +static PyObject *perf_trace_context_common_pc(PyObject *obj, PyObject *args) { static struct scripting_context *scripting_context; PyObject *context; @@ -40,7 +40,7 @@ static PyObject *perf_trace_context_common_pc(PyObject *self, PyObject *args) return Py_BuildValue("i", retval); } -static PyObject *perf_trace_context_common_flags(PyObject *self, +static PyObject *perf_trace_context_common_flags(PyObject *obj, PyObject *args) { static struct scripting_context *scripting_context; @@ -56,7 +56,7 @@ static PyObject *perf_trace_context_common_flags(PyObject *self, return Py_BuildValue("i", retval); } -static PyObject *perf_trace_context_common_lock_depth(PyObject *self, +static PyObject *perf_trace_context_common_lock_depth(PyObject *obj, PyObject *args) { static struct scripting_context *scripting_context; diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README index d102957cd59..430024f618f 100644 --- a/tools/perf/tests/attr/README +++ b/tools/perf/tests/attr/README @@ -44,9 +44,9 @@ Following tests are defined (with perf commands): perf record -c 123 kill (test-record-count) perf record -d kill (test-record-data) perf record -F 100 kill (test-record-freq) - perf record -g -- kill (test-record-graph-default) - perf record -g dwarf -- kill (test-record-graph-dwarf) - perf record -g fp kill (test-record-graph-fp) + perf record -g kill (test-record-graph-default) + perf record --call-graph dwarf kill (test-record-graph-dwarf) + perf record --call-graph fp kill (test-record-graph-fp) perf record --group -e cycles,instructions kill (test-record-group) perf record -e '{cycles,instructions}' kill (test-record-group1) perf record -D kill (test-record-no-delay) diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default index 833d1849d76..853597a9a8f 100644 --- a/tools/perf/tests/attr/test-record-graph-default +++ b/tools/perf/tests/attr/test-record-graph-default @@ -1,6 +1,6 @@ [config] command = record -args = -g -- kill >/dev/null 2>&1 +args = -g kill >/dev/null 2>&1 [event:base-record] sample_type=295 diff --git a/tools/perf/tests/attr/test-record-graph-dwarf b/tools/perf/tests/attr/test-record-graph-dwarf index e93e082f520..d6f324ea578 100644 --- a/tools/perf/tests/attr/test-record-graph-dwarf +++ b/tools/perf/tests/attr/test-record-graph-dwarf @@ -1,6 +1,6 @@ [config] command = record -args = -g dwarf -- kill >/dev/null 2>&1 +args = --call-graph dwarf -- kill >/dev/null 2>&1 [event:base-record] sample_type=12583 diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp index 7cef3743f03..055e3bee799 100644 --- a/tools/perf/tests/attr/test-record-graph-fp +++ b/tools/perf/tests/attr/test-record-graph-fp @@ -1,6 +1,6 @@ [config] command = record -args = -g fp kill >/dev/null 2>&1 +args = --call-graph fp kill >/dev/null 2>&1 [event:base-record] sample_type=295 diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling new file mode 100644 index 00000000000..658f5d60c87 --- /dev/null +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -0,0 +1,36 @@ +[config] +command = record +args = -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1 + +[event-1:base-record] +fd=1 +group_fd=-1 +sample_type=343 +read_format=12 +inherit=0 + +[event-2:base-record] +fd=2 +group_fd=1 + +# cache-misses +type=0 +config=3 + +# default | PERF_SAMPLE_READ +sample_type=343 + +# PERF_FORMAT_ID | PERF_FORMAT_GROUP +read_format=12 + +mmap=0 +comm=0 +enable_on_exec=0 +disabled=0 + +# inherit is disabled for group sampling +inherit=0 + +# sampling disabled +sample_freq=0 +sample_period=0 diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 35b45f1466b..1e67437fb4c 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -93,6 +93,28 @@ static struct test { .desc = "Test software clock events have valid period values", .func = test__sw_clock_freq, }, +#if defined(__x86_64__) || defined(__i386__) + { + .desc = "Test converting perf time to TSC", + .func = test__perf_time_to_tsc, + }, +#endif + { + .desc = "Test object code reading", + .func = test__code_reading, + }, + { + .desc = "Test sample parsing", + .func = test__sample_parsing, + }, + { + .desc = "Test using a dummy software event to keep tracking", + .func = test__keep_tracking, + }, + { + .desc = "Test parsing with no sample_id_all bit set", + .func = test__parse_no_sample_id_all, + }, { .func = NULL, }, diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c new file mode 100644 index 00000000000..49ccc3b2995 --- /dev/null +++ b/tools/perf/tests/code-reading.c @@ -0,0 +1,573 @@ +#include <sys/types.h> +#include <stdlib.h> +#include <unistd.h> +#include <stdio.h> +#include <inttypes.h> +#include <ctype.h> +#include <string.h> + +#include "parse-events.h" +#include "evlist.h" +#include "evsel.h" +#include "thread_map.h" +#include "cpumap.h" +#include "machine.h" +#include "event.h" +#include "thread.h" + +#include "tests.h" + +#define BUFSZ 1024 +#define READLEN 128 + +struct state { + u64 done[1024]; + size_t done_cnt; +}; + +static unsigned int hex(char c) +{ + if (c >= '0' && c <= '9') + return c - '0'; + if (c >= 'a' && c <= 'f') + return c - 'a' + 10; + return c - 'A' + 10; +} + +static void read_objdump_line(const char *line, size_t line_len, void **buf, + size_t *len) +{ + const char *p; + size_t i; + + /* Skip to a colon */ + p = strchr(line, ':'); + if (!p) + return; + i = p + 1 - line; + + /* Read bytes */ + while (*len) { + char c1, c2; + + /* Skip spaces */ + for (; i < line_len; i++) { + if (!isspace(line[i])) + break; + } + /* Get 2 hex digits */ + if (i >= line_len || !isxdigit(line[i])) + break; + c1 = line[i++]; + if (i >= line_len || !isxdigit(line[i])) + break; + c2 = line[i++]; + /* Followed by a space */ + if (i < line_len && line[i] && !isspace(line[i])) + break; + /* Store byte */ + *(unsigned char *)*buf = (hex(c1) << 4) | hex(c2); + *buf += 1; + *len -= 1; + } +} + +static int read_objdump_output(FILE *f, void **buf, size_t *len) +{ + char *line = NULL; + size_t line_len; + ssize_t ret; + int err = 0; + + while (1) { + ret = getline(&line, &line_len, f); + if (feof(f)) + break; + if (ret < 0) { + pr_debug("getline failed\n"); + err = -1; + break; + } + read_objdump_line(line, ret, buf, len); + } + + free(line); + + return err; +} + +static int read_via_objdump(const char *filename, u64 addr, void *buf, + size_t len) +{ + char cmd[PATH_MAX * 2]; + const char *fmt; + FILE *f; + int ret; + + fmt = "%s -d --start-address=0x%"PRIx64" --stop-address=0x%"PRIx64" %s"; + ret = snprintf(cmd, sizeof(cmd), fmt, "objdump", addr, addr + len, + filename); + if (ret <= 0 || (size_t)ret >= sizeof(cmd)) + return -1; + + pr_debug("Objdump command is: %s\n", cmd); + + /* Ignore objdump errors */ + strcat(cmd, " 2>/dev/null"); + + f = popen(cmd, "r"); + if (!f) { + pr_debug("popen failed\n"); + return -1; + } + + ret = read_objdump_output(f, &buf, &len); + if (len) { + pr_debug("objdump read too few bytes\n"); + if (!ret) + ret = len; + } + + pclose(f); + + return ret; +} + +static int read_object_code(u64 addr, size_t len, u8 cpumode, + struct thread *thread, struct machine *machine, + struct state *state) +{ + struct addr_location al; + unsigned char buf1[BUFSZ]; + unsigned char buf2[BUFSZ]; + size_t ret_len; + u64 objdump_addr; + int ret; + + pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr); + + thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, addr, + &al); + if (!al.map || !al.map->dso) { + pr_debug("thread__find_addr_map failed\n"); + return -1; + } + + pr_debug("File is: %s\n", al.map->dso->long_name); + + if (al.map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && + !dso__is_kcore(al.map->dso)) { + pr_debug("Unexpected kernel address - skipping\n"); + return 0; + } + + pr_debug("On file address is: %#"PRIx64"\n", al.addr); + + if (len > BUFSZ) + len = BUFSZ; + + /* Do not go off the map */ + if (addr + len > al.map->end) + len = al.map->end - addr; + + /* Read the object code using perf */ + ret_len = dso__data_read_offset(al.map->dso, machine, al.addr, buf1, + len); + if (ret_len != len) { + pr_debug("dso__data_read_offset failed\n"); + return -1; + } + + /* + * Converting addresses for use by objdump requires more information. + * map__load() does that. See map__rip_2objdump() for details. + */ + if (map__load(al.map, NULL)) + return -1; + + /* objdump struggles with kcore - try each map only once */ + if (dso__is_kcore(al.map->dso)) { + size_t d; + + for (d = 0; d < state->done_cnt; d++) { + if (state->done[d] == al.map->start) { + pr_debug("kcore map tested already"); + pr_debug(" - skipping\n"); + return 0; + } + } + if (state->done_cnt >= ARRAY_SIZE(state->done)) { + pr_debug("Too many kcore maps - skipping\n"); + return 0; + } + state->done[state->done_cnt++] = al.map->start; + } + + /* Read the object code using objdump */ + objdump_addr = map__rip_2objdump(al.map, al.addr); + ret = read_via_objdump(al.map->dso->long_name, objdump_addr, buf2, len); + if (ret > 0) { + /* + * The kernel maps are inaccurate - assume objdump is right in + * that case. + */ + if (cpumode == PERF_RECORD_MISC_KERNEL || + cpumode == PERF_RECORD_MISC_GUEST_KERNEL) { + len -= ret; + if (len) { + pr_debug("Reducing len to %zu\n", len); + } else if (dso__is_kcore(al.map->dso)) { + /* + * objdump cannot handle very large segments + * that may be found in kcore. + */ + pr_debug("objdump failed for kcore"); + pr_debug(" - skipping\n"); + return 0; + } else { + return -1; + } + } + } + if (ret < 0) { + pr_debug("read_via_objdump failed\n"); + return -1; + } + + /* The results should be identical */ + if (memcmp(buf1, buf2, len)) { + pr_debug("Bytes read differ from those read by objdump\n"); + return -1; + } + pr_debug("Bytes read match those read by objdump\n"); + + return 0; +} + +static int process_sample_event(struct machine *machine, + struct perf_evlist *evlist, + union perf_event *event, struct state *state) +{ + struct perf_sample sample; + struct thread *thread; + u8 cpumode; + + if (perf_evlist__parse_sample(evlist, event, &sample)) { + pr_debug("perf_evlist__parse_sample failed\n"); + return -1; + } + + thread = machine__findnew_thread(machine, sample.pid, sample.pid); + if (!thread) { + pr_debug("machine__findnew_thread failed\n"); + return -1; + } + + cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + + return read_object_code(sample.ip, READLEN, cpumode, thread, machine, + state); +} + +static int process_event(struct machine *machine, struct perf_evlist *evlist, + union perf_event *event, struct state *state) +{ + if (event->header.type == PERF_RECORD_SAMPLE) + return process_sample_event(machine, evlist, event, state); + + if (event->header.type < PERF_RECORD_MAX) + return machine__process_event(machine, event, NULL); + + return 0; +} + +static int process_events(struct machine *machine, struct perf_evlist *evlist, + struct state *state) +{ + union perf_event *event; + int i, ret; + + for (i = 0; i < evlist->nr_mmaps; i++) { + while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + ret = process_event(machine, evlist, event, state); + perf_evlist__mmap_consume(evlist, i); + if (ret < 0) + return ret; + } + } + return 0; +} + +static int comp(const void *a, const void *b) +{ + return *(int *)a - *(int *)b; +} + +static void do_sort_something(void) +{ + int buf[40960], i; + + for (i = 0; i < (int)ARRAY_SIZE(buf); i++) + buf[i] = ARRAY_SIZE(buf) - i - 1; + + qsort(buf, ARRAY_SIZE(buf), sizeof(int), comp); + + for (i = 0; i < (int)ARRAY_SIZE(buf); i++) { + if (buf[i] != i) { + pr_debug("qsort failed\n"); + break; + } + } +} + +static void sort_something(void) +{ + int i; + + for (i = 0; i < 10; i++) + do_sort_something(); +} + +static void syscall_something(void) +{ + int pipefd[2]; + int i; + + for (i = 0; i < 1000; i++) { + if (pipe(pipefd) < 0) { + pr_debug("pipe failed\n"); + break; + } + close(pipefd[1]); + close(pipefd[0]); + } +} + +static void fs_something(void) +{ + const char *test_file_name = "temp-perf-code-reading-test-file--"; + FILE *f; + int i; + + for (i = 0; i < 1000; i++) { + f = fopen(test_file_name, "w+"); + if (f) { + fclose(f); + unlink(test_file_name); + } + } +} + +static void do_something(void) +{ + fs_something(); + + sort_something(); + + syscall_something(); +} + +enum { + TEST_CODE_READING_OK, + TEST_CODE_READING_NO_VMLINUX, + TEST_CODE_READING_NO_KCORE, + TEST_CODE_READING_NO_ACCESS, + TEST_CODE_READING_NO_KERNEL_OBJ, +}; + +static int do_test_code_reading(bool try_kcore) +{ + struct machines machines; + struct machine *machine; + struct thread *thread; + struct perf_record_opts opts = { + .mmap_pages = UINT_MAX, + .user_freq = UINT_MAX, + .user_interval = ULLONG_MAX, + .freq = 4000, + .target = { + .uses_mmap = true, + }, + }; + struct state state = { + .done_cnt = 0, + }; + struct thread_map *threads = NULL; + struct cpu_map *cpus = NULL; + struct perf_evlist *evlist = NULL; + struct perf_evsel *evsel = NULL; + int err = -1, ret; + pid_t pid; + struct map *map; + bool have_vmlinux, have_kcore, excl_kernel = false; + + pid = getpid(); + + machines__init(&machines); + machine = &machines.host; + + ret = machine__create_kernel_maps(machine); + if (ret < 0) { + pr_debug("machine__create_kernel_maps failed\n"); + goto out_err; + } + + /* Force the use of kallsyms instead of vmlinux to try kcore */ + if (try_kcore) + symbol_conf.kallsyms_name = "/proc/kallsyms"; + + /* Load kernel map */ + map = machine->vmlinux_maps[MAP__FUNCTION]; + ret = map__load(map, NULL); + if (ret < 0) { + pr_debug("map__load failed\n"); + goto out_err; + } + have_vmlinux = dso__is_vmlinux(map->dso); + have_kcore = dso__is_kcore(map->dso); + + /* 2nd time through we just try kcore */ + if (try_kcore && !have_kcore) + return TEST_CODE_READING_NO_KCORE; + + /* No point getting kernel events if there is no kernel object */ + if (!have_vmlinux && !have_kcore) + excl_kernel = true; + + threads = thread_map__new_by_tid(pid); + if (!threads) { + pr_debug("thread_map__new_by_tid failed\n"); + goto out_err; + } + + ret = perf_event__synthesize_thread_map(NULL, threads, + perf_event__process, machine); + if (ret < 0) { + pr_debug("perf_event__synthesize_thread_map failed\n"); + goto out_err; + } + + thread = machine__findnew_thread(machine, pid, pid); + if (!thread) { + pr_debug("machine__findnew_thread failed\n"); + goto out_err; + } + + cpus = cpu_map__new(NULL); + if (!cpus) { + pr_debug("cpu_map__new failed\n"); + goto out_err; + } + + while (1) { + const char *str; + + evlist = perf_evlist__new(); + if (!evlist) { + pr_debug("perf_evlist__new failed\n"); + goto out_err; + } + + perf_evlist__set_maps(evlist, cpus, threads); + + if (excl_kernel) + str = "cycles:u"; + else + str = "cycles"; + pr_debug("Parsing event '%s'\n", str); + ret = parse_events(evlist, str); + if (ret < 0) { + pr_debug("parse_events failed\n"); + goto out_err; + } + + perf_evlist__config(evlist, &opts); + + evsel = perf_evlist__first(evlist); + + evsel->attr.comm = 1; + evsel->attr.disabled = 1; + evsel->attr.enable_on_exec = 0; + + ret = perf_evlist__open(evlist); + if (ret < 0) { + if (!excl_kernel) { + excl_kernel = true; + perf_evlist__delete(evlist); + evlist = NULL; + continue; + } + pr_debug("perf_evlist__open failed\n"); + goto out_err; + } + break; + } + + ret = perf_evlist__mmap(evlist, UINT_MAX, false); + if (ret < 0) { + pr_debug("perf_evlist__mmap failed\n"); + goto out_err; + } + + perf_evlist__enable(evlist); + + do_something(); + + perf_evlist__disable(evlist); + + ret = process_events(machine, evlist, &state); + if (ret < 0) + goto out_err; + + if (!have_vmlinux && !have_kcore && !try_kcore) + err = TEST_CODE_READING_NO_KERNEL_OBJ; + else if (!have_vmlinux && !try_kcore) + err = TEST_CODE_READING_NO_VMLINUX; + else if (excl_kernel) + err = TEST_CODE_READING_NO_ACCESS; + else + err = TEST_CODE_READING_OK; +out_err: + if (evlist) { + perf_evlist__munmap(evlist); + perf_evlist__close(evlist); + perf_evlist__delete(evlist); + } + if (cpus) + cpu_map__delete(cpus); + if (threads) + thread_map__delete(threads); + machines__destroy_kernel_maps(&machines); + machine__delete_threads(machine); + machines__exit(&machines); + + return err; +} + +int test__code_reading(void) +{ + int ret; + + ret = do_test_code_reading(false); + if (!ret) + ret = do_test_code_reading(true); + + switch (ret) { + case TEST_CODE_READING_OK: + return 0; + case TEST_CODE_READING_NO_VMLINUX: + fprintf(stderr, " (no vmlinux)"); + return 0; + case TEST_CODE_READING_NO_KCORE: + fprintf(stderr, " (no kcore)"); + return 0; + case TEST_CODE_READING_NO_ACCESS: + fprintf(stderr, " (no access)"); + return 0; + case TEST_CODE_READING_NO_KERNEL_OBJ: + fprintf(stderr, " (no kernel obj)"); + return 0; + default: + return -1; + }; +} diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 5eaffa2de9c..9cc81a3eb9b 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -10,14 +10,6 @@ #include "symbol.h" #include "tests.h" -#define TEST_ASSERT_VAL(text, cond) \ -do { \ - if (!(cond)) { \ - pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \ - return -1; \ - } \ -} while (0) - static char *test_file(int size) { static char buf_templ[] = "/tmp/test-XXXXXX"; @@ -43,6 +35,7 @@ static char *test_file(int size) if (size != write(fd, buf, size)) templ = NULL; + free(buf); close(fd); return templ; } diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index a5d2fcc5ae3..9b98c155483 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -1,6 +1,6 @@ +#include <traceevent/event-parse.h> #include "evsel.h" #include "tests.h" -#include "event-parse.h" static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, int size, bool should_be_signed) @@ -49,7 +49,7 @@ int test__perf_evsel__tp_sched_test(void) if (perf_evsel__test_field(evsel, "prev_prio", 4, true)) ret = -1; - if (perf_evsel__test_field(evsel, "prev_state", 8, true)) + if (perf_evsel__test_field(evsel, "prev_state", sizeof(long), true)) ret = -1; if (perf_evsel__test_field(evsel, "next_comm", 16, true)) diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 89085a9615e..173bf42cc03 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -88,11 +88,12 @@ static struct machine *setup_fake_machine(struct machines *machines) for (i = 0; i < ARRAY_SIZE(fake_threads); i++) { struct thread *thread; - thread = machine__findnew_thread(machine, fake_threads[i].pid); + thread = machine__findnew_thread(machine, fake_threads[i].pid, + fake_threads[i].pid); if (thread == NULL) goto out; - thread__set_comm(thread, fake_threads[i].comm); + thread__set_comm(thread, fake_threads[i].comm, 0); } for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) { @@ -109,7 +110,7 @@ static struct machine *setup_fake_machine(struct machines *machines) strcpy(fake_mmap_event.mmap.filename, fake_mmap_info[i].filename); - machine__process_mmap_event(machine, &fake_mmap_event); + machine__process_mmap_event(machine, &fake_mmap_event, NULL); } for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) { @@ -210,20 +211,19 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) list_for_each_entry(evsel, &evlist->entries, node) { for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) { const union perf_event event = { - .ip = { - .header = { - .misc = PERF_RECORD_MISC_USER, - }, - .pid = fake_common_samples[k].pid, - .ip = fake_common_samples[k].ip, + .header = { + .misc = PERF_RECORD_MISC_USER, }, }; + sample.pid = fake_common_samples[k].pid; + sample.ip = fake_common_samples[k].ip; if (perf_event__preprocess_sample(&event, machine, &al, - &sample, 0) < 0) + &sample) < 0) goto out; - he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1); + he = __hists__add_entry(&evsel->hists, &al, NULL, + NULL, NULL, 1, 1, 0); if (he == NULL) goto out; @@ -234,20 +234,19 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) for (k = 0; k < ARRAY_SIZE(fake_samples[i]); k++) { const union perf_event event = { - .ip = { - .header = { - .misc = PERF_RECORD_MISC_USER, - }, - .pid = fake_samples[i][k].pid, - .ip = fake_samples[i][k].ip, + .header = { + .misc = PERF_RECORD_MISC_USER, }, }; + sample.pid = fake_samples[i][k].pid; + sample.ip = fake_samples[i][k].ip; if (perf_event__preprocess_sample(&event, machine, &al, - &sample, 0) < 0) + &sample) < 0) goto out; - he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1); + he = __hists__add_entry(&evsel->hists, &al, NULL, + NULL, NULL, 1, 1, 0); if (he == NULL) goto out; @@ -422,7 +421,7 @@ static void print_hists(struct hists *hists) he = rb_entry(node, struct hist_entry, rb_node_in); pr_info("%2d: entry: %-8s [%-8s] %20s: period = %"PRIu64"\n", - i, he->thread->comm, he->ms.map->dso->short_name, + i, thread__comm_str(he->thread), he->ms.map->dso->short_name, he->ms.sym->name, he->stat.period); i++; @@ -468,7 +467,7 @@ int test__hists_link(void) goto out; list_for_each_entry(evsel, &evlist->entries, node) { - hists__collapse_resort(&evsel->hists); + hists__collapse_resort(&evsel->hists, NULL); if (verbose > 2) print_hists(&evsel->hists); diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c new file mode 100644 index 00000000000..376c3560853 --- /dev/null +++ b/tools/perf/tests/keep-tracking.c @@ -0,0 +1,155 @@ +#include <sys/types.h> +#include <unistd.h> +#include <sys/prctl.h> + +#include "parse-events.h" +#include "evlist.h" +#include "evsel.h" +#include "thread_map.h" +#include "cpumap.h" +#include "tests.h" + +#define CHECK__(x) { \ + while ((x) < 0) { \ + pr_debug(#x " failed!\n"); \ + goto out_err; \ + } \ +} + +#define CHECK_NOT_NULL__(x) { \ + while ((x) == NULL) { \ + pr_debug(#x " failed!\n"); \ + goto out_err; \ + } \ +} + +static int find_comm(struct perf_evlist *evlist, const char *comm) +{ + union perf_event *event; + int i, found; + + found = 0; + for (i = 0; i < evlist->nr_mmaps; i++) { + while ((event = perf_evlist__mmap_read(evlist, i)) != 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); + } + } + return found; +} + +/** + * test__keep_tracking - test using a dummy software event to keep tracking. + * + * This function implements a test that checks that tracking events continue + * when an event is disabled but a dummy software event is not disabled. If the + * test passes %0 is returned, otherwise %-1 is returned. + */ +int test__keep_tracking(void) +{ + struct perf_record_opts opts = { + .mmap_pages = UINT_MAX, + .user_freq = UINT_MAX, + .user_interval = ULLONG_MAX, + .freq = 4000, + .target = { + .uses_mmap = true, + }, + }; + struct thread_map *threads = NULL; + struct cpu_map *cpus = NULL; + struct perf_evlist *evlist = NULL; + struct perf_evsel *evsel = NULL; + int found, err = -1; + const char *comm; + + threads = thread_map__new(-1, getpid(), UINT_MAX); + CHECK_NOT_NULL__(threads); + + cpus = cpu_map__new(NULL); + CHECK_NOT_NULL__(cpus); + + evlist = perf_evlist__new(); + CHECK_NOT_NULL__(evlist); + + perf_evlist__set_maps(evlist, cpus, threads); + + CHECK__(parse_events(evlist, "dummy:u")); + CHECK__(parse_events(evlist, "cycles:u")); + + perf_evlist__config(evlist, &opts); + + evsel = perf_evlist__first(evlist); + + evsel->attr.comm = 1; + evsel->attr.disabled = 1; + evsel->attr.enable_on_exec = 0; + + if (perf_evlist__open(evlist) < 0) { + fprintf(stderr, " (not supported)"); + err = 0; + goto out_err; + } + + CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false)); + + /* + * First, test that a 'comm' event can be found when the event is + * enabled. + */ + + perf_evlist__enable(evlist); + + comm = "Test COMM 1"; + CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0)); + + perf_evlist__disable(evlist); + + found = find_comm(evlist, comm); + if (found != 1) { + pr_debug("First time, failed to find tracking event.\n"); + goto out_err; + } + + /* + * Secondly, test that a 'comm' event can be found when the event is + * disabled with the dummy event still enabled. + */ + + perf_evlist__enable(evlist); + + evsel = perf_evlist__last(evlist); + + CHECK__(perf_evlist__disable_event(evlist, evsel)); + + comm = "Test COMM 2"; + CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0)); + + perf_evlist__disable(evlist); + + found = find_comm(evlist, comm); + if (found != 1) { + pr_debug("Seconf time, failed to find tracking event.\n"); + goto out_err; + } + + err = 0; + +out_err: + if (evlist) { + perf_evlist__disable(evlist); + perf_evlist__munmap(evlist); + perf_evlist__close(evlist); + perf_evlist__delete(evlist); + } + if (cpus) + cpu_map__delete(cpus); + if (threads) + thread_map__delete(threads); + + return err; +} diff --git a/tools/perf/tests/make b/tools/perf/tests/make index c441a287512..2ca0abf1b2b 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -1,6 +1,8 @@ PERF := . MK := Makefile +has = $(shell which $1 2>/dev/null) + # standard single make variable specified make_clean_all := clean all make_python_perf_so := python/perf.so @@ -25,6 +27,13 @@ make_help := help make_doc := doc make_perf_o := perf.o make_util_map_o := util/map.o +make_install := install +make_install_bin := install-bin +make_install_doc := install-doc +make_install_man := install-man +make_install_html := install-html +make_install_info := install-info +make_install_pdf := install-pdf # all the NO_* variable combined make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 @@ -50,14 +59,27 @@ run += make_no_backtrace run += make_no_libnuma run += make_no_libaudit run += make_no_libbionic -run += make_tags -run += make_cscope run += make_help run += make_doc run += make_perf_o run += make_util_map_o +run += make_install +run += make_install_bin +# FIXME 'install-*' commented out till they're fixed +# run += make_install_doc +# run += make_install_man +# run += make_install_html +# run += make_install_info +# run += make_install_pdf run += make_minimal +ifneq ($(call has,ctags),) +run += make_tags +endif +ifneq ($(call has,cscope),) +run += make_cscope +endif + # $(run_O) contains same portion of $(run) tests with '_O' attached # to distinguish O=... tests run_O := $(addsuffix _O,$(run)) @@ -84,6 +106,31 @@ test_make_python_perf_so := test -f $(PERF)/python/perf.so test_make_perf_o := test -f $(PERF)/perf.o test_make_util_map_o := test -f $(PERF)/util/map.o +test_make_install := test -x $$TMP_DEST/bin/perf +test_make_install_O := $(test_make_install) +test_make_install_bin := $(test_make_install) +test_make_install_bin_O := $(test_make_install) + +# FIXME nothing gets installed +test_make_install_man := test -f $$TMP_DEST/share/man/man1/perf.1 +test_make_install_man_O := $(test_make_install_man) + +# FIXME nothing gets installed +test_make_install_doc := $(test_ok) +test_make_install_doc_O := $(test_ok) + +# FIXME nothing gets installed +test_make_install_html := $(test_ok) +test_make_install_html_O := $(test_ok) + +# FIXME nothing gets installed +test_make_install_info := $(test_ok) +test_make_install_info_O := $(test_ok) + +# FIXME nothing gets installed +test_make_install_pdf := $(test_ok) +test_make_install_pdf_O := $(test_ok) + # Kbuild tests only #test_make_python_perf_so_O := test -f $$TMP/tools/perf/python/perf.so #test_make_perf_o_O := test -f $$TMP/tools/perf/perf.o @@ -95,7 +142,7 @@ test_make_util_map_o_O := true test_default = test -x $(PERF)/perf test = $(if $(test_$1),$(test_$1),$(test_default)) -test_default_O = test -x $$TMP/perf +test_default_O = test -x $$TMP_O/perf test_O = $(if $(test_$1),$(test_$1),$(test_default_O)) all: @@ -111,23 +158,27 @@ clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null) $(run): $(call clean) - @cmd="cd $(PERF) && make -f $(MK) $($@)"; \ + @TMP_DEST=$$(mktemp -d); \ + cmd="cd $(PERF) && make -f $(MK) DESTDIR=$$TMP_DEST $($@)"; \ echo "- $@: $$cmd" && echo $$cmd > $@ && \ ( eval $$cmd ) >> $@ 2>&1; \ echo " test: $(call test,$@)"; \ $(call test,$@) && \ - rm -f $@ + rm -f $@ \ + rm -rf $$TMP_DEST $(run_O): $(call clean) - @TMP=$$(mktemp -d); \ - cmd="cd $(PERF) && make -f $(MK) $($(patsubst %_O,%,$@)) O=$$TMP"; \ + @TMP_O=$$(mktemp -d); \ + TMP_DEST=$$(mktemp -d); \ + cmd="cd $(PERF) && make -f $(MK) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \ echo "- $@: $$cmd" && echo $$cmd > $@ && \ ( eval $$cmd ) >> $@ 2>&1 && \ echo " test: $(call test_O,$@)"; \ $(call test_O,$@) && \ rm -f $@ && \ - rm -rf $$TMP + rm -rf $$TMP_O \ + rm -rf $$TMP_DEST all: $(run) $(run_O) @echo OK diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 5b1b5aba722..a7232c204eb 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -72,7 +72,7 @@ int test__basic_mmap(void) } evsels[i]->attr.wakeup_events = 1; - perf_evsel__set_sample_id(evsels[i]); + perf_evsel__set_sample_id(evsels[i], false); perf_evlist__add(evlist, evsels[i]); @@ -122,6 +122,7 @@ int test__basic_mmap(void) goto out_munmap; } nr_events[evsel->idx]++; + perf_evlist__mmap_consume(evlist, 0); } err = 0; diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c index fc5b9fca8b4..524b221b829 100644 --- a/tools/perf/tests/open-syscall-tp-fields.c +++ b/tools/perf/tests/open-syscall-tp-fields.c @@ -77,8 +77,10 @@ int test__syscall_open_tp_fields(void) ++nr_events; - if (type != PERF_RECORD_SAMPLE) + if (type != PERF_RECORD_SAMPLE) { + perf_evlist__mmap_consume(evlist, i); continue; + } err = perf_evsel__parse_sample(evsel, event, &sample); if (err) { diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 0275bab4ea9..ef671cd41bb 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -2,19 +2,11 @@ #include "parse-events.h" #include "evsel.h" #include "evlist.h" -#include "sysfs.h" +#include "fs.h" #include <lk/debugfs.h> #include "tests.h" #include <linux/hw_breakpoint.h> -#define TEST_ASSERT_VAL(text, cond) \ -do { \ - if (!(cond)) { \ - pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \ - return -1; \ - } \ -} while (0) - #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \ PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD) @@ -460,6 +452,7 @@ static int test__checkevent_pmu_events(struct perf_evlist *evlist) evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned); return 0; } @@ -528,6 +521,7 @@ static int test__group1(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* cycles:upp */ evsel = perf_evsel__next(evsel); @@ -543,6 +537,7 @@ static int test__group1(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); return 0; } @@ -568,6 +563,7 @@ static int test__group2(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* cache-references + :u modifier */ evsel = perf_evsel__next(evsel); @@ -582,6 +578,7 @@ static int test__group2(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* cycles:k */ evsel = perf_evsel__next(evsel); @@ -595,6 +592,7 @@ static int test__group2(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); return 0; } @@ -623,6 +621,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) !strcmp(leader->group_name, "group1")); TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* group1 cycles:kppp */ evsel = perf_evsel__next(evsel); @@ -639,6 +638,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* group2 cycles + G modifier */ evsel = leader = perf_evsel__next(evsel); @@ -656,6 +656,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) !strcmp(leader->group_name, "group2")); TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* group2 1:3 + G modifier */ evsel = perf_evsel__next(evsel); @@ -669,6 +670,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* instructions:u */ evsel = perf_evsel__next(evsel); @@ -682,6 +684,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); return 0; } @@ -709,6 +712,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* instructions:kp + p */ evsel = perf_evsel__next(evsel); @@ -724,6 +728,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); return 0; } @@ -750,6 +755,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* instructions + G */ evsel = perf_evsel__next(evsel); @@ -764,6 +770,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* cycles:G */ evsel = leader = perf_evsel__next(evsel); @@ -780,6 +787,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read); /* instructions:G */ evsel = perf_evsel__next(evsel); @@ -971,6 +979,142 @@ static int test__group_gh4(struct perf_evlist *evlist) return 0; } +static int test__leader_sample1(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries); + + /* cycles - sampling group leader */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read); + + /* cache-misses - not sampling */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read); + + /* branch-misses - not sampling */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read); + + return 0; +} + +static int test__leader_sample2(struct perf_evlist *evlist __maybe_unused) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + + /* instructions - sampling group leader */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read); + + /* branch-misses - not sampling */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read); + + return 0; +} + +static int test__checkevent_pinned_modifier(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong pinned", evsel->attr.pinned); + + return test__checkevent_symbolic_name(evlist); +} + +static int test__pinned_group(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries); + + /* cycles - group leader */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong pinned", evsel->attr.pinned); + + /* cache-misses - can not be pinned, but will go on with the leader */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned); + + /* branch-misses - ditto */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned); + + return 0; +} + static int count_tracepoints(void) { char events_path[PATH_MAX]; @@ -1187,6 +1331,22 @@ static struct evlist_test test__events[] = { .name = "{cycles:G,cache-misses:H}:uG", .check = test__group_gh4, }, + [38] = { + .name = "{cycles,cache-misses,branch-misses}:S", + .check = test__leader_sample1, + }, + [39] = { + .name = "{instructions,branch-misses}:Su", + .check = test__leader_sample2, + }, + [40] = { + .name = "instructions:uDp", + .check = test__checkevent_pinned_modifier, + }, + [41] = { + .name = "{cycles,cache-misses,branch-misses}:D", + .check = test__pinned_group, + }, }; static struct evlist_test test__events_pmu[] = { @@ -1254,24 +1414,20 @@ static int test_events(struct evlist_test *events, unsigned cnt) static int test_term(struct terms_test *t) { - struct list_head *terms; + struct list_head terms; int ret; - terms = malloc(sizeof(*terms)); - if (!terms) - return -ENOMEM; - - INIT_LIST_HEAD(terms); + INIT_LIST_HEAD(&terms); - ret = parse_events_terms(terms, t->str); + ret = parse_events_terms(&terms, t->str); if (ret) { pr_debug("failed to parse terms '%s', err %d\n", t->str , ret); return ret; } - ret = t->check(terms); - parse_events__free_terms(terms); + ret = t->check(&terms); + parse_events__free_terms(&terms); return ret; } @@ -1300,7 +1456,7 @@ static int test_pmu(void) int ret; snprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu/format/", - sysfs_find_mountpoint()); + sysfs__mountpoint()); ret = stat(path, &st); if (ret) @@ -1317,7 +1473,7 @@ static int test_pmu_events(void) int ret; snprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu/events/", - sysfs_find_mountpoint()); + sysfs__mountpoint()); ret = stat(path, &st); if (ret) { diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c new file mode 100644 index 00000000000..e117b6c6a24 --- /dev/null +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -0,0 +1,108 @@ +#include <sys/types.h> +#include <stddef.h> + +#include "tests.h" + +#include "event.h" +#include "evlist.h" +#include "header.h" +#include "util.h" + +static int process_event(struct perf_evlist **pevlist, union perf_event *event) +{ + struct perf_sample sample; + + if (event->header.type == PERF_RECORD_HEADER_ATTR) { + if (perf_event__process_attr(NULL, event, pevlist)) { + pr_debug("perf_event__process_attr failed\n"); + return -1; + } + return 0; + } + + if (event->header.type >= PERF_RECORD_USER_TYPE_START) + return -1; + + if (!*pevlist) + return -1; + + if (perf_evlist__parse_sample(*pevlist, event, &sample)) { + pr_debug("perf_evlist__parse_sample failed\n"); + return -1; + } + + return 0; +} + +static int process_events(union perf_event **events, size_t count) +{ + struct perf_evlist *evlist = NULL; + int err = 0; + size_t i; + + for (i = 0; i < count && !err; i++) + err = process_event(&evlist, events[i]); + + if (evlist) + perf_evlist__delete(evlist); + + return err; +} + +struct test_attr_event { + struct attr_event attr; + u64 id; +}; + +/** + * test__parse_no_sample_id_all - test parsing with no sample_id_all bit set. + * + * This function tests parsing data produced on kernel's that do not support the + * sample_id_all bit. Without the sample_id_all bit, non-sample events (such as + * mmap events) do not have an id sample appended, and consequently logic + * designed to determine the id will not work. That case happens when there is + * more than one selected event, so this test processes three events: 2 + * attributes representing the selected events and one mmap event. + * + * Return: %0 on success, %-1 if the test fails. + */ +int test__parse_no_sample_id_all(void) +{ + int err; + + struct test_attr_event event1 = { + .attr = { + .header = { + .type = PERF_RECORD_HEADER_ATTR, + .size = sizeof(struct test_attr_event), + }, + }, + .id = 1, + }; + struct test_attr_event event2 = { + .attr = { + .header = { + .type = PERF_RECORD_HEADER_ATTR, + .size = sizeof(struct test_attr_event), + }, + }, + .id = 2, + }; + struct mmap_event event3 = { + .header = { + .type = PERF_RECORD_MMAP, + .size = sizeof(struct mmap_event), + }, + }; + union perf_event *events[] = { + (union perf_event *)&event1, + (union perf_event *)&event2, + (union perf_event *)&event3, + }; + + err = process_events(events, ARRAY_SIZE(events)); + if (err) + return -1; + + return 0; +} diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 72d8881873b..93a62b06c3a 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -45,12 +45,12 @@ int test__PERF_RECORD(void) }; cpu_set_t cpu_mask; size_t cpu_mask_size = sizeof(cpu_mask); - struct perf_evlist *evlist = perf_evlist__new(); + struct perf_evlist *evlist = perf_evlist__new_default(); struct perf_evsel *evsel; struct perf_sample sample; const char *cmd = "sleep"; const char *argv[] = { cmd, "1", NULL, }; - char *bname; + char *bname, *mmap_filename; u64 prev_time = 0; bool found_cmd_mmap = false, found_libc_mmap = false, @@ -66,16 +66,6 @@ int test__PERF_RECORD(void) } /* - * We need at least one evsel in the evlist, use the default - * one: "cycles". - */ - err = perf_evlist__add_default(evlist); - if (err < 0) { - pr_debug("Not enough memory to create evsel\n"); - goto out_delete_evlist; - } - - /* * Create maps of threads and cpus to monitor. In this case * we start with all threads and cpus (-1, -1) but then in * perf_evlist__prepare_workload we'll fill in the only thread @@ -212,6 +202,7 @@ int test__PERF_RECORD(void) if ((type == PERF_RECORD_COMM || type == PERF_RECORD_MMAP || + type == PERF_RECORD_MMAP2 || type == PERF_RECORD_FORK || type == PERF_RECORD_EXIT) && (pid_t)event->comm.pid != evlist->workload.pid) { @@ -220,7 +211,8 @@ int test__PERF_RECORD(void) } if ((type == PERF_RECORD_COMM || - type == PERF_RECORD_MMAP) && + type == PERF_RECORD_MMAP || + type == PERF_RECORD_MMAP2) && event->comm.pid != event->comm.tid) { pr_debug("%s with different pid/tid!\n", name); ++errs; @@ -236,7 +228,12 @@ int test__PERF_RECORD(void) case PERF_RECORD_EXIT: goto found_exit; case PERF_RECORD_MMAP: - bname = strrchr(event->mmap.filename, '/'); + mmap_filename = event->mmap.filename; + goto check_bname; + case PERF_RECORD_MMAP2: + mmap_filename = event->mmap2.filename; + check_bname: + bname = strrchr(mmap_filename, '/'); if (bname != NULL) { if (!found_cmd_mmap) found_cmd_mmap = !strcmp(bname + 1, cmd); @@ -245,7 +242,7 @@ int test__PERF_RECORD(void) if (!found_ld_mmap) found_ld_mmap = !strncmp(bname + 1, "ld", 2); } else if (!found_vdso_mmap) - found_vdso_mmap = !strcmp(event->mmap.filename, "[vdso]"); + found_vdso_mmap = !strcmp(mmap_filename, "[vdso]"); break; case PERF_RECORD_SAMPLE: @@ -256,6 +253,8 @@ int test__PERF_RECORD(void) type); ++errs; } + + perf_evlist__mmap_consume(evlist, i); } } diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c new file mode 100644 index 00000000000..4ca1b938f6a --- /dev/null +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -0,0 +1,179 @@ +#include <stdio.h> +#include <sys/types.h> +#include <unistd.h> +#include <inttypes.h> +#include <sys/prctl.h> + +#include "parse-events.h" +#include "evlist.h" +#include "evsel.h" +#include "thread_map.h" +#include "cpumap.h" +#include "tests.h" + +#include "../arch/x86/util/tsc.h" + +#define CHECK__(x) { \ + while ((x) < 0) { \ + pr_debug(#x " failed!\n"); \ + goto out_err; \ + } \ +} + +#define CHECK_NOT_NULL__(x) { \ + while ((x) == NULL) { \ + pr_debug(#x " failed!\n"); \ + goto out_err; \ + } \ +} + +static u64 rdtsc(void) +{ + unsigned int low, high; + + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + + return low | ((u64)high) << 32; +} + +/** + * test__perf_time_to_tsc - test converting perf time to TSC. + * + * This function implements a test that checks that the conversion of perf time + * to and from TSC is consistent with the order of events. If the test passes + * %0 is returned, otherwise %-1 is returned. If TSC conversion is not + * supported then then the test passes but " (not supported)" is printed. + */ +int test__perf_time_to_tsc(void) +{ + struct perf_record_opts opts = { + .mmap_pages = UINT_MAX, + .user_freq = UINT_MAX, + .user_interval = ULLONG_MAX, + .freq = 4000, + .target = { + .uses_mmap = true, + }, + .sample_time = true, + }; + struct thread_map *threads = NULL; + struct cpu_map *cpus = NULL; + struct perf_evlist *evlist = NULL; + struct perf_evsel *evsel = NULL; + int err = -1, ret, i; + const char *comm1, *comm2; + struct perf_tsc_conversion tc; + struct perf_event_mmap_page *pc; + union perf_event *event; + u64 test_tsc, comm1_tsc, comm2_tsc; + u64 test_time, comm1_time = 0, comm2_time = 0; + + threads = thread_map__new(-1, getpid(), UINT_MAX); + CHECK_NOT_NULL__(threads); + + cpus = cpu_map__new(NULL); + CHECK_NOT_NULL__(cpus); + + evlist = perf_evlist__new(); + CHECK_NOT_NULL__(evlist); + + perf_evlist__set_maps(evlist, cpus, threads); + + CHECK__(parse_events(evlist, "cycles:u")); + + perf_evlist__config(evlist, &opts); + + evsel = perf_evlist__first(evlist); + + evsel->attr.comm = 1; + evsel->attr.disabled = 1; + evsel->attr.enable_on_exec = 0; + + CHECK__(perf_evlist__open(evlist)); + + CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false)); + + pc = evlist->mmap[0].base; + ret = perf_read_tsc_conversion(pc, &tc); + if (ret) { + if (ret == -EOPNOTSUPP) { + fprintf(stderr, " (not supported)"); + return 0; + } + goto out_err; + } + + perf_evlist__enable(evlist); + + comm1 = "Test COMM 1"; + CHECK__(prctl(PR_SET_NAME, (unsigned long)comm1, 0, 0, 0)); + + test_tsc = rdtsc(); + + comm2 = "Test COMM 2"; + CHECK__(prctl(PR_SET_NAME, (unsigned long)comm2, 0, 0, 0)); + + perf_evlist__disable(evlist); + + for (i = 0; i < evlist->nr_mmaps; i++) { + while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { + struct perf_sample sample; + + if (event->header.type != PERF_RECORD_COMM || + (pid_t)event->comm.pid != getpid() || + (pid_t)event->comm.tid != getpid()) + goto next_event; + + if (strcmp(event->comm.comm, comm1) == 0) { + CHECK__(perf_evsel__parse_sample(evsel, event, + &sample)); + comm1_time = sample.time; + } + if (strcmp(event->comm.comm, comm2) == 0) { + CHECK__(perf_evsel__parse_sample(evsel, event, + &sample)); + comm2_time = sample.time; + } +next_event: + perf_evlist__mmap_consume(evlist, i); + } + } + + if (!comm1_time || !comm2_time) + goto out_err; + + test_time = tsc_to_perf_time(test_tsc, &tc); + comm1_tsc = perf_time_to_tsc(comm1_time, &tc); + comm2_tsc = perf_time_to_tsc(comm2_time, &tc); + + pr_debug("1st event perf time %"PRIu64" tsc %"PRIu64"\n", + comm1_time, comm1_tsc); + pr_debug("rdtsc time %"PRIu64" tsc %"PRIu64"\n", + test_time, test_tsc); + pr_debug("2nd event perf time %"PRIu64" tsc %"PRIu64"\n", + comm2_time, comm2_tsc); + + if (test_time <= comm1_time || + test_time >= comm2_time) + goto out_err; + + if (test_tsc <= comm1_tsc || + test_tsc >= comm2_tsc) + goto out_err; + + err = 0; + +out_err: + if (evlist) { + perf_evlist__disable(evlist); + perf_evlist__munmap(evlist); + perf_evlist__close(evlist); + perf_evlist__delete(evlist); + } + if (cpus) + cpu_map__delete(cpus); + if (threads) + thread_map__delete(threads); + + return err; +} diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c index ff94886aad9..46649c25fa5 100644 --- a/tools/perf/tests/rdpmc.c +++ b/tools/perf/tests/rdpmc.c @@ -9,8 +9,6 @@ #if defined(__x86_64__) || defined(__i386__) -#define barrier() asm volatile("" ::: "memory") - static u64 rdpmc(unsigned int counter) { unsigned int low, high; diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c new file mode 100644 index 00000000000..1b677202638 --- /dev/null +++ b/tools/perf/tests/sample-parsing.c @@ -0,0 +1,321 @@ +#include <stdbool.h> +#include <inttypes.h> + +#include "util.h" +#include "event.h" +#include "evsel.h" + +#include "tests.h" + +#define COMP(m) do { \ + if (s1->m != s2->m) { \ + pr_debug("Samples differ at '"#m"'\n"); \ + return false; \ + } \ +} while (0) + +#define MCOMP(m) do { \ + if (memcmp(&s1->m, &s2->m, sizeof(s1->m))) { \ + pr_debug("Samples differ at '"#m"'\n"); \ + return false; \ + } \ +} while (0) + +static bool samples_same(const struct perf_sample *s1, + const struct perf_sample *s2, u64 type, u64 regs_user, + u64 read_format) +{ + size_t i; + + if (type & PERF_SAMPLE_IDENTIFIER) + COMP(id); + + if (type & PERF_SAMPLE_IP) + COMP(ip); + + if (type & PERF_SAMPLE_TID) { + COMP(pid); + COMP(tid); + } + + if (type & PERF_SAMPLE_TIME) + COMP(time); + + if (type & PERF_SAMPLE_ADDR) + COMP(addr); + + if (type & PERF_SAMPLE_ID) + COMP(id); + + if (type & PERF_SAMPLE_STREAM_ID) + COMP(stream_id); + + if (type & PERF_SAMPLE_CPU) + COMP(cpu); + + if (type & PERF_SAMPLE_PERIOD) + COMP(period); + + if (type & PERF_SAMPLE_READ) { + if (read_format & PERF_FORMAT_GROUP) + COMP(read.group.nr); + else + COMP(read.one.value); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + COMP(read.time_enabled); + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + COMP(read.time_running); + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_GROUP) { + for (i = 0; i < s1->read.group.nr; i++) + MCOMP(read.group.values[i]); + } else { + COMP(read.one.id); + } + } + + if (type & PERF_SAMPLE_CALLCHAIN) { + COMP(callchain->nr); + for (i = 0; i < s1->callchain->nr; i++) + COMP(callchain->ips[i]); + } + + if (type & PERF_SAMPLE_RAW) { + COMP(raw_size); + if (memcmp(s1->raw_data, s2->raw_data, s1->raw_size)) { + pr_debug("Samples differ at 'raw_data'\n"); + return false; + } + } + + if (type & PERF_SAMPLE_BRANCH_STACK) { + COMP(branch_stack->nr); + for (i = 0; i < s1->branch_stack->nr; i++) + MCOMP(branch_stack->entries[i]); + } + + if (type & PERF_SAMPLE_REGS_USER) { + size_t sz = hweight_long(regs_user) * sizeof(u64); + + COMP(user_regs.abi); + if (s1->user_regs.abi && + (!s1->user_regs.regs || !s2->user_regs.regs || + memcmp(s1->user_regs.regs, s2->user_regs.regs, sz))) { + pr_debug("Samples differ at 'user_regs'\n"); + return false; + } + } + + if (type & PERF_SAMPLE_STACK_USER) { + COMP(user_stack.size); + if (memcmp(s1->user_stack.data, s1->user_stack.data, + s1->user_stack.size)) { + pr_debug("Samples differ at 'user_stack'\n"); + return false; + } + } + + if (type & PERF_SAMPLE_WEIGHT) + COMP(weight); + + if (type & PERF_SAMPLE_DATA_SRC) + COMP(data_src); + + if (type & PERF_SAMPLE_TRANSACTION) + COMP(transaction); + + return true; +} + +static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format) +{ + struct perf_evsel evsel = { + .needs_swap = false, + .attr = { + .sample_type = sample_type, + .sample_regs_user = sample_regs_user, + .read_format = read_format, + }, + }; + union perf_event *event; + union { + struct ip_callchain callchain; + u64 data[64]; + } callchain = { + /* 3 ips */ + .data = {3, 201, 202, 203}, + }; + union { + struct branch_stack branch_stack; + u64 data[64]; + } branch_stack = { + /* 1 branch_entry */ + .data = {1, 211, 212, 213}, + }; + u64 user_regs[64]; + const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL}; + const u64 data[] = {0x2211443366558877ULL, 0, 0xaabbccddeeff4321ULL}; + struct perf_sample sample = { + .ip = 101, + .pid = 102, + .tid = 103, + .time = 104, + .addr = 105, + .id = 106, + .stream_id = 107, + .period = 108, + .weight = 109, + .cpu = 110, + .raw_size = sizeof(raw_data), + .data_src = 111, + .transaction = 112, + .raw_data = (void *)raw_data, + .callchain = &callchain.callchain, + .branch_stack = &branch_stack.branch_stack, + .user_regs = { + .abi = PERF_SAMPLE_REGS_ABI_64, + .regs = user_regs, + }, + .user_stack = { + .size = sizeof(data), + .data = (void *)data, + }, + .read = { + .time_enabled = 0x030a59d664fca7deULL, + .time_running = 0x011b6ae553eb98edULL, + }, + }; + struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},}; + struct perf_sample sample_out; + size_t i, sz, bufsz; + int err, ret = -1; + + for (i = 0; i < sizeof(user_regs); i++) + *(i + (u8 *)user_regs) = i & 0xfe; + + if (read_format & PERF_FORMAT_GROUP) { + sample.read.group.nr = 4; + sample.read.group.values = values; + } else { + sample.read.one.value = 0x08789faeb786aa87ULL; + sample.read.one.id = 99; + } + + sz = perf_event__sample_event_size(&sample, sample_type, + sample_regs_user, read_format); + bufsz = sz + 4096; /* Add a bit for overrun checking */ + event = malloc(bufsz); + if (!event) { + pr_debug("malloc failed\n"); + return -1; + } + + memset(event, 0xff, bufsz); + event->header.type = PERF_RECORD_SAMPLE; + event->header.misc = 0; + event->header.size = sz; + + err = perf_event__synthesize_sample(event, sample_type, + sample_regs_user, read_format, + &sample, false); + if (err) { + pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", + "perf_event__synthesize_sample", sample_type, err); + goto out_free; + } + + /* The data does not contain 0xff so we use that to check the size */ + for (i = bufsz; i > 0; i--) { + if (*(i - 1 + (u8 *)event) != 0xff) + break; + } + if (i != sz) { + pr_debug("Event size mismatch: actual %zu vs expected %zu\n", + i, sz); + goto out_free; + } + + evsel.sample_size = __perf_evsel__sample_size(sample_type); + + err = perf_evsel__parse_sample(&evsel, event, &sample_out); + if (err) { + pr_debug("%s failed for sample_type %#"PRIx64", error %d\n", + "perf_evsel__parse_sample", sample_type, err); + goto out_free; + } + + if (!samples_same(&sample, &sample_out, sample_type, + sample_regs_user, read_format)) { + pr_debug("parsing failed for sample_type %#"PRIx64"\n", + sample_type); + goto out_free; + } + + ret = 0; +out_free: + free(event); + if (ret && read_format) + pr_debug("read_format %#"PRIx64"\n", read_format); + return ret; +} + +/** + * test__sample_parsing - test sample parsing. + * + * This function implements a test that synthesizes a sample event, parses it + * and then checks that the parsed sample matches the original sample. The test + * checks sample format bits separately and together. If the test passes %0 is + * returned, otherwise %-1 is returned. + */ +int test__sample_parsing(void) +{ + const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15}; + u64 sample_type; + u64 sample_regs_user; + size_t i; + int err; + + /* + * Fail the test if it has not been updated when new sample format bits + * were added. Please actually update the test rather than just change + * the condition below. + */ + if (PERF_SAMPLE_MAX > PERF_SAMPLE_TRANSACTION << 1) { + pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n"); + return -1; + } + + /* Test each sample format bit separately */ + for (sample_type = 1; sample_type != PERF_SAMPLE_MAX; + sample_type <<= 1) { + /* Test read_format variations */ + if (sample_type == PERF_SAMPLE_READ) { + for (i = 0; i < ARRAY_SIZE(rf); i++) { + err = do_test(sample_type, 0, rf[i]); + if (err) + return err; + } + continue; + } + + if (sample_type == PERF_SAMPLE_REGS_USER) + sample_regs_user = 0x3fff; + else + sample_regs_user = 0; + + err = do_test(sample_type, sample_regs_user, 0); + if (err) + return err; + } + + /* Test all sample format bits together */ + sample_type = PERF_SAMPLE_MAX - 1; + sample_regs_user = 0x3fff; + for (i = 0; i < ARRAY_SIZE(rf); i++) { + err = do_test(sample_type, sample_regs_user, rf[i]); + if (err) + return err; + } + + return 0; +} diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 2e41e2d32cc..6e2b44ec074 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) struct perf_sample sample; if (event->header.type != PERF_RECORD_SAMPLE) - continue; + goto next_event; err = perf_evlist__parse_sample(evlist, event, &sample); if (err < 0) { @@ -88,6 +88,8 @@ 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); } if ((u64) nr_samples == total_periods) { diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 28fe5894b06..c33d95f9559 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -37,20 +37,11 @@ int test__task_exit(void) signal(SIGCHLD, sig_handler); signal(SIGUSR1, sig_handler); - evlist = perf_evlist__new(); + evlist = perf_evlist__new_default(); if (evlist == NULL) { - pr_debug("perf_evlist__new\n"); + pr_debug("perf_evlist__new_default\n"); return -1; } - /* - * We need at least one evsel in the evlist, use the default - * one: "cycles". - */ - err = perf_evlist__add_default(evlist); - if (err < 0) { - pr_debug("Not enough memory to create evsel\n"); - goto out_free_evlist; - } /* * Create maps of threads and cpus to monitor. In this case @@ -96,10 +87,10 @@ int test__task_exit(void) retry: while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { - if (event->header.type != PERF_RECORD_EXIT) - continue; + if (event->header.type == PERF_RECORD_EXIT) + nr_exit++; - nr_exit++; + perf_evlist__mmap_consume(evlist, 0); } if (!exited || !nr_exit) { @@ -117,7 +108,6 @@ out_close_evlist: perf_evlist__close(evlist); out_delete_maps: perf_evlist__delete_maps(evlist); -out_free_evlist: perf_evlist__delete(evlist); return err; } diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index dd7feae2d37..e0ac713857b 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -1,6 +1,14 @@ #ifndef TESTS_H #define TESTS_H +#define TEST_ASSERT_VAL(text, cond) \ +do { \ + if (!(cond)) { \ + pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \ + return -1; \ + } \ +} while (0) + enum { TEST_OK = 0, TEST_FAIL = -1, @@ -27,5 +35,10 @@ int test__bp_signal(void); int test__bp_signal_overflow(void); int test__task_exit(void); int test__sw_clock_freq(void); +int test__perf_time_to_tsc(void); +int test__code_reading(void); +int test__sample_parsing(void); +int test__keep_tracking(void); +int test__parse_no_sample_id_all(void); #endif /* TESTS_H */ diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 7b4c4d26d1b..2bd13edcbc1 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -16,6 +16,8 @@ static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused, return 0; } +#define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x)) + int test__vmlinux_matches_kallsyms(void) { int err = -1; @@ -25,6 +27,7 @@ int test__vmlinux_matches_kallsyms(void) struct machine kallsyms, vmlinux; enum map_type type = MAP__FUNCTION; struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", }; + u64 mem_start, mem_end; /* * Step 1: @@ -73,7 +76,7 @@ int test__vmlinux_matches_kallsyms(void) goto out; } - ref_reloc_sym.addr = sym->start; + ref_reloc_sym.addr = UM(sym->start); /* * Step 5: @@ -123,10 +126,14 @@ int test__vmlinux_matches_kallsyms(void) if (sym->start == sym->end) continue; - first_pair = machine__find_kernel_symbol(&kallsyms, type, sym->start, NULL, NULL); + 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, NULL); pair = first_pair; - if (pair && pair->start == sym->start) { + if (pair && UM(pair->start) == mem_start) { next_pair: if (strcmp(sym->name, pair->name) == 0) { /* @@ -138,12 +145,20 @@ next_pair: * off the real size. More than that and we * _really_ have a problem. */ - s64 skew = sym->end - pair->end; - if (llabs(skew) < page_size) - continue; + s64 skew = mem_end - UM(pair->end); + if (llabs(skew) >= page_size) + pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n", + mem_start, sym->name, mem_end, + UM(pair->end)); + + /* + * Do not count this as a failure, because we + * could really find a case where it's not + * possible to get proper function end from + * kallsyms. + */ + continue; - pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n", - sym->start, sym->name, sym->end, pair->end); } else { struct rb_node *nnd; detour: @@ -152,7 +167,7 @@ detour: if (nnd) { struct symbol *next = rb_entry(nnd, struct symbol, rb_node); - if (next->start == sym->start) { + if (UM(next->start) == mem_start) { pair = next; goto next_pair; } @@ -165,10 +180,11 @@ detour: } pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n", - sym->start, sym->name, pair->name); + mem_start, sym->name, pair->name); } } else - pr_debug("%#" PRIx64 ": %s not on kallsyms\n", sym->start, sym->name); + pr_debug("%#" PRIx64 ": %s not on kallsyms\n", + mem_start, sym->name); err = -1; } @@ -201,16 +217,19 @@ detour: for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) { struct map *pos = rb_entry(nd, struct map, rb_node), *pair; - pair = map_groups__find(&kallsyms.kmaps, type, pos->start); + mem_start = vmlinux_map->unmap_ip(vmlinux_map, pos->start); + mem_end = vmlinux_map->unmap_ip(vmlinux_map, pos->end); + + pair = map_groups__find(&kallsyms.kmaps, type, mem_start); if (pair == NULL || pair->priv) continue; - if (pair->start == pos->start) { + if (pair->start == mem_start) { pair->priv = 1; pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as", pos->start, pos->end, pos->pgoff, pos->dso->name); - if (pos->pgoff != pair->pgoff || pos->end != pair->end) - pr_info(": \n*%" PRIx64 "-%" PRIx64 " %" PRIx64 "", + if (mem_end != pair->end) + pr_info(":\n*%" PRIx64 "-%" PRIx64 " %" PRIx64, pair->start, pair->end, pair->pgoff); pr_info(" %s\n", pair->dso->name); pair->priv = 1; diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 404ff66a3e3..7d45d2f5360 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -21,32 +21,32 @@ struct ui_browser { void *priv; const char *title; char *helpline; - unsigned int (*refresh)(struct ui_browser *self); - void (*write)(struct ui_browser *self, void *entry, int row); - void (*seek)(struct ui_browser *self, off_t offset, int whence); - bool (*filter)(struct ui_browser *self, void *entry); + unsigned int (*refresh)(struct ui_browser *browser); + void (*write)(struct ui_browser *browser, void *entry, int row); + void (*seek)(struct ui_browser *browser, off_t offset, int whence); + bool (*filter)(struct ui_browser *browser, void *entry); u32 nr_entries; bool navkeypressed; bool use_navkeypressed; }; int ui_browser__set_color(struct ui_browser *browser, int color); -void ui_browser__set_percent_color(struct ui_browser *self, +void ui_browser__set_percent_color(struct ui_browser *browser, double percent, bool current); -bool ui_browser__is_current_entry(struct ui_browser *self, unsigned row); -void ui_browser__refresh_dimensions(struct ui_browser *self); -void ui_browser__reset_index(struct ui_browser *self); +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(struct ui_browser *self, int y, int x); +void ui_browser__gotorc(struct ui_browser *browser, int y, int x); void ui_browser__write_graph(struct ui_browser *browser, int graph); void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column, u64 start, u64 end); void __ui_browser__show_title(struct ui_browser *browser, const char *title); void ui_browser__show_title(struct ui_browser *browser, const char *title); -int ui_browser__show(struct ui_browser *self, const char *title, +int ui_browser__show(struct ui_browser *browser, const char *title, const char *helpline, ...); -void ui_browser__hide(struct ui_browser *self); -int ui_browser__refresh(struct ui_browser *self); +void ui_browser__hide(struct ui_browser *browser); +int ui_browser__refresh(struct ui_browser *browser); int ui_browser__run(struct ui_browser *browser, int delay_secs); void ui_browser__update_nr_entries(struct ui_browser *browser, u32 nr_entries); void ui_browser__handle_resize(struct ui_browser *browser); @@ -63,11 +63,11 @@ int ui_browser__input_window(const char *title, const char *text, char *input, void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence); unsigned int ui_browser__argv_refresh(struct ui_browser *browser); -void ui_browser__rb_tree_seek(struct ui_browser *self, off_t offset, int whence); -unsigned int ui_browser__rb_tree_refresh(struct ui_browser *self); +void ui_browser__rb_tree_seek(struct ui_browser *browser, off_t offset, int whence); +unsigned int ui_browser__rb_tree_refresh(struct ui_browser *browser); -void ui_browser__list_head_seek(struct ui_browser *self, off_t offset, int whence); -unsigned int ui_browser__list_head_refresh(struct ui_browser *self); +void ui_browser__list_head_seek(struct ui_browser *browser, off_t offset, int whence); +unsigned int ui_browser__list_head_refresh(struct ui_browser *browser); void ui_browser__init(void); void annotate_browser__init(void); diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index cc64d3f7fc3..f0697a3aede 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -428,40 +428,52 @@ static void annotate_browser__init_asm_mode(struct annotate_browser *browser) browser->b.nr_entries = browser->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) +{ + return snprintf(title, sz, "%s %s", sym->name, map->dso->long_name); +} + static bool annotate_browser__callq(struct annotate_browser *browser, struct perf_evsel *evsel, struct hist_browser_timer *hbt) { struct map_symbol *ms = browser->b.priv; struct disasm_line *dl = browser->selection; - struct symbol *sym = ms->sym; struct annotation *notes; - struct symbol *target; - u64 ip; + 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; - ip = ms->map->map_ip(ms->map, dl->ops.target.addr); - target = map__find_symbol(ms->map, ip, NULL); - if (target == NULL) { + if (map_groups__find_ams(&target, NULL) || + map__rip_2objdump(target.map, target.map->map_ip(target.map, + target.addr)) != + dl->ops.target.addr) { ui_helpline__puts("The called function was not found."); return true; } - notes = symbol__annotation(target); + notes = symbol__annotation(target.sym); pthread_mutex_lock(¬es->lock); - if (notes->src == NULL && symbol__alloc_hist(target) < 0) { + if (notes->src == NULL && symbol__alloc_hist(target.sym) < 0) { pthread_mutex_unlock(¬es->lock); ui__warning("Not enough memory for annotating '%s' symbol!\n", - target->name); + target.sym->name); return true; } pthread_mutex_unlock(¬es->lock); - symbol__tui_annotate(target, ms->map, evsel, hbt); - ui_browser__show_title(&browser->b, sym->name); + symbol__tui_annotate(target.sym, target.map, evsel, hbt); + sym_title(ms->sym, ms->map, title, sizeof(title)); + ui_browser__show_title(&browser->b, title); return true; } @@ -495,7 +507,7 @@ static bool annotate_browser__jump(struct annotate_browser *browser) dl = annotate_browser__find_offset(browser, dl->ops.target.offset, &idx); if (dl == NULL) { - ui_helpline__puts("Invallid jump offset"); + ui_helpline__puts("Invalid jump offset"); return true; } @@ -653,8 +665,10 @@ static int annotate_browser__run(struct annotate_browser *browser, const char *help = "Press 'h' for help on key bindings"; int delay_secs = hbt ? hbt->refresh : 0; int key; + char title[SYM_TITLE_MAX_SIZE]; - if (ui_browser__show(&browser->b, sym->name, help) < 0) + sym_title(sym, ms->map, title, sizeof(title)); + if (ui_browser__show(&browser->b, title, help) < 0) return -1; annotate_browser__calc_percent(browser, evsel); @@ -720,7 +734,7 @@ static int annotate_browser__run(struct annotate_browser *browser, "s Toggle source code view\n" "/ Search string\n" "r Run available scripts\n" - "? Search previous string\n"); + "? Search string backwards\n"); continue; case 'r': { diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index fc0bd3843d3..16848bb4c41 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -685,8 +685,10 @@ static u64 __hpp_get_##_field(struct hist_entry *he) \ return he->stat._field; \ } \ \ -static int hist_browser__hpp_color_##_type(struct perf_hpp *hpp, \ - struct hist_entry *he) \ +static int \ +hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\ + struct perf_hpp *hpp, \ + struct hist_entry *he) \ { \ return __hpp__color_fmt(hpp, he, __hpp_get_##_field, _cb); \ } @@ -701,8 +703,6 @@ __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, NULL) void hist_browser__init_hpp(void) { - perf_hpp__column_enable(PERF_HPP__OVERHEAD); - perf_hpp__init(); perf_hpp__format[PERF_HPP__OVERHEAD].color = @@ -762,9 +762,9 @@ static int hist_browser__show_entry(struct hist_browser *browser, first = false; if (fmt->color) { - width -= fmt->color(&hpp, entry); + width -= fmt->color(fmt, &hpp, entry); } else { - width -= fmt->entry(&hpp, entry); + width -= fmt->entry(fmt, &hpp, entry); slsmg_printf("%s", s); } } @@ -1255,8 +1255,8 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size, if (thread) printed += scnprintf(bf + printed, size - printed, ", Thread: %s(%d)", - (thread->comm_set ? thread->comm : ""), - thread->pid); + (thread->comm_set ? thread__comm_str(thread) : ""), + thread->tid); if (dso) printed += scnprintf(bf + printed, size - printed, ", DSO: %s", dso->short_name); @@ -1578,8 +1578,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (thread != NULL && asprintf(&options[nr_options], "Zoom %s %s(%d) thread", (browser->hists->thread_filter ? "out of" : "into"), - (thread->comm_set ? thread->comm : ""), - thread->pid) > 0) + (thread->comm_set ? thread__comm_str(thread) : ""), + thread->tid) > 0) zoom_thread = nr_options++; if (dso != NULL && @@ -1598,7 +1598,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, struct symbol *sym; if (asprintf(&options[nr_options], "Run scripts for samples of thread [%s]", - browser->he_selection->thread->comm) > 0) + thread__comm_str(browser->he_selection->thread)) > 0) scripts_comm = nr_options++; sym = browser->he_selection->ms.sym; @@ -1701,8 +1701,8 @@ zoom_out_thread: sort_thread.elide = false; } else { ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"", - thread->comm_set ? thread->comm : "", - thread->pid); + thread->comm_set ? thread__comm_str(thread) : "", + thread->tid); browser->hists->thread_filter = thread; sort_thread.elide = true; pstack__push(fstack, &browser->hists->thread_filter); @@ -1717,7 +1717,7 @@ do_scripts: memset(script_opt, 0, 64); if (choice == scripts_comm) - sprintf(script_opt, " -c %s ", browser->he_selection->thread->comm); + sprintf(script_opt, " -c %s ", thread__comm_str(browser->he_selection->thread)); if (choice == scripts_symbol) sprintf(script_opt, " -S %s ", browser->he_selection->ms.sym->name); @@ -1889,7 +1889,7 @@ out: return key; } -static bool filter_group_entries(struct ui_browser *self __maybe_unused, +static bool filter_group_entries(struct ui_browser *browser __maybe_unused, void *entry) { struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node); diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c index 95c7cfb8f2c..b11639f3368 100644 --- a/tools/perf/ui/browsers/map.c +++ b/tools/perf/ui/browsers/map.c @@ -18,30 +18,30 @@ struct map_browser { u8 addrlen; }; -static void map_browser__write(struct ui_browser *self, void *nd, int row) +static void map_browser__write(struct ui_browser *browser, void *nd, int row) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); - struct map_browser *mb = container_of(self, struct map_browser, b); - bool current_entry = ui_browser__is_current_entry(self, row); + struct map_browser *mb = container_of(browser, struct map_browser, b); + bool current_entry = ui_browser__is_current_entry(browser, row); int width; - ui_browser__set_percent_color(self, 0, current_entry); + ui_browser__set_percent_color(browser, 0, current_entry); slsmg_printf("%*" PRIx64 " %*" PRIx64 " %c ", mb->addrlen, sym->start, mb->addrlen, sym->end, sym->binding == STB_GLOBAL ? 'g' : sym->binding == STB_LOCAL ? 'l' : 'w'); - width = self->width - ((mb->addrlen * 2) + 4); + width = browser->width - ((mb->addrlen * 2) + 4); if (width > 0) slsmg_write_nstring(sym->name, width); } /* FIXME uber-kludgy, see comment on cmd_report... */ -static u32 *symbol__browser_index(struct symbol *self) +static u32 *symbol__browser_index(struct symbol *browser) { - return ((void *)self) - sizeof(struct rb_node) - sizeof(u32); + return ((void *)browser) - sizeof(struct rb_node) - sizeof(u32); } -static int map_browser__search(struct map_browser *self) +static int map_browser__search(struct map_browser *browser) { char target[512]; struct symbol *sym; @@ -53,37 +53,37 @@ static int map_browser__search(struct map_browser *self) if (target[0] == '0' && tolower(target[1]) == 'x') { u64 addr = strtoull(target, NULL, 16); - sym = map__find_symbol(self->map, addr, NULL); + sym = map__find_symbol(browser->map, addr, NULL); } else - sym = map__find_symbol_by_name(self->map, target, NULL); + sym = map__find_symbol_by_name(browser->map, target, NULL); if (sym != NULL) { u32 *idx = symbol__browser_index(sym); - self->b.top = &sym->rb_node; - self->b.index = self->b.top_idx = *idx; + browser->b.top = &sym->rb_node; + browser->b.index = browser->b.top_idx = *idx; } else ui_helpline__fpush("%s not found!", target); return 0; } -static int map_browser__run(struct map_browser *self) +static int map_browser__run(struct map_browser *browser) { int key; - if (ui_browser__show(&self->b, self->map->dso->long_name, + if (ui_browser__show(&browser->b, browser->map->dso->long_name, "Press <- or ESC to exit, %s / to search", verbose ? "" : "restart with -v to use") < 0) return -1; while (1) { - key = ui_browser__run(&self->b, 0); + key = ui_browser__run(&browser->b, 0); switch (key) { case '/': if (verbose) - map_browser__search(self); + map_browser__search(browser); default: break; case K_LEFT: @@ -94,20 +94,20 @@ static int map_browser__run(struct map_browser *self) } } out: - ui_browser__hide(&self->b); + ui_browser__hide(&browser->b); return key; } -int map__browse(struct map *self) +int map__browse(struct map *map) { struct map_browser mb = { .b = { - .entries = &self->dso->symbols[self->type], + .entries = &map->dso->symbols[map->type], .refresh = ui_browser__rb_tree_refresh, .seek = ui_browser__rb_tree_seek, .write = map_browser__write, }, - .map = self, + .map = map, }; struct rb_node *nd; char tmp[BITS_PER_LONG / 4]; diff --git a/tools/perf/ui/browsers/map.h b/tools/perf/ui/browsers/map.h index df8581a43e1..2d58e4b3eb6 100644 --- a/tools/perf/ui/browsers/map.h +++ b/tools/perf/ui/browsers/map.h @@ -2,5 +2,5 @@ #define _PERF_UI_MAP_BROWSER_H_ 1 struct map; -int map__browse(struct map *self); +int map__browse(struct map *map); #endif /* _PERF_UI_MAP_BROWSER_H_ */ diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index 12f009e61e9..d63c68ea02a 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -84,22 +84,22 @@ static void script_browser__write(struct ui_browser *browser, slsmg_write_nstring(sline->line, browser->width); } -static int script_browser__run(struct perf_script_browser *self) +static int script_browser__run(struct perf_script_browser *browser) { int key; - if (ui_browser__show(&self->b, self->script_name, + if (ui_browser__show(&browser->b, browser->script_name, "Press <- or ESC to exit") < 0) return -1; while (1) { - key = ui_browser__run(&self->b, 0); + key = ui_browser__run(&browser->b, 0); /* We can add some special key handling here if needed */ break; } - ui_browser__hide(&self->b); + ui_browser__hide(&browser->b); return key; } diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index f538794615d..9c7ff8d31b2 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -154,9 +154,9 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym, return 0; } -int symbol__gtk_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, - struct hist_browser_timer *hbt) +static int symbol__gtk_annotate(struct symbol *sym, struct map *map, + struct perf_evsel *evsel, + struct hist_browser_timer *hbt) { GtkWidget *window; GtkWidget *notebook; @@ -226,6 +226,13 @@ int symbol__gtk_annotate(struct symbol *sym, struct map *map, return 0; } +int hist_entry__gtk_annotate(struct hist_entry *he, + struct perf_evsel *evsel, + struct hist_browser_timer *hbt) +{ + return symbol__gtk_annotate(he->ms.sym, he->ms.map, evsel, hbt); +} + void perf_gtk__show_annotations(void) { GtkWidget *window; diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c index c95012cdb43..c24d9122129 100644 --- a/tools/perf/ui/gtk/browser.c +++ b/tools/perf/ui/gtk/browser.c @@ -43,7 +43,7 @@ const char *perf_gtk__get_percent_color(double percent) return NULL; } -#ifdef HAVE_GTK_INFO_BAR +#ifdef HAVE_GTK_INFO_BAR_SUPPORT GtkWidget *perf_gtk__setup_info_bar(void) { GtkWidget *info_bar; diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h index 3d96785ef15..0a9173ff9a6 100644 --- a/tools/perf/ui/gtk/gtk.h +++ b/tools/perf/ui/gtk/gtk.h @@ -12,7 +12,7 @@ struct perf_gtk_context { GtkWidget *main_window; GtkWidget *notebook; -#ifdef HAVE_GTK_INFO_BAR +#ifdef HAVE_GTK_INFO_BAR_SUPPORT GtkWidget *info_bar; GtkWidget *message_label; #endif @@ -20,6 +20,9 @@ struct perf_gtk_context { guint statbar_ctx_id; }; +int perf_gtk__init(void); +void perf_gtk__exit(bool wait_for_ok); + extern struct perf_gtk_context *pgctx; static inline bool perf_gtk__is_active_context(struct perf_gtk_context *ctx) @@ -31,7 +34,7 @@ struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window); int perf_gtk__deactivate_context(struct perf_gtk_context **ctx); void perf_gtk__init_helpline(void); -void perf_gtk__init_progress(void); +void gtk_ui_progress__init(void); void perf_gtk__init_hpp(void); void perf_gtk__signal(int sig); @@ -39,7 +42,7 @@ void perf_gtk__resize_window(GtkWidget *window); const char *perf_gtk__get_percent_color(double percent); GtkWidget *perf_gtk__setup_statusbar(void); -#ifdef HAVE_GTK_INFO_BAR +#ifdef HAVE_GTK_INFO_BAR_SUPPORT GtkWidget *perf_gtk__setup_info_bar(void); #else static inline GtkWidget *perf_gtk__setup_info_bar(void) @@ -48,4 +51,17 @@ static inline GtkWidget *perf_gtk__setup_info_bar(void) } #endif +struct perf_evsel; +struct perf_evlist; +struct hist_entry; +struct hist_browser_timer; + +int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help, + struct hist_browser_timer *hbt, + float min_pcnt); +int hist_entry__gtk_annotate(struct hist_entry *he, + struct perf_evsel *evsel, + struct hist_browser_timer *hbt); +void perf_gtk__show_annotations(void); + #endif /* _PERF_GTK_H_ */ diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 9708dd5fb8f..2ca66cc1160 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -91,7 +91,8 @@ static u64 he_get_##_field(struct hist_entry *he) \ return he->stat._field; \ } \ \ -static int perf_gtk__hpp_color_##_type(struct perf_hpp *hpp, \ +static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ + struct perf_hpp *hpp, \ struct hist_entry *he) \ { \ return __hpp__color_fmt(hpp, he, he_get_##_field); \ @@ -108,8 +109,6 @@ __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us) void perf_gtk__init_hpp(void) { - perf_hpp__column_enable(PERF_HPP__OVERHEAD); - perf_hpp__init(); perf_hpp__format[PERF_HPP__OVERHEAD].color = @@ -124,6 +123,81 @@ void perf_gtk__init_hpp(void) perf_gtk__hpp_color_overhead_guest_us; } +static void callchain_list__sym_name(struct callchain_list *cl, + char *bf, size_t bfsize) +{ + if (cl->ms.sym) + scnprintf(bf, bfsize, "%s", cl->ms.sym->name); + else + scnprintf(bf, bfsize, "%#" PRIx64, cl->ip); +} + +static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store, + GtkTreeIter *parent, int col, u64 total) +{ + struct rb_node *nd; + bool has_single_node = (rb_first(root) == rb_last(root)); + + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + struct callchain_node *node; + struct callchain_list *chain; + GtkTreeIter iter, new_parent; + bool need_new_parent; + double percent; + u64 hits, child_total; + + node = rb_entry(nd, struct callchain_node, rb_node); + + hits = callchain_cumul_hits(node); + percent = 100.0 * hits / total; + + new_parent = *parent; + need_new_parent = !has_single_node && (node->val_nr > 1); + + list_for_each_entry(chain, &node->val, list) { + char buf[128]; + + gtk_tree_store_append(store, &iter, &new_parent); + + scnprintf(buf, sizeof(buf), "%5.2f%%", percent); + gtk_tree_store_set(store, &iter, 0, buf, -1); + + callchain_list__sym_name(chain, buf, sizeof(buf)); + gtk_tree_store_set(store, &iter, col, buf, -1); + + if (need_new_parent) { + /* + * Only show the top-most symbol in a callchain + * if it's not the only callchain. + */ + new_parent = iter; + need_new_parent = false; + } + } + + if (callchain_param.mode == CHAIN_GRAPH_REL) + child_total = node->children_hit; + else + child_total = total; + + /* Now 'iter' contains info of the last callchain_list */ + perf_gtk__add_callchain(&node->rb_root, store, &iter, col, + child_total); + } +} + +static void on_row_activated(GtkTreeView *view, GtkTreePath *path, + GtkTreeViewColumn *col __maybe_unused, + gpointer user_data __maybe_unused) +{ + bool expanded = gtk_tree_view_row_expanded(view, path); + + if (expanded) + gtk_tree_view_collapse_row(view, path); + else + gtk_tree_view_expand_row(view, path, FALSE); +} + static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, float min_pcnt) { @@ -131,10 +205,11 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, GType col_types[MAX_COLUMNS]; GtkCellRenderer *renderer; struct sort_entry *se; - GtkListStore *store; + GtkTreeStore *store; struct rb_node *nd; GtkWidget *view; int col_idx; + int sym_col = -1; int nr_cols; char s[512]; @@ -153,10 +228,13 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, if (se->elide) continue; + if (se == &sort_sym) + sym_col = nr_cols; + col_types[nr_cols++] = G_TYPE_STRING; } - store = gtk_list_store_newv(nr_cols, col_types); + store = gtk_tree_store_newv(nr_cols, col_types); view = gtk_tree_view_new(); @@ -165,7 +243,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx = 0; perf_hpp__for_each_format(fmt) { - fmt->header(&hpp); + fmt->header(fmt, &hpp); gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), -1, ltrim(s), @@ -183,6 +261,18 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx++, NULL); } + for (col_idx = 0; col_idx < nr_cols; col_idx++) { + GtkTreeViewColumn *column; + + column = gtk_tree_view_get_column(GTK_TREE_VIEW(view), col_idx); + gtk_tree_view_column_set_resizable(column, TRUE); + + if (col_idx == sym_col) { + gtk_tree_view_set_expander_column(GTK_TREE_VIEW(view), + column); + } + } + gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store)); g_object_unref(GTK_TREE_MODEL(store)); @@ -199,17 +289,17 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, if (percent < min_pcnt) continue; - gtk_list_store_append(store, &iter); + gtk_tree_store_append(store, &iter, NULL); col_idx = 0; perf_hpp__for_each_format(fmt) { if (fmt->color) - fmt->color(&hpp, h); + fmt->color(fmt, &hpp, h); else - fmt->entry(&hpp, h); + fmt->entry(fmt, &hpp, h); - gtk_list_store_set(store, &iter, col_idx++, s, -1); + gtk_tree_store_set(store, &iter, col_idx++, s, -1); } list_for_each_entry(se, &hist_entry__sort_list, list) { @@ -219,10 +309,26 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, se->se_snprintf(h, s, ARRAY_SIZE(s), hists__col_len(hists, se->se_width_idx)); - gtk_list_store_set(store, &iter, col_idx++, s, -1); + gtk_tree_store_set(store, &iter, col_idx++, s, -1); + } + + if (symbol_conf.use_callchain && sort__has_sym) { + u64 total; + + if (callchain_param.mode == CHAIN_GRAPH_REL) + total = h->stat.period; + else + total = hists->stats.total_period; + + perf_gtk__add_callchain(&h->sorted_chain, store, &iter, + sym_col, total); } } + gtk_tree_view_set_rules_hint(GTK_TREE_VIEW(view), TRUE); + + g_signal_connect(view, "row-activated", + G_CALLBACK(on_row_activated), NULL); gtk_container_add(GTK_CONTAINER(window), view); } diff --git a/tools/perf/ui/gtk/progress.c b/tools/perf/ui/gtk/progress.c index 482bcf3df9b..b656655fbc3 100644 --- a/tools/perf/ui/gtk/progress.c +++ b/tools/perf/ui/gtk/progress.c @@ -7,14 +7,14 @@ static GtkWidget *dialog; static GtkWidget *progress; -static void gtk_progress_update(u64 curr, u64 total, const char *title) +static void gtk_ui_progress__update(struct ui_progress *p) { - double fraction = total ? 1.0 * curr / total : 0.0; + double fraction = p->total ? 1.0 * p->curr / p->total : 0.0; char buf[1024]; if (dialog == NULL) { GtkWidget *vbox = gtk_vbox_new(TRUE, 5); - GtkWidget *label = gtk_label_new(title); + GtkWidget *label = gtk_label_new(p->title); dialog = gtk_window_new(GTK_WINDOW_TOPLEVEL); progress = gtk_progress_bar_new(); @@ -32,7 +32,7 @@ static void gtk_progress_update(u64 curr, u64 total, const char *title) } gtk_progress_bar_set_fraction(GTK_PROGRESS_BAR(progress), fraction); - snprintf(buf, sizeof(buf), "%"PRIu64" / %"PRIu64, curr, total); + snprintf(buf, sizeof(buf), "%"PRIu64" / %"PRIu64, p->curr, p->total); gtk_progress_bar_set_text(GTK_PROGRESS_BAR(progress), buf); /* we didn't call gtk_main yet, so do it manually */ @@ -40,7 +40,7 @@ static void gtk_progress_update(u64 curr, u64 total, const char *title) gtk_main_iteration(); } -static void gtk_progress_finish(void) +static void gtk_ui_progress__finish(void) { /* this will also destroy all of its children */ gtk_widget_destroy(dialog); @@ -48,12 +48,12 @@ static void gtk_progress_finish(void) dialog = NULL; } -static struct ui_progress gtk_progress_fns = { - .update = gtk_progress_update, - .finish = gtk_progress_finish, +static struct ui_progress_ops gtk_ui_progress__ops = { + .update = gtk_ui_progress__update, + .finish = gtk_ui_progress__finish, }; -void perf_gtk__init_progress(void) +void gtk_ui_progress__init(void) { - progress_fns = >k_progress_fns; + ui_progress__ops = >k_ui_progress__ops; } diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c index 6c2dd2e423f..1d57676f821 100644 --- a/tools/perf/ui/gtk/setup.c +++ b/tools/perf/ui/gtk/setup.c @@ -8,7 +8,7 @@ int perf_gtk__init(void) { perf_error__register(&perf_gtk_eops); perf_gtk__init_helpline(); - perf_gtk__init_progress(); + gtk_ui_progress__init(); perf_gtk__init_hpp(); return gtk_init_check(NULL, NULL) ? 0 : -1; diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c index c06942a41c7..696c1fbe424 100644 --- a/tools/perf/ui/gtk/util.c +++ b/tools/perf/ui/gtk/util.c @@ -53,7 +53,7 @@ static int perf_gtk__error(const char *format, va_list args) return 0; } -#ifdef HAVE_GTK_INFO_BAR +#ifdef HAVE_GTK_INFO_BAR_SUPPORT static int perf_gtk__warning_info_bar(const char *format, va_list args) { char *msg; @@ -105,7 +105,7 @@ static int perf_gtk__warning_statusbar(const char *format, va_list args) struct perf_error_ops perf_gtk_eops = { .error = perf_gtk__error, -#ifdef HAVE_GTK_INFO_BAR +#ifdef HAVE_GTK_INFO_BAR_SUPPORT .warning = perf_gtk__warning_info_bar, #else .warning = perf_gtk__warning_statusbar, diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 4bf91b09d62..78f4c92e9b7 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -1,4 +1,5 @@ #include <math.h> +#include <linux/compiler.h> #include "../util/hist.h" #include "../util/util.h" @@ -79,7 +80,8 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, } #define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ -static int hpp__header_##_type(struct perf_hpp *hpp) \ +static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ + struct perf_hpp *hpp) \ { \ int len = _min_width; \ \ @@ -92,7 +94,8 @@ static int hpp__header_##_type(struct perf_hpp *hpp) \ } #define __HPP_WIDTH_FN(_type, _min_width, _unit_width) \ -static int hpp__width_##_type(struct perf_hpp *hpp __maybe_unused) \ +static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ + struct perf_hpp *hpp __maybe_unused) \ { \ int len = _min_width; \ \ @@ -110,14 +113,16 @@ static u64 he_get_##_field(struct hist_entry *he) \ return he->stat._field; \ } \ \ -static int hpp__color_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ +static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \ + struct perf_hpp *hpp, struct hist_entry *he) \ { \ return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \ - (hpp_snprint_fn)percent_color_snprintf, true); \ + percent_color_snprintf, true); \ } #define __HPP_ENTRY_PERCENT_FN(_type, _field) \ -static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ +static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \ + struct perf_hpp *hpp, struct hist_entry *he) \ { \ const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%"; \ return __hpp__fmt(hpp, he, he_get_##_field, fmt, \ @@ -130,7 +135,8 @@ static u64 he_get_raw_##_field(struct hist_entry *he) \ return he->stat._field; \ } \ \ -static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ +static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \ + struct perf_hpp *hpp, struct hist_entry *he) \ { \ const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64; \ return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf, false); \ @@ -157,196 +163,6 @@ HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8) HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12) HPP_RAW_FNS(period, "Period", period, 12, 12) - -static int hpp__header_baseline(struct perf_hpp *hpp) -{ - return scnprintf(hpp->buf, hpp->size, "Baseline"); -} - -static int hpp__width_baseline(struct perf_hpp *hpp __maybe_unused) -{ - return 8; -} - -static double baseline_percent(struct hist_entry *he) -{ - struct hist_entry *pair = hist_entry__next_pair(he); - struct hists *pair_hists = pair ? pair->hists : NULL; - double percent = 0.0; - - if (pair) { - u64 total_period = pair_hists->stats.total_period; - u64 base_period = pair->stat.period; - - percent = 100.0 * base_period / total_period; - } - - return percent; -} - -static int hpp__color_baseline(struct perf_hpp *hpp, struct hist_entry *he) -{ - double percent = baseline_percent(he); - - if (hist_entry__has_pairs(he) || symbol_conf.field_sep) - return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent); - else - return scnprintf(hpp->buf, hpp->size, " "); -} - -static int hpp__entry_baseline(struct perf_hpp *hpp, struct hist_entry *he) -{ - double percent = baseline_percent(he); - const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%"; - - if (hist_entry__has_pairs(he) || symbol_conf.field_sep) - return scnprintf(hpp->buf, hpp->size, fmt, percent); - else - return scnprintf(hpp->buf, hpp->size, " "); -} - -static int hpp__header_period_baseline(struct perf_hpp *hpp) -{ - const char *fmt = symbol_conf.field_sep ? "%s" : "%12s"; - - return scnprintf(hpp->buf, hpp->size, fmt, "Period Base"); -} - -static int hpp__width_period_baseline(struct perf_hpp *hpp __maybe_unused) -{ - return 12; -} - -static int hpp__entry_period_baseline(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hist_entry *pair = hist_entry__next_pair(he); - u64 period = pair ? pair->stat.period : 0; - const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%12" PRIu64; - - return scnprintf(hpp->buf, hpp->size, fmt, period); -} - -static int hpp__header_delta(struct perf_hpp *hpp) -{ - const char *fmt = symbol_conf.field_sep ? "%s" : "%7s"; - - return scnprintf(hpp->buf, hpp->size, fmt, "Delta"); -} - -static int hpp__width_delta(struct perf_hpp *hpp __maybe_unused) -{ - return 7; -} - -static int hpp__entry_delta(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hist_entry *pair = hist_entry__next_pair(he); - const char *fmt = symbol_conf.field_sep ? "%s" : "%7.7s"; - char buf[32] = " "; - double diff = 0.0; - - if (pair) { - if (he->diff.computed) - diff = he->diff.period_ratio_delta; - else - diff = perf_diff__compute_delta(he, pair); - } else - diff = perf_diff__period_percent(he, he->stat.period); - - if (fabs(diff) >= 0.01) - scnprintf(buf, sizeof(buf), "%+4.2F%%", diff); - - return scnprintf(hpp->buf, hpp->size, fmt, buf); -} - -static int hpp__header_ratio(struct perf_hpp *hpp) -{ - const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; - - return scnprintf(hpp->buf, hpp->size, fmt, "Ratio"); -} - -static int hpp__width_ratio(struct perf_hpp *hpp __maybe_unused) -{ - return 14; -} - -static int hpp__entry_ratio(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hist_entry *pair = hist_entry__next_pair(he); - const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; - char buf[32] = " "; - double ratio = 0.0; - - if (pair) { - if (he->diff.computed) - ratio = he->diff.period_ratio; - else - ratio = perf_diff__compute_ratio(he, pair); - } - - if (ratio > 0.0) - scnprintf(buf, sizeof(buf), "%+14.6F", ratio); - - return scnprintf(hpp->buf, hpp->size, fmt, buf); -} - -static int hpp__header_wdiff(struct perf_hpp *hpp) -{ - const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; - - return scnprintf(hpp->buf, hpp->size, fmt, "Weighted diff"); -} - -static int hpp__width_wdiff(struct perf_hpp *hpp __maybe_unused) -{ - return 14; -} - -static int hpp__entry_wdiff(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hist_entry *pair = hist_entry__next_pair(he); - const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; - char buf[32] = " "; - s64 wdiff = 0; - - if (pair) { - if (he->diff.computed) - wdiff = he->diff.wdiff; - else - wdiff = perf_diff__compute_wdiff(he, pair); - } - - if (wdiff != 0) - scnprintf(buf, sizeof(buf), "%14ld", wdiff); - - return scnprintf(hpp->buf, hpp->size, fmt, buf); -} - -static int hpp__header_formula(struct perf_hpp *hpp) -{ - const char *fmt = symbol_conf.field_sep ? "%s" : "%70s"; - - return scnprintf(hpp->buf, hpp->size, fmt, "Formula"); -} - -static int hpp__width_formula(struct perf_hpp *hpp __maybe_unused) -{ - return 70; -} - -static int hpp__entry_formula(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hist_entry *pair = hist_entry__next_pair(he); - const char *fmt = symbol_conf.field_sep ? "%s" : "%-70s"; - char buf[96] = " "; - - if (pair) - perf_diff__formula(he, pair, buf, sizeof(buf)); - - return scnprintf(hpp->buf, hpp->size, fmt, buf); -} - #define HPP__COLOR_PRINT_FNS(_name) \ { \ .header = hpp__header_ ## _name, \ @@ -363,19 +179,13 @@ static int hpp__entry_formula(struct perf_hpp *hpp, struct hist_entry *he) } struct perf_hpp_fmt perf_hpp__format[] = { - HPP__COLOR_PRINT_FNS(baseline), HPP__COLOR_PRINT_FNS(overhead), HPP__COLOR_PRINT_FNS(overhead_sys), HPP__COLOR_PRINT_FNS(overhead_us), HPP__COLOR_PRINT_FNS(overhead_guest_sys), HPP__COLOR_PRINT_FNS(overhead_guest_us), HPP__PRINT_FNS(samples), - HPP__PRINT_FNS(period), - HPP__PRINT_FNS(period_baseline), - HPP__PRINT_FNS(delta), - HPP__PRINT_FNS(ratio), - HPP__PRINT_FNS(wdiff), - HPP__PRINT_FNS(formula) + HPP__PRINT_FNS(period) }; LIST_HEAD(perf_hpp__list); @@ -396,6 +206,8 @@ LIST_HEAD(perf_hpp__list); void perf_hpp__init(void) { + perf_hpp__column_enable(PERF_HPP__OVERHEAD); + if (symbol_conf.show_cpu_utilization) { perf_hpp__column_enable(PERF_HPP__OVERHEAD_SYS); perf_hpp__column_enable(PERF_HPP__OVERHEAD_US); @@ -424,46 +236,6 @@ void perf_hpp__column_enable(unsigned col) perf_hpp__column_register(&perf_hpp__format[col]); } -static inline void advance_hpp(struct perf_hpp *hpp, int inc) -{ - hpp->buf += inc; - hpp->size -= inc; -} - -int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he, - bool color) -{ - const char *sep = symbol_conf.field_sep; - struct perf_hpp_fmt *fmt; - char *start = hpp->buf; - int ret; - bool first = true; - - if (symbol_conf.exclude_other && !he->parent) - return 0; - - perf_hpp__for_each_format(fmt) { - /* - * If there's no field_sep, we still need - * to display initial ' '. - */ - if (!sep || !first) { - ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: " "); - advance_hpp(hpp, ret); - } else - first = false; - - if (color && fmt->color) - ret = fmt->color(hpp, he); - else - ret = fmt->entry(hpp, he); - - advance_hpp(hpp, ret); - } - - return hpp->buf - start; -} - int hist_entry__sort_snprintf(struct hist_entry *he, char *s, size_t size, struct hists *hists) { @@ -499,7 +271,7 @@ unsigned int hists__sort_list_width(struct hists *hists) if (i) ret += 2; - ret += fmt->width(&dummy_hpp); + ret += fmt->width(fmt, &dummy_hpp); } list_for_each_entry(se, &hist_entry__sort_list, list) diff --git a/tools/perf/ui/progress.c b/tools/perf/ui/progress.c index 3ec695607a4..a0f24c7115c 100644 --- a/tools/perf/ui/progress.c +++ b/tools/perf/ui/progress.c @@ -1,26 +1,38 @@ #include "../cache.h" #include "progress.h" -static void nop_progress_update(u64 curr __maybe_unused, - u64 total __maybe_unused, - const char *title __maybe_unused) +static void null_progress__update(struct ui_progress *p __maybe_unused) { } -static struct ui_progress default_progress_fns = +static struct ui_progress_ops null_progress__ops = { - .update = nop_progress_update, + .update = null_progress__update, }; -struct ui_progress *progress_fns = &default_progress_fns; +struct ui_progress_ops *ui_progress__ops = &null_progress__ops; -void ui_progress__update(u64 curr, u64 total, const char *title) +void ui_progress__update(struct ui_progress *p, u64 adv) { - return progress_fns->update(curr, total, title); + p->curr += adv; + + if (p->curr >= p->next) { + p->next += p->step; + ui_progress__ops->update(p); + } +} + +void ui_progress__init(struct ui_progress *p, u64 total, const char *title) +{ + p->curr = 0; + p->next = p->step = total / 16; + p->total = total; + p->title = title; + } void ui_progress__finish(void) { - if (progress_fns->finish) - progress_fns->finish(); + if (ui_progress__ops->finish) + ui_progress__ops->finish(); } diff --git a/tools/perf/ui/progress.h b/tools/perf/ui/progress.h index 257cc224f9c..29ec8efffef 100644 --- a/tools/perf/ui/progress.h +++ b/tools/perf/ui/progress.h @@ -3,16 +3,21 @@ #include <../types.h> +void ui_progress__finish(void); + struct ui_progress { - void (*update)(u64, u64, const char *); - void (*finish)(void); + const char *title; + u64 curr, next, step, total; }; + +void ui_progress__init(struct ui_progress *p, u64 total, const char *title); +void ui_progress__update(struct ui_progress *p, u64 adv); -extern struct ui_progress *progress_fns; - -void ui_progress__init(void); +struct ui_progress_ops { + void (*update)(struct ui_progress *p); + void (*finish)(void); +}; -void ui_progress__update(u64 curr, u64 total, const char *title); -void ui_progress__finish(void); +extern struct ui_progress_ops *ui_progress__ops; #endif diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index ae6a789cb0f..5df5140a9f2 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -1,10 +1,64 @@ #include <pthread.h> +#include <dlfcn.h> #include "../util/cache.h" #include "../util/debug.h" #include "../util/hist.h" pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; +void *perf_gtk_handle; + +#ifdef HAVE_GTK2_SUPPORT +static int setup_gtk_browser(void) +{ + int (*perf_ui_init)(void); + + if (perf_gtk_handle) + return 0; + + perf_gtk_handle = dlopen(PERF_GTK_DSO, RTLD_LAZY); + if (perf_gtk_handle == NULL) { + char buf[PATH_MAX]; + scnprintf(buf, sizeof(buf), "%s/%s", LIBDIR, PERF_GTK_DSO); + perf_gtk_handle = dlopen(buf, RTLD_LAZY); + } + if (perf_gtk_handle == NULL) + return -1; + + perf_ui_init = dlsym(perf_gtk_handle, "perf_gtk__init"); + if (perf_ui_init == NULL) + goto out_close; + + if (perf_ui_init() == 0) + return 0; + +out_close: + dlclose(perf_gtk_handle); + return -1; +} + +static void exit_gtk_browser(bool wait_for_ok) +{ + void (*perf_ui_exit)(bool); + + if (perf_gtk_handle == NULL) + return; + + perf_ui_exit = dlsym(perf_gtk_handle, "perf_gtk__exit"); + if (perf_ui_exit == NULL) + goto out_close; + + perf_ui_exit(wait_for_ok); + +out_close: + dlclose(perf_gtk_handle); + + perf_gtk_handle = NULL; +} +#else +static inline int setup_gtk_browser(void) { return -1; } +static inline void exit_gtk_browser(bool wait_for_ok __maybe_unused) {} +#endif void setup_browser(bool fallback_to_pager) { @@ -17,8 +71,11 @@ void setup_browser(bool fallback_to_pager) switch (use_browser) { case 2: - if (perf_gtk__init() == 0) + if (setup_gtk_browser() == 0) break; + printf("GTK browser requested but could not find %s\n", + PERF_GTK_DSO); + sleep(1); /* fall through */ case 1: use_browser = 1; @@ -30,7 +87,6 @@ void setup_browser(bool fallback_to_pager) if (fallback_to_pager) setup_pager(); - perf_hpp__column_enable(PERF_HPP__OVERHEAD); perf_hpp__init(); break; } @@ -40,7 +96,7 @@ void exit_browser(bool wait_for_ok) { switch (use_browser) { case 2: - perf_gtk__exit(wait_for_ok); + exit_gtk_browser(wait_for_ok); break; case 1: diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index ae7a7543224..c244cb524ef 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -213,20 +213,19 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, return ret; } -static size_t __callchain__fprintf_flat(FILE *fp, - struct callchain_node *self, +static size_t __callchain__fprintf_flat(FILE *fp, struct callchain_node *node, u64 total_samples) { struct callchain_list *chain; size_t ret = 0; - if (!self) + if (!node) return 0; - ret += __callchain__fprintf_flat(fp, self->parent, total_samples); + ret += __callchain__fprintf_flat(fp, node->parent, total_samples); - list_for_each_entry(chain, &self->val, list) { + list_for_each_entry(chain, &node->val, list) { if (chain->ip >= PERF_CONTEXT_MAX) continue; if (chain->ms.sym) @@ -239,15 +238,14 @@ static size_t __callchain__fprintf_flat(FILE *fp, return ret; } -static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *self, +static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *tree, u64 total_samples) { size_t ret = 0; u32 entries_printed = 0; - struct rb_node *rb_node; struct callchain_node *chain; + struct rb_node *rb_node = rb_first(tree); - rb_node = rb_first(self); while (rb_node) { double percent; @@ -308,21 +306,60 @@ static size_t hist_entry__callchain_fprintf(struct hist_entry *he, return hist_entry_callchain__fprintf(he, total_period, left_margin, fp); } +static inline void advance_hpp(struct perf_hpp *hpp, int inc) +{ + hpp->buf += inc; + hpp->size -= inc; +} + +static int hist_entry__period_snprintf(struct perf_hpp *hpp, + struct hist_entry *he) +{ + const char *sep = symbol_conf.field_sep; + struct perf_hpp_fmt *fmt; + char *start = hpp->buf; + int ret; + bool first = true; + + if (symbol_conf.exclude_other && !he->parent) + return 0; + + perf_hpp__for_each_format(fmt) { + /* + * If there's no field_sep, we still need + * to display initial ' '. + */ + if (!sep || !first) { + ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: " "); + advance_hpp(hpp, ret); + } else + first = false; + + if (perf_hpp__use_color() && fmt->color) + ret = fmt->color(fmt, hpp, he); + else + ret = fmt->entry(fmt, hpp, he); + + advance_hpp(hpp, ret); + } + + return hpp->buf - start; +} + static int hist_entry__fprintf(struct hist_entry *he, size_t size, - struct hists *hists, FILE *fp) + struct hists *hists, + char *bf, size_t bfsz, FILE *fp) { - char bf[512]; int ret; struct perf_hpp hpp = { .buf = bf, .size = size, }; - bool color = !symbol_conf.field_sep; - if (size == 0 || size > sizeof(bf)) - size = hpp.size = sizeof(bf); + if (size == 0 || size > bfsz) + size = hpp.size = bfsz; - ret = hist_entry__period_snprintf(&hpp, he, color); + ret = hist_entry__period_snprintf(&hpp, he); hist_entry__sort_snprintf(he, bf + ret, size - ret, hists); ret = fprintf(fp, "%s\n", bf); @@ -351,6 +388,8 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, .ptr = hists_to_evsel(hists), }; bool first = true; + size_t linesz; + char *line = NULL; init_rem_hits(); @@ -365,7 +404,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, else first = false; - fmt->header(&dummy_hpp); + fmt->header(fmt, &dummy_hpp); fprintf(fp, "%s", bf); } @@ -410,7 +449,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, else first = false; - width = fmt->width(&dummy_hpp); + width = fmt->width(fmt, &dummy_hpp); for (i = 0; i < width; i++) fprintf(fp, "."); } @@ -438,6 +477,14 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, goto out; print_entries: + linesz = hists__sort_list_width(hists) + 3 + 1; + linesz += perf_hpp__color_overhead(); + line = malloc(linesz); + if (line == NULL) { + ret = -1; + goto out; + } + for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); float percent = h->stat.period * 100.0 / @@ -449,10 +496,10 @@ print_entries: if (percent < min_pcnt) continue; - ret += hist_entry__fprintf(h, max_cols, hists, fp); + ret += hist_entry__fprintf(h, max_cols, hists, line, linesz, fp); if (max_rows && ++nr_rows >= max_rows) - goto out; + break; if (h->ms.map == NULL && verbose > 1) { __map_groups__fprintf_maps(&h->thread->mg, @@ -460,6 +507,8 @@ print_entries: fprintf(fp, "%.10s end\n", graph_dotted_line); } } + + free(line); out: free(rem_sq_bracket); diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c index 6c2184d53cb..3e2d936d744 100644 --- a/tools/perf/ui/tui/progress.c +++ b/tools/perf/ui/tui/progress.c @@ -2,9 +2,10 @@ #include "../progress.h" #include "../libslang.h" #include "../ui.h" +#include "tui.h" #include "../browser.h" -static void tui_progress__update(u64 curr, u64 total, const char *title) +static void tui_progress__update(struct ui_progress *p) { int bar, y; /* @@ -14,7 +15,7 @@ static void tui_progress__update(u64 curr, u64 total, const char *title) if (use_browser <= 0) return; - if (total == 0) + if (p->total == 0) return; ui__refresh_dimensions(true); @@ -23,20 +24,20 @@ static void tui_progress__update(u64 curr, u64 total, const char *title) SLsmg_set_color(0); SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols); SLsmg_gotorc(y++, 1); - SLsmg_write_string((char *)title); + SLsmg_write_string((char *)p->title); SLsmg_set_color(HE_COLORSET_SELECTED); - bar = ((SLtt_Screen_Cols - 2) * curr) / total; + bar = ((SLtt_Screen_Cols - 2) * p->curr) / p->total; SLsmg_fill_region(y, 1, 1, bar, ' '); SLsmg_refresh(); pthread_mutex_unlock(&ui__lock); } -static struct ui_progress tui_progress_fns = +static struct ui_progress_ops tui_progress__ops = { .update = tui_progress__update, }; -void ui_progress__init(void) +void tui_progress__init(void) { - progress_fns = &tui_progress_fns; + ui_progress__ops = &tui_progress__ops; } diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index b9401482d11..2f612562978 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -9,6 +9,7 @@ #include "../util.h" #include "../libslang.h" #include "../keysyms.h" +#include "tui.h" static volatile int ui__need_resize; @@ -119,7 +120,7 @@ int ui__init(void) ui_helpline__init(); ui_browser__init(); - ui_progress__init(); + tui_progress__init(); signal(SIGSEGV, ui__signal); signal(SIGFPE, ui__signal); diff --git a/tools/perf/ui/tui/tui.h b/tools/perf/ui/tui/tui.h new file mode 100644 index 00000000000..18961c7b6ec --- /dev/null +++ b/tools/perf/ui/tui/tui.h @@ -0,0 +1,6 @@ +#ifndef _PERF_TUI_H_ +#define _PERF_TUI_H_ 1 + +void tui_progress__init(void); + +#endif /* _PERF_TUI_H_ */ diff --git a/tools/perf/ui/ui.h b/tools/perf/ui/ui.h index 70cb0d4eb8a..ab88383f8be 100644 --- a/tools/perf/ui/ui.h +++ b/tools/perf/ui/ui.h @@ -6,13 +6,14 @@ #include <linux/compiler.h> extern pthread_mutex_t ui__lock; +extern void *perf_gtk_handle; extern int use_browser; void setup_browser(bool fallback_to_pager); void exit_browser(bool wait_for_ok); -#ifdef SLANG_SUPPORT +#ifdef HAVE_SLANG_SUPPORT int ui__init(void); void ui__exit(bool wait_for_ok); #else @@ -23,17 +24,6 @@ static inline int ui__init(void) static inline void ui__exit(bool wait_for_ok __maybe_unused) {} #endif -#ifdef GTK2_SUPPORT -int perf_gtk__init(void); -void perf_gtk__exit(bool wait_for_ok); -#else -static inline int perf_gtk__init(void) -{ - return -1; -} -static inline void perf_gtk__exit(bool wait_for_ok __maybe_unused) {} -#endif - void ui__refresh_dimensions(bool force); #endif /* _PERF_UI_H_ */ diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN index 15a77b7c0e3..39f17507578 100755 --- a/tools/perf/util/PERF-VERSION-GEN +++ b/tools/perf/util/PERF-VERSION-GEN @@ -19,6 +19,9 @@ if test -d ../../.git -o -f ../../.git then TAG=$(git describe --abbrev=0 --match "v[0-9].[0-9]*" 2>/dev/null ) CID=$(git log -1 --abbrev=4 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID" +elif test -f ../../PERF-VERSION-FILE +then + TAG=$(cut -d' ' -f3 ../../PERF-VERSION-FILE | sed -e 's/\"//g') fi if test -z "$TAG" then @@ -40,7 +43,7 @@ else VC=unset fi test "$VN" = "$VC" || { - echo >&2 "PERF_VERSION = $VN" + echo >&2 " PERF_VERSION = $VN" echo "#define PERF_VERSION \"$VN\"" >$GVF } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index d102716c43a..cf6242c92ee 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -110,10 +110,10 @@ static int jump__parse(struct ins_operands *ops) { const char *s = strchr(ops->raw, '+'); - ops->target.addr = strtoll(ops->raw, NULL, 16); + ops->target.addr = strtoull(ops->raw, NULL, 16); if (s++ != NULL) - ops->target.offset = strtoll(s, NULL, 16); + ops->target.offset = strtoull(s, NULL, 16); else ops->target.offset = UINT64_MAX; @@ -809,7 +809,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, end = map__rip_2objdump(map, sym->end); offset = line_ip - start; - if (offset < 0 || (u64)line_ip > end) + if ((u64)line_ip < start || (u64)line_ip > end) offset = -1; else parsed_line = tmp2 + 1; @@ -821,11 +821,51 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, if (dl == NULL) return -1; + if (dl->ops.target.offset == UINT64_MAX) + dl->ops.target.offset = dl->ops.target.addr - + map__rip_2objdump(map, sym->start); + + /* kcore has no symbols, so add the call target name */ + if (dl->ins && ins__is_call(dl->ins) && !dl->ops.target.name) { + struct addr_map_symbol target = { + .map = map, + .addr = dl->ops.target.addr, + }; + + if (!map_groups__find_ams(&target, NULL) && + target.sym->start == target.al_addr) + dl->ops.target.name = strdup(target.sym->name); + } + disasm__add(¬es->src->source, dl); return 0; } +static void delete_last_nop(struct symbol *sym) +{ + struct annotation *notes = symbol__annotation(sym); + struct list_head *list = ¬es->src->source; + struct disasm_line *dl; + + while (!list_empty(list)) { + dl = list_entry(list->prev, struct disasm_line, node); + + if (dl->ins && dl->ins->ops) { + if (dl->ins->ops != &nop_ops) + return; + } else { + if (!strstr(dl->line, " nop ") && + !strstr(dl->line, " nopl ") && + !strstr(dl->line, " nopw ")) + return; + } + + list_del(&dl->node); + disasm_line__free(dl); + } +} + int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) { struct dso *dso = map->dso; @@ -835,6 +875,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) FILE *file; int err = 0; char symfs_filename[PATH_MAX]; + struct kcore_extract kce; + bool delete_extract = false; if (filename) { snprintf(symfs_filename, sizeof(symfs_filename), "%s%s", @@ -864,7 +906,8 @@ fallback: free_filename = false; } - if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) { + if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && + !dso__is_kcore(dso)) { char bf[BUILD_ID_SIZE * 2 + 16] = " with build id "; char *build_id_msg = NULL; @@ -895,10 +938,27 @@ fallback: pr_debug("annotating [%p] %30s : [%p] %30s\n", dso, dso->long_name, sym, sym->name); + if (dso__is_kcore(dso)) { + kce.kcore_filename = symfs_filename; + kce.addr = map__rip_2objdump(map, sym->start); + kce.offs = sym->start; + kce.len = sym->end + 1 - sym->start; + if (!kcore_extract__create(&kce)) { + delete_extract = true; + strlcpy(symfs_filename, kce.extract_filename, + sizeof(symfs_filename)); + if (free_filename) { + free(filename); + free_filename = false; + } + filename = symfs_filename; + } + } + snprintf(command, sizeof(command), "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -d %s %s -C %s|grep -v %s|expand", + " -d %s %s -C %s 2>/dev/null|grep -v %s|expand", objdump_path ? objdump_path : "objdump", disassembler_style ? "-M " : "", disassembler_style ? disassembler_style : "", @@ -918,8 +978,17 @@ fallback: if (symbol__parse_objdump_line(sym, map, file, privsize) < 0) break; + /* + * kallsyms does not have symbol sizes so there may a nop at the end. + * Remove it. + */ + if (dso__is_kcore(dso)) + delete_last_nop(sym); + pclose(file); out_free_filename: + if (delete_extract) + kcore_extract__delete(&kce); if (free_filename) free(filename); return err; @@ -1018,7 +1087,7 @@ static void symbol__free_source_line(struct symbol *sym, int len) (sizeof(src_line->p) * (src_line->nr_pcnt - 1)); for (i = 0; i < len; i++) { - free(src_line->path); + free_srcline(src_line->path); src_line = (void *)src_line + sizeof_src_line; } @@ -1029,13 +1098,11 @@ static void symbol__free_source_line(struct symbol *sym, int len) /* Get the filename:line for the colored entries */ static int symbol__get_source_line(struct symbol *sym, struct map *map, struct perf_evsel *evsel, - struct rb_root *root, int len, - const char *filename) + struct rb_root *root, int len) { u64 start; int i, k; int evidx = evsel->idx; - char cmd[PATH_MAX * 2]; struct source_line *src_line; struct annotation *notes = symbol__annotation(sym); struct sym_hist *h = annotation__histogram(notes, evidx); @@ -1063,10 +1130,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, start = map__rip_2objdump(map, sym->start); for (i = 0; i < len; i++) { - char *path = NULL; - size_t line_len; u64 offset; - FILE *fp; double percent_max = 0.0; src_line->nr_pcnt = nr_pcnt; @@ -1083,23 +1147,9 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, goto next; offset = start + i; - sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset); - fp = popen(cmd, "r"); - if (!fp) - goto next; - - if (getline(&path, &line_len, fp) < 0 || !line_len) - goto next_close; - - src_line->path = malloc(sizeof(char) * line_len + 1); - if (!src_line->path) - goto next_close; - - strcpy(src_line->path, path); + src_line->path = get_srcline(map->dso, offset); insert_source_line(&tmp_root, src_line); - next_close: - pclose(fp); next: src_line = (void *)src_line + sizeof_src_line; } @@ -1140,7 +1190,7 @@ static void print_summary(struct rb_root *root, const char *filename) path = src_line->path; color = get_percent_color(percent_max); - color_fprintf(stdout, color, " %s", path); + color_fprintf(stdout, color, " %s\n", path); node = rb_next(node); } @@ -1304,7 +1354,6 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, bool full_paths, int min_pcnt, int max_lines) { struct dso *dso = map->dso; - const char *filename = dso->long_name; struct rb_root source_line = RB_ROOT; u64 len; @@ -1314,9 +1363,8 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, len = symbol__size(sym); if (print_lines) { - symbol__get_source_line(sym, map, evsel, &source_line, - len, filename); - print_summary(&source_line, filename); + symbol__get_source_line(sym, map, evsel, &source_line, len); + print_summary(&source_line, dso->long_name); } symbol__annotate_printf(sym, map, evsel, full_paths, diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index af755156d27..834b7b57b78 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -150,7 +150,7 @@ 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); -#ifdef SLANG_SUPPORT +#ifdef HAVE_SLANG_SUPPORT int symbol__tui_annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, struct hist_browser_timer *hbt); @@ -165,30 +165,6 @@ static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, } #endif -#ifdef GTK2_SUPPORT -int symbol__gtk_annotate(struct symbol *sym, struct map *map, - struct perf_evsel *evsel, - struct hist_browser_timer *hbt); - -static inline int hist_entry__gtk_annotate(struct hist_entry *he, - struct perf_evsel *evsel, - struct hist_browser_timer *hbt) -{ - return symbol__gtk_annotate(he->ms.sym, he->ms.map, evsel, hbt); -} - -void perf_gtk__show_annotations(void); -#else -static inline int hist_entry__gtk_annotate(struct hist_entry *he __maybe_unused, - struct perf_evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused) -{ - return 0; -} - -static inline void perf_gtk__show_annotations(void) {} -#endif - extern const char *disassembler_style; #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 5295625c0c0..a92770c98cc 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -18,13 +18,14 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct perf_evsel *evsel __maybe_unused, struct machine *machine) { struct addr_location al; u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread = machine__findnew_thread(machine, event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->pid); if (thread == NULL) { pr_err("problem processing %d event, skipping it.\n", @@ -33,7 +34,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, } thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - event->ip.ip, &al); + sample->ip, &al); if (al.map != NULL) al.map->dso->hit = 1; @@ -47,7 +48,9 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, __maybe_unused, struct machine *machine) { - struct thread *thread = machine__findnew_thread(machine, event->fork.tid); + struct thread *thread = machine__findnew_thread(machine, + event->fork.pid, + event->fork.tid); dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid, event->fork.ppid, event->fork.ptid); @@ -64,6 +67,7 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused, struct perf_tool build_id__mark_dso_hit_ops = { .sample = build_id__mark_dso_hit, .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, .fork = perf_event__process_fork, .exit = perf_event__exit_del_thread, .attr = perf_event__process_attr, @@ -85,14 +89,14 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf) return raw - build_id; } -char *dso__build_id_filename(struct dso *self, char *bf, size_t size) +char *dso__build_id_filename(struct dso *dso, char *bf, size_t size) { char build_id_hex[BUILD_ID_SIZE * 2 + 1]; - if (!self->has_build_id) + if (!dso->has_build_id) return NULL; - build_id__sprintf(self->build_id, sizeof(self->build_id), build_id_hex); + build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex); if (bf == NULL) { if (asprintf(&bf, "%s/.build-id/%.2s/%s", buildid_dir, build_id_hex, build_id_hex + 2) < 0) diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index a811f5c62e1..929f28a7c14 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -10,10 +10,9 @@ extern struct perf_tool build_id__mark_dso_hit_ops; struct dso; int build_id__sprintf(const u8 *build_id, int len, char *bf); -char *dso__build_id_filename(struct dso *self, char *bf, size_t size); +char *dso__build_id_filename(struct dso *dso, char *bf, size_t size); int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine); - #endif diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 26e36723987..7b176dd02e1 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -70,8 +70,7 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2 extern char *perf_pathdup(const char *fmt, ...) __attribute__((format (printf, 1, 2))); -#ifndef HAVE_STRLCPY +/* Matches the libc/libbsd function attribute so we declare this unconditionally: */ extern size_t strlcpy(char *dest, const char *src, size_t size); -#endif #endif /* __PERF_CACHE_H */ diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 42b6a632fe7..e3970e3eaac 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -15,25 +15,12 @@ #include <errno.h> #include <math.h> +#include "hist.h" #include "util.h" #include "callchain.h" __thread struct callchain_cursor callchain_cursor; -bool ip_callchain__valid(struct ip_callchain *chain, - const union perf_event *event) -{ - unsigned int chain_size = event->header.size; - chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event; - return chain->nr * sizeof(u64) <= chain_size; -} - -#define chain_for_each_child(child, parent) \ - list_for_each_entry(child, &parent->children, siblings) - -#define chain_for_each_child_safe(child, next, parent) \ - list_for_each_entry_safe(child, next, &parent->children, siblings) - static void rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, enum chain_mode mode) @@ -78,10 +65,16 @@ static void __sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node, u64 min_hit) { + struct rb_node *n; struct callchain_node *child; - chain_for_each_child(child, node) + n = rb_first(&node->rb_root_in); + while (n) { + child = rb_entry(n, struct callchain_node, rb_node_in); + n = rb_next(n); + __sort_chain_flat(rb_root, child, min_hit); + } if (node->hit && node->hit >= min_hit) rb_insert_callchain(rb_root, node, CHAIN_FLAT); @@ -101,11 +94,16 @@ sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root, static void __sort_chain_graph_abs(struct callchain_node *node, u64 min_hit) { + struct rb_node *n; struct callchain_node *child; node->rb_root = RB_ROOT; + n = rb_first(&node->rb_root_in); + + while (n) { + child = rb_entry(n, struct callchain_node, rb_node_in); + n = rb_next(n); - chain_for_each_child(child, node) { __sort_chain_graph_abs(child, min_hit); if (callchain_cumul_hits(child) >= min_hit) rb_insert_callchain(&node->rb_root, child, @@ -124,13 +122,18 @@ sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_root *chain_root, static void __sort_chain_graph_rel(struct callchain_node *node, double min_percent) { + struct rb_node *n; struct callchain_node *child; u64 min_hit; node->rb_root = RB_ROOT; min_hit = ceil(node->children_hit * min_percent); - chain_for_each_child(child, node) { + n = rb_first(&node->rb_root_in); + while (n) { + child = rb_entry(n, struct callchain_node, rb_node_in); + n = rb_next(n); + __sort_chain_graph_rel(child, min_percent); if (callchain_cumul_hits(child) >= min_hit) rb_insert_callchain(&node->rb_root, child, @@ -180,19 +183,26 @@ create_child(struct callchain_node *parent, bool inherit_children) return NULL; } new->parent = parent; - INIT_LIST_HEAD(&new->children); INIT_LIST_HEAD(&new->val); if (inherit_children) { - struct callchain_node *next; + struct rb_node *n; + struct callchain_node *child; + + new->rb_root_in = parent->rb_root_in; + parent->rb_root_in = RB_ROOT; - list_splice(&parent->children, &new->children); - INIT_LIST_HEAD(&parent->children); + n = rb_first(&new->rb_root_in); + while (n) { + child = rb_entry(n, struct callchain_node, rb_node_in); + child->parent = new; + n = rb_next(n); + } - chain_for_each_child(next, new) - next->parent = new; + /* make it the first child */ + rb_link_node(&new->rb_node_in, NULL, &parent->rb_root_in.rb_node); + rb_insert_color(&new->rb_node_in, &parent->rb_root_in); } - list_add_tail(&new->siblings, &parent->children); return new; } @@ -230,7 +240,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) } } -static void +static struct callchain_node * add_child(struct callchain_node *parent, struct callchain_cursor *cursor, u64 period) @@ -242,6 +252,19 @@ add_child(struct callchain_node *parent, new->children_hit = 0; new->hit = period; + return new; +} + +static s64 match_chain(struct callchain_cursor_node *node, + struct callchain_list *cnode) +{ + struct symbol *sym = node->sym; + + if (cnode->ms.sym && sym && + callchain_param.key == CCKEY_FUNCTION) + return cnode->ms.sym->start - sym->start; + else + return cnode->ip - node->ip; } /* @@ -279,9 +302,33 @@ split_add_child(struct callchain_node *parent, /* create a new child for the new branch if any */ if (idx_total < cursor->nr) { + struct callchain_node *first; + struct callchain_list *cnode; + struct callchain_cursor_node *node; + struct rb_node *p, **pp; + parent->hit = 0; - add_child(parent, cursor, period); parent->children_hit += period; + + node = callchain_cursor_current(cursor); + new = add_child(parent, cursor, period); + + /* + * This is second child since we moved parent's children + * to new (first) child above. + */ + p = parent->rb_root_in.rb_node; + first = rb_entry(p, struct callchain_node, rb_node_in); + cnode = list_first_entry(&first->val, struct callchain_list, + list); + + if (match_chain(node, cnode) < 0) + pp = &p->rb_left; + else + pp = &p->rb_right; + + rb_link_node(&new->rb_node_in, p, pp); + rb_insert_color(&new->rb_node_in, &parent->rb_root_in); } else { parent->hit = period; } @@ -298,16 +345,40 @@ append_chain_children(struct callchain_node *root, u64 period) { struct callchain_node *rnode; + struct callchain_cursor_node *node; + struct rb_node **p = &root->rb_root_in.rb_node; + struct rb_node *parent = NULL; + + node = callchain_cursor_current(cursor); + if (!node) + return; /* lookup in childrens */ - chain_for_each_child(rnode, root) { - unsigned int ret = append_chain(rnode, cursor, period); + while (*p) { + s64 ret; + struct callchain_list *cnode; - if (!ret) + parent = *p; + rnode = rb_entry(parent, struct callchain_node, rb_node_in); + cnode = list_first_entry(&rnode->val, struct callchain_list, + list); + + /* just check first entry */ + ret = match_chain(node, cnode); + if (ret == 0) { + append_chain(rnode, cursor, period); goto inc_children_hit; + } + + if (ret < 0) + p = &parent->rb_left; + else + p = &parent->rb_right; } /* nothing in children, add to the current node */ - add_child(root, cursor, period); + rnode = add_child(root, cursor, period); + rb_link_node(&rnode->rb_node_in, parent, p); + rb_insert_color(&rnode->rb_node_in, &root->rb_root_in); inc_children_hit: root->children_hit += period; @@ -327,31 +398,25 @@ append_chain(struct callchain_node *root, /* * Lookup in the current node * If we have a symbol, then compare the start to match - * anywhere inside a function. + * anywhere inside a function, unless function + * mode is disabled. */ list_for_each_entry(cnode, &root->val, list) { struct callchain_cursor_node *node; - struct symbol *sym; node = callchain_cursor_current(cursor); if (!node) break; - sym = node->sym; - - if (cnode->ms.sym && sym) { - if (cnode->ms.sym->start != sym->start) - break; - } else if (cnode->ip != node->ip) + if (match_chain(node, cnode) != 0) break; - if (!found) - found = true; + found = true; callchain_cursor_advance(cursor); } - /* matches not, relay on the parent */ + /* matches not, relay no the parent */ if (!found) { cursor->curr = curr_snap; cursor->pos = start; @@ -400,8 +465,9 @@ merge_chain_branch(struct callchain_cursor *cursor, struct callchain_node *dst, struct callchain_node *src) { struct callchain_cursor_node **old_last = cursor->last; - struct callchain_node *child, *next_child; + struct callchain_node *child; struct callchain_list *list, *next_list; + struct rb_node *n; int old_pos = cursor->nr; int err = 0; @@ -417,12 +483,16 @@ merge_chain_branch(struct callchain_cursor *cursor, append_chain_children(dst, cursor, src->hit); } - chain_for_each_child_safe(child, next_child, src) { + n = rb_first(&src->rb_root_in); + while (n) { + child = container_of(n, struct callchain_node, rb_node_in); + n = rb_next(n); + rb_erase(&child->rb_node_in, &src->rb_root_in); + err = merge_chain_branch(cursor, dst, child); if (err) break; - list_del(&child->siblings); free(child); } diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 3ee9f67d5af..4f7f989876e 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -21,11 +21,11 @@ enum chain_order { struct callchain_node { struct callchain_node *parent; - struct list_head siblings; - struct list_head children; struct list_head val; - struct rb_node rb_node; /* to sort nodes in an rbtree */ - struct rb_root rb_root; /* sorted tree of children */ + struct rb_node rb_node_in; /* to insert nodes in an rbtree */ + struct rb_node rb_node; /* to sort nodes in an output tree */ + struct rb_root rb_root_in; /* input tree of children */ + struct rb_root rb_root; /* sorted output tree of children */ unsigned int val_nr; u64 hit; u64 children_hit; @@ -41,12 +41,18 @@ struct callchain_param; typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *, u64, struct callchain_param *); +enum chain_key { + CCKEY_FUNCTION, + CCKEY_ADDRESS +}; + struct callchain_param { enum chain_mode mode; u32 print_limit; double min_percent; sort_chain_func_t sort; enum chain_order order; + enum chain_key key; }; struct callchain_list { @@ -80,13 +86,12 @@ extern __thread struct callchain_cursor callchain_cursor; static inline void callchain_init(struct callchain_root *root) { - INIT_LIST_HEAD(&root->node.siblings); - INIT_LIST_HEAD(&root->node.children); INIT_LIST_HEAD(&root->node.val); root->node.parent = NULL; root->node.hit = 0; root->node.children_hit = 0; + root->node.rb_root_in = RB_ROOT; root->max_depth = 0; } @@ -103,11 +108,6 @@ int callchain_append(struct callchain_root *root, int callchain_merge(struct callchain_cursor *cursor, struct callchain_root *dst, struct callchain_root *src); -struct ip_callchain; -union perf_event; - -bool ip_callchain__valid(struct ip_callchain *chain, - const union perf_event *event); /* * Initialize a cursor before adding entries inside, but keep * the previously allocated entries as a cache. @@ -146,6 +146,9 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor) struct option; +int record_parse_callchain(const char *arg, struct perf_record_opts *opts); int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); +int record_callchain_opt(const struct option *opt, const char *arg, int unset); + extern const char record_callchain_help[]; #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index 11e46da17bb..66e44a5019d 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -318,8 +318,15 @@ int percent_color_fprintf(FILE *fp, const char *fmt, double percent) return r; } -int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent) +int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...) { - const char *color = get_percent_color(percent); + va_list args; + double percent; + const char *color; + + va_start(args, fmt); + percent = va_arg(args, double); + va_end(args); + color = get_percent_color(percent); return color_snprintf(bf, size, color, fmt, percent); } diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index dea082b7960..fced3840e99 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -39,7 +39,7 @@ int color_fprintf(FILE *fp, const char *color, const char *fmt, ...); int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...); int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...); int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf); -int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent); +int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...); int percent_color_fprintf(FILE *fp, const char *fmt, double percent); const char *get_percent_color(double percent); diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c new file mode 100644 index 00000000000..ee0df0e24cd --- /dev/null +++ b/tools/perf/util/comm.c @@ -0,0 +1,121 @@ +#include "comm.h" +#include "util.h" +#include <stdlib.h> +#include <stdio.h> + +struct comm_str { + char *str; + struct rb_node rb_node; + int ref; +}; + +/* Should perhaps be moved to struct machine */ +static struct rb_root comm_str_root; + +static void comm_str__get(struct comm_str *cs) +{ + cs->ref++; +} + +static void comm_str__put(struct comm_str *cs) +{ + if (!--cs->ref) { + rb_erase(&cs->rb_node, &comm_str_root); + free(cs->str); + free(cs); + } +} + +static struct comm_str *comm_str__alloc(const char *str) +{ + struct comm_str *cs; + + cs = zalloc(sizeof(*cs)); + if (!cs) + return NULL; + + cs->str = strdup(str); + if (!cs->str) { + free(cs); + return NULL; + } + + return cs; +} + +static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct comm_str *iter, *new; + int cmp; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct comm_str, rb_node); + + cmp = strcmp(str, iter->str); + if (!cmp) + return iter; + + if (cmp < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + new = comm_str__alloc(str); + if (!new) + return NULL; + + rb_link_node(&new->rb_node, parent, p); + rb_insert_color(&new->rb_node, root); + + return new; +} + +struct comm *comm__new(const char *str, u64 timestamp) +{ + struct comm *comm = zalloc(sizeof(*comm)); + + if (!comm) + return NULL; + + comm->start = timestamp; + + comm->comm_str = comm_str__findnew(str, &comm_str_root); + if (!comm->comm_str) { + free(comm); + return NULL; + } + + comm_str__get(comm->comm_str); + + return comm; +} + +void comm__override(struct comm *comm, const char *str, u64 timestamp) +{ + struct comm_str *old = comm->comm_str; + + comm->comm_str = comm_str__findnew(str, &comm_str_root); + if (!comm->comm_str) { + comm->comm_str = old; + return; + } + + comm->start = timestamp; + comm_str__get(comm->comm_str); + comm_str__put(old); +} + +void comm__free(struct comm *comm) +{ + comm_str__put(comm->comm_str); + free(comm); +} + +const char *comm__str(const struct comm *comm) +{ + return comm->comm_str->str; +} diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h new file mode 100644 index 00000000000..7a86e565671 --- /dev/null +++ b/tools/perf/util/comm.h @@ -0,0 +1,21 @@ +#ifndef __PERF_COMM_H +#define __PERF_COMM_H + +#include "../perf.h" +#include <linux/rbtree.h> +#include <linux/list.h> + +struct comm_str; + +struct comm { + struct comm_str *comm_str; + u64 start; + struct list_head list; +}; + +void comm__free(struct comm *comm); +struct comm *comm__new(const char *str, u64 timestamp); +const char *comm__str(const struct comm *comm); +void comm__override(struct comm *comm, const char *str, u64 timestamp); + +#endif /* __PERF_COMM_H */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index beb8cf9f997..a9b48c42e81 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -1,5 +1,5 @@ #include "util.h" -#include "sysfs.h" +#include "fs.h" #include "../perf.h" #include "cpumap.h" #include <assert.h> @@ -216,7 +216,7 @@ int cpu_map__get_socket(struct cpu_map *map, int idx) cpu = map->map[idx]; - mnt = sysfs_find_mountpoint(); + mnt = sysfs__mountpoint(); if (!mnt) return -1; @@ -279,7 +279,7 @@ int cpu_map__get_core(struct cpu_map *map, int idx) cpu = map->map[idx]; - mnt = sysfs_find_mountpoint(); + mnt = sysfs__mountpoint(); if (!mnt) return -1; diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 9bed02e5fb3..b123bb9d6f5 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -41,7 +41,7 @@ static inline int cpu_map__nr(const struct cpu_map *map) return map ? map->nr : 1; } -static inline bool cpu_map__all(const struct cpu_map *map) +static inline bool cpu_map__empty(const struct cpu_map *map) { return map ? map->map[0] == -1 : true; } diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c new file mode 100644 index 00000000000..7d09faf85cf --- /dev/null +++ b/tools/perf/util/data.c @@ -0,0 +1,120 @@ +#include <linux/compiler.h> +#include <linux/kernel.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <string.h> + +#include "data.h" +#include "util.h" + +static bool check_pipe(struct perf_data_file *file) +{ + struct stat st; + bool is_pipe = false; + int fd = perf_data_file__is_read(file) ? + STDIN_FILENO : STDOUT_FILENO; + + if (!file->path) { + if (!fstat(fd, &st) && S_ISFIFO(st.st_mode)) + is_pipe = true; + } else { + if (!strcmp(file->path, "-")) + is_pipe = true; + } + + if (is_pipe) + file->fd = fd; + + return file->is_pipe = is_pipe; +} + +static int check_backup(struct perf_data_file *file) +{ + struct stat st; + + if (!stat(file->path, &st) && st.st_size) { + /* TODO check errors properly */ + char oldname[PATH_MAX]; + snprintf(oldname, sizeof(oldname), "%s.old", + file->path); + unlink(oldname); + rename(file->path, oldname); + } + + return 0; +} + +static int open_file_read(struct perf_data_file *file) +{ + struct stat st; + int fd; + + fd = open(file->path, O_RDONLY); + if (fd < 0) { + int err = errno; + + pr_err("failed to open %s: %s", file->path, strerror(err)); + if (err == ENOENT && !strcmp(file->path, "perf.data")) + pr_err(" (try 'perf record' first)"); + pr_err("\n"); + return -err; + } + + if (fstat(fd, &st) < 0) + goto out_close; + + if (!file->force && st.st_uid && (st.st_uid != geteuid())) { + pr_err("file %s not owned by current user or root\n", + file->path); + goto out_close; + } + + if (!st.st_size) { + pr_info("zero-sized file (%s), nothing to do!\n", + file->path); + goto out_close; + } + + file->size = st.st_size; + return fd; + + out_close: + close(fd); + return -1; +} + +static int open_file_write(struct perf_data_file *file) +{ + if (check_backup(file)) + return -1; + + return open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR); +} + +static int open_file(struct perf_data_file *file) +{ + int fd; + + fd = perf_data_file__is_read(file) ? + open_file_read(file) : open_file_write(file); + + file->fd = fd; + return fd < 0 ? -1 : 0; +} + +int perf_data_file__open(struct perf_data_file *file) +{ + if (check_pipe(file)) + return 0; + + if (!file->path) + file->path = "perf.data"; + + return open_file(file); +} + +void perf_data_file__close(struct perf_data_file *file) +{ + close(file->fd); +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h new file mode 100644 index 00000000000..8c2df80152a --- /dev/null +++ b/tools/perf/util/data.h @@ -0,0 +1,48 @@ +#ifndef __PERF_DATA_H +#define __PERF_DATA_H + +#include <stdbool.h> + +enum perf_data_mode { + PERF_DATA_MODE_WRITE, + PERF_DATA_MODE_READ, +}; + +struct perf_data_file { + const char *path; + int fd; + bool is_pipe; + bool force; + unsigned long size; + enum perf_data_mode mode; +}; + +static inline bool perf_data_file__is_read(struct perf_data_file *file) +{ + return file->mode == PERF_DATA_MODE_READ; +} + +static inline bool perf_data_file__is_write(struct perf_data_file *file) +{ + return file->mode == PERF_DATA_MODE_WRITE; +} + +static inline int perf_data_file__is_pipe(struct perf_data_file *file) +{ + return file->is_pipe; +} + +static inline int perf_data_file__fd(struct perf_data_file *file) +{ + return file->fd; +} + +static inline unsigned long perf_data_file__size(struct perf_data_file *file) +{ + return file->size; +} + +int perf_data_file__open(struct perf_data_file *file); +void perf_data_file__close(struct perf_data_file *file); + +#endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index c4374f07603..af4c687cc49 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -7,19 +7,20 @@ char dso__symtab_origin(const struct dso *dso) { static const char origin[] = { - [DSO_BINARY_TYPE__KALLSYMS] = 'k', - [DSO_BINARY_TYPE__VMLINUX] = 'v', - [DSO_BINARY_TYPE__JAVA_JIT] = 'j', - [DSO_BINARY_TYPE__DEBUGLINK] = 'l', - [DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B', - [DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f', - [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u', - [DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b', - [DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd', - [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K', - [DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g', - [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G', - [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V', + [DSO_BINARY_TYPE__KALLSYMS] = 'k', + [DSO_BINARY_TYPE__VMLINUX] = 'v', + [DSO_BINARY_TYPE__JAVA_JIT] = 'j', + [DSO_BINARY_TYPE__DEBUGLINK] = 'l', + [DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B', + [DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f', + [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u', + [DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO] = 'o', + [DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b', + [DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd', + [DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K', + [DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g', + [DSO_BINARY_TYPE__GUEST_KMODULE] = 'G', + [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V', }; if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND) @@ -64,6 +65,28 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, symbol_conf.symfs, dso->long_name); break; + case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: + { + char *last_slash; + size_t len; + size_t dir_size; + + last_slash = dso->long_name + dso->long_name_len; + while (last_slash != dso->long_name && *last_slash != '/') + last_slash--; + + len = scnprintf(file, size, "%s", symbol_conf.symfs); + dir_size = last_slash - dso->long_name + 2; + if (dir_size > (size - len)) { + ret = -1; + break; + } + len += scnprintf(file + len, dir_size, "%s", dso->long_name); + len += scnprintf(file + len , size - len, ".debug%s", + last_slash); + break; + } + case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: if (!dso->has_build_id) { ret = -1; @@ -78,6 +101,8 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, symbol_conf.symfs, build_id_hex, build_id_hex + 2); break; + case DSO_BINARY_TYPE__VMLINUX: + case DSO_BINARY_TYPE__GUEST_VMLINUX: case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: snprintf(file, size, "%s%s", symbol_conf.symfs, dso->long_name); @@ -93,11 +118,14 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type, dso->long_name); break; + case DSO_BINARY_TYPE__KCORE: + case DSO_BINARY_TYPE__GUEST_KCORE: + snprintf(file, size, "%s", dso->long_name); + break; + default: case DSO_BINARY_TYPE__KALLSYMS: - case DSO_BINARY_TYPE__VMLINUX: case DSO_BINARY_TYPE__GUEST_KALLSYMS: - case DSO_BINARY_TYPE__GUEST_VMLINUX: case DSO_BINARY_TYPE__JAVA_JIT: case DSO_BINARY_TYPE__NOT_FOUND: ret = -1; @@ -419,8 +447,10 @@ struct dso *dso__new(const char *name) dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND; dso->data_type = DSO_BINARY_TYPE__NOT_FOUND; dso->loaded = 0; + dso->rel = 0; dso->sorted_by_name = 0; dso->has_build_id = 0; + dso->has_srcline = 1; dso->kernel = DSO_TYPE_USER; dso->needs_swap = DSO_SWAP__UNSET; INIT_LIST_HEAD(&dso->node); diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index d51aaf272c6..9ac666abbe7 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -3,8 +3,10 @@ #include <linux/types.h> #include <linux/rbtree.h> +#include <stdbool.h> #include "types.h" #include "map.h" +#include "build-id.h" enum dso_binary_type { DSO_BINARY_TYPE__KALLSYMS = 0, @@ -20,6 +22,9 @@ enum dso_binary_type { DSO_BINARY_TYPE__SYSTEM_PATH_DSO, DSO_BINARY_TYPE__GUEST_KMODULE, DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + DSO_BINARY_TYPE__KCORE, + DSO_BINARY_TYPE__GUEST_KCORE, + DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, DSO_BINARY_TYPE__NOT_FOUND, }; @@ -78,12 +83,14 @@ struct dso { enum dso_binary_type data_type; u8 adjust_symbols:1; u8 has_build_id:1; + u8 has_srcline:1; u8 hit:1; u8 annotate_warned:1; u8 sname_alloc:1; u8 lname_alloc:1; u8 sorted_by_name; u8 loaded; + u8 rel; u8 build_id[BUILD_ID_SIZE]; const char *short_name; char *long_name; @@ -146,4 +153,17 @@ 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); + +static inline bool dso__is_vmlinux(struct dso *dso) +{ + return dso->data_type == DSO_BINARY_TYPE__VMLINUX || + dso->data_type == DSO_BINARY_TYPE__GUEST_VMLINUX; +} + +static inline bool dso__is_kcore(struct dso *dso) +{ + return dso->data_type == DSO_BINARY_TYPE__KCORE || + dso->data_type == DSO_BINARY_TYPE__GUEST_KCORE; +} + #endif /* __PERF_DSO */ diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 3e5f5430a28..7defd77105d 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -263,6 +263,21 @@ bool die_is_signed_type(Dwarf_Die *tp_die) } /** + * die_is_func_def - Ensure that this DIE is a subprogram and definition + * @dw_die: a DIE + * + * Ensure that this DIE is a subprogram and NOT a declaration. This + * returns true if @dw_die is a function definition. + **/ +bool die_is_func_def(Dwarf_Die *dw_die) +{ + Dwarf_Attribute attr; + + return (dwarf_tag(dw_die) == DW_TAG_subprogram && + dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL); +} + +/** * die_get_data_member_location - Get the data-member offset * @mb_die: a DIE of a member of a data structure * @offs: The offset of the member in the data structure @@ -392,6 +407,10 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data) { struct __addr_die_search_param *ad = data; + /* + * Since a declaration entry doesn't has given pc, this always returns + * function definition entry. + */ if (dwarf_tag(fn_die) == DW_TAG_subprogram && dwarf_haspc(fn_die, ad->addr)) { memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die)); @@ -407,7 +426,7 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data) * @die_mem: a buffer for result DIE * * Search a non-inlined function DIE which includes @addr. Stores the - * DIE to @die_mem and returns it if found. Returns NULl if failed. + * DIE to @die_mem and returns it if found. Returns NULL if failed. */ Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr, Dwarf_Die *die_mem) @@ -435,15 +454,32 @@ static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data) } /** + * die_find_top_inlinefunc - Search the top inlined function at given address + * @sp_die: a subprogram DIE which including @addr + * @addr: target address + * @die_mem: a buffer for result DIE + * + * Search an inlined function DIE which includes @addr. Stores the + * DIE to @die_mem and returns it if found. Returns NULL if failed. + * Even if several inlined functions are expanded recursively, this + * doesn't trace it down, and returns the topmost one. + */ +Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, + Dwarf_Die *die_mem) +{ + return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem); +} + +/** * die_find_inlinefunc - Search an inlined function at given address - * @cu_die: a CU DIE which including @addr + * @sp_die: a subprogram DIE which including @addr * @addr: target address * @die_mem: a buffer for result DIE * * Search an inlined function DIE which includes @addr. Stores the - * DIE to @die_mem and returns it if found. Returns NULl if failed. + * DIE to @die_mem and returns it if found. Returns NULL if failed. * If several inlined functions are expanded recursively, this trace - * it and returns deepest one. + * it down and returns deepest one. */ Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, Dwarf_Die *die_mem) diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index 6ce1717784b..b4fe90c6cb2 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -38,6 +38,9 @@ extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr, extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, int (*callback)(Dwarf_Die *, void *), void *data); +/* Ensure that this DIE is a subprogram and definition (not declaration) */ +extern bool die_is_func_def(Dwarf_Die *dw_die); + /* Compare diename and tname */ extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname); @@ -76,7 +79,11 @@ extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die, extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr, Dwarf_Die *die_mem); -/* Search an inlined function including given address */ +/* Search the top inlined function including given address */ +extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, + Dwarf_Die *die_mem); + +/* Search the deepest inlined function including given address */ extern Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, Dwarf_Die *die_mem); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 5cd13d768ce..ec9ae1114ed 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -11,6 +11,7 @@ static const char *perf_event__names[] = { [0] = "TOTAL", [PERF_RECORD_MMAP] = "MMAP", + [PERF_RECORD_MMAP2] = "MMAP2", [PERF_RECORD_LOST] = "LOST", [PERF_RECORD_COMM] = "COMM", [PERF_RECORD_EXIT] = "EXIT", @@ -198,6 +199,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, char execname[PATH_MAX]; char anonstr[] = "//anon"; size_t size; + ssize_t n; if (fgets(bf, sizeof(bf), fp) == NULL) break; @@ -206,9 +208,13 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, ""); /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n", + n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n", &event->mmap.start, &event->mmap.len, prot, - &event->mmap.pgoff, execname); + &event->mmap.pgoff, + execname); + + if (n != 5) + continue; if (prot[2] != 'x') continue; @@ -221,7 +227,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, size = PERF_ALIGN(size, sizeof(u64)); event->mmap.len -= event->mmap.start; event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size)); + (sizeof(event->mmap.filename) - size)); memset(event->mmap.filename + size, 0, machine->id_hdr_size); event->mmap.header.size += machine->id_hdr_size; event->mmap.pid = tgid; @@ -506,18 +512,18 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) int perf_event__process_comm(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_comm_event(machine, event); + return machine__process_comm_event(machine, event, sample); } int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_lost_event(machine, event); + return machine__process_lost_event(machine, event, sample); } size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) @@ -527,12 +533,31 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp) event->mmap.len, event->mmap.pgoff, event->mmap.filename); } +size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) +{ + return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 + " %02x:%02x %"PRIu64" %"PRIu64"]: %s\n", + event->mmap2.pid, event->mmap2.tid, event->mmap2.start, + event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj, + event->mmap2.min, event->mmap2.ino, + event->mmap2.ino_generation, + event->mmap2.filename); +} + int perf_event__process_mmap(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_mmap_event(machine, event); + return machine__process_mmap_event(machine, event, sample); +} + +int perf_event__process_mmap2(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + return machine__process_mmap2_event(machine, event, sample); } size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) @@ -544,18 +569,18 @@ size_t perf_event__fprintf_task(union perf_event *event, FILE *fp) int perf_event__process_fork(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_fork_event(machine, event); + return machine__process_fork_event(machine, event, sample); } int perf_event__process_exit(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_exit_event(machine, event); + return machine__process_exit_event(machine, event, sample); } size_t perf_event__fprintf(union perf_event *event, FILE *fp) @@ -574,6 +599,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) case PERF_RECORD_MMAP: ret += perf_event__fprintf_mmap(event, fp); break; + case PERF_RECORD_MMAP2: + ret += perf_event__fprintf_mmap2(event, fp); + break; default: ret += fprintf(fp, "\n"); } @@ -583,20 +611,21 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) int perf_event__process(struct perf_tool *tool __maybe_unused, union perf_event *event, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct machine *machine) { - return machine__process_event(machine, event); + return machine__process_event(machine, event, sample); } -void thread__find_addr_map(struct thread *self, +void thread__find_addr_map(struct thread *thread, struct machine *machine, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al) { - struct map_groups *mg = &self->mg; + struct map_groups *mg = &thread->mg; + bool load_map = false; - al->thread = self; + al->thread = thread; al->addr = addr; al->cpumode = cpumode; al->filtered = false; @@ -609,11 +638,13 @@ void thread__find_addr_map(struct thread *self, if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { al->level = 'k'; mg = &machine->kmaps; + load_map = true; } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) { al->level = '.'; } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) { al->level = 'g'; mg = &machine->kmaps; + load_map = true; } else { /* * 'u' means guest os user space. @@ -654,18 +685,25 @@ try_again: mg = &machine->kmaps; goto try_again; } - } else + } else { + /* + * Kernel maps might be changed when loading symbols so loading + * must be done prior to using kernel maps. + */ + if (load_map) + map__load(al->map, machine->symbol_filter); al->addr = al->map->map_ip(al->map, al->addr); + } } void thread__find_addr_location(struct thread *thread, struct machine *machine, u8 cpumode, enum map_type type, u64 addr, - struct addr_location *al, - symbol_filter_t filter) + struct addr_location *al) { thread__find_addr_map(thread, machine, cpumode, type, addr, al); if (al->map != NULL) - al->sym = map__find_symbol(al->map, al->addr, filter); + al->sym = map__find_symbol(al->map, al->addr, + machine->symbol_filter); else al->sym = NULL; } @@ -673,20 +711,20 @@ void thread__find_addr_location(struct thread *thread, struct machine *machine, int perf_event__preprocess_sample(const union perf_event *event, struct machine *machine, struct addr_location *al, - struct perf_sample *sample, - symbol_filter_t filter) + struct perf_sample *sample) { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread = machine__findnew_thread(machine, event->ip.pid); + struct thread *thread = machine__findnew_thread(machine, sample->pid, + sample->pid); if (thread == NULL) return -1; if (symbol_conf.comm_list && - !strlist__has_entry(symbol_conf.comm_list, thread->comm)) + !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread))) goto out_filtered; - dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); + dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid); /* * Have we already created the kernel maps for this machine? * @@ -699,7 +737,7 @@ int perf_event__preprocess_sample(const union perf_event *event, machine__create_kernel_maps(machine); thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, - event->ip.ip, al); + sample->ip, al); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : "<not found>"); @@ -717,7 +755,8 @@ int perf_event__preprocess_sample(const union perf_event *event, dso->long_name))))) goto out_filtered; - al->sym = map__find_symbol(al->map, al->addr, filter); + al->sym = map__find_symbol(al->map, al->addr, + machine->symbol_filter); } if (symbol_conf.sym_list && diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 181389535c0..f8d70f3003a 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -8,22 +8,25 @@ #include "map.h" #include "build-id.h" -/* - * PERF_SAMPLE_IP | PERF_SAMPLE_TID | * - */ -struct ip_event { +struct mmap_event { struct perf_event_header header; - u64 ip; u32 pid, tid; - unsigned char __more_data[]; + u64 start; + u64 len; + u64 pgoff; + char filename[PATH_MAX]; }; -struct mmap_event { +struct mmap2_event { struct perf_event_header header; u32 pid, tid; u64 start; u64 len; u64 pgoff; + u32 maj; + u32 min; + u64 ino; + u64 ino_generation; char filename[PATH_MAX]; }; @@ -58,12 +61,22 @@ struct read_event { u64 id; }; +struct throttle_event { + struct perf_event_header header; + u64 time; + u64 id; + u64 stream_id; +}; #define PERF_SAMPLE_MASK \ (PERF_SAMPLE_IP | PERF_SAMPLE_TID | \ PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR | \ PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID | \ - PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD) + PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD | \ + PERF_SAMPLE_IDENTIFIER) + +/* perf sample has 16 bits size limit */ +#define PERF_SAMPLE_MAX_SIZE (1 << 16) struct sample_event { struct perf_event_header header; @@ -71,6 +84,7 @@ struct sample_event { }; struct regs_dump { + u64 abi; u64 *regs; }; @@ -80,6 +94,23 @@ struct stack_dump { char *data; }; +struct sample_read_value { + u64 value; + u64 id; +}; + +struct sample_read { + u64 time_enabled; + u64 time_running; + union { + struct { + u64 nr; + struct sample_read_value *values; + } group; + struct sample_read_value one; + }; +}; + struct perf_sample { u64 ip; u32 pid, tid; @@ -89,6 +120,7 @@ struct perf_sample { u64 stream_id; u64 period; u64 weight; + u64 transaction; u32 cpu; u32 raw_size; u64 data_src; @@ -97,6 +129,7 @@ struct perf_sample { struct branch_stack *branch_stack; struct regs_dump user_regs; struct stack_dump user_stack; + struct sample_read read; }; #define PERF_MEM_DATA_SRC_NONE \ @@ -116,7 +149,7 @@ struct build_id_event { enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_USER_TYPE_START = 64, PERF_RECORD_HEADER_ATTR = 64, - PERF_RECORD_HEADER_EVENT_TYPE = 65, + PERF_RECORD_HEADER_EVENT_TYPE = 65, /* depreceated */ PERF_RECORD_HEADER_TRACING_DATA = 66, PERF_RECORD_HEADER_BUILD_ID = 67, PERF_RECORD_FINISHED_ROUND = 68, @@ -148,12 +181,13 @@ struct tracing_data_event { union perf_event { struct perf_event_header header; - struct ip_event ip; struct mmap_event mmap; + struct mmap2_event mmap2; struct comm_event comm; struct fork_event fork; struct lost_event lost; struct read_event read; + struct throttle_event throttle; struct sample_event sample; struct attr_event attr; struct event_type_event event_type; @@ -199,6 +233,10 @@ int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_mmap2(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_event__process_fork(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -213,20 +251,24 @@ int perf_event__process(struct perf_tool *tool, struct machine *machine); struct addr_location; -int perf_event__preprocess_sample(const union perf_event *self, + +int perf_event__preprocess_sample(const union perf_event *event, struct machine *machine, struct addr_location *al, - struct perf_sample *sample, - symbol_filter_t filter); + struct perf_sample *sample); const char *perf_event__name(unsigned int id); +size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, + u64 sample_regs_user, u64 read_format); int perf_event__synthesize_sample(union perf_event *event, u64 type, + u64 sample_regs_user, u64 read_format, const struct perf_sample *sample, bool swapped); 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); size_t perf_event__fprintf_task(union perf_event *event, FILE *fp); size_t perf_event__fprintf(union perf_event *event, FILE *fp); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 8065ce8fa9a..b939221efd8 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -14,9 +14,11 @@ #include "target.h" #include "evlist.h" #include "evsel.h" +#include "debug.h" #include <unistd.h> #include "parse-events.h" +#include "parse-options.h" #include <sys/mman.h> @@ -48,26 +50,41 @@ struct perf_evlist *perf_evlist__new(void) return evlist; } -void perf_evlist__config(struct perf_evlist *evlist, - struct perf_record_opts *opts) +struct perf_evlist *perf_evlist__new_default(void) { - struct perf_evsel *evsel; - /* - * Set the evsel leader links before we configure attributes, - * since some might depend on this info. - */ - if (opts->group) - perf_evlist__set_leader(evlist); + struct perf_evlist *evlist = perf_evlist__new(); - if (evlist->cpus->map[0] < 0) - opts->no_inherit = true; + if (evlist && perf_evlist__add_default(evlist)) { + perf_evlist__delete(evlist); + evlist = NULL; + } - list_for_each_entry(evsel, &evlist->entries, node) { - perf_evsel__config(evsel, opts); + return evlist; +} - if (evlist->nr_entries > 1) - perf_evsel__set_sample_id(evsel); - } +/** + * perf_evlist__set_id_pos - set the positions of event ids. + * @evlist: selected event list + * + * Events with compatible sample types all have the same id_pos + * and is_pos. For convenience, put a copy on evlist. + */ +void perf_evlist__set_id_pos(struct perf_evlist *evlist) +{ + struct perf_evsel *first = perf_evlist__first(evlist); + + evlist->id_pos = first->id_pos; + evlist->is_pos = first->is_pos; +} + +static void perf_evlist__update_id_pos(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) + perf_evsel__calc_id_pos(evsel); + + perf_evlist__set_id_pos(evlist); } static void perf_evlist__purge(struct perf_evlist *evlist) @@ -100,15 +117,20 @@ void perf_evlist__delete(struct perf_evlist *evlist) void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) { list_add_tail(&entry->node, &evlist->entries); - ++evlist->nr_entries; + if (!evlist->nr_entries++) + perf_evlist__set_id_pos(evlist); } void perf_evlist__splice_list_tail(struct perf_evlist *evlist, struct list_head *list, int nr_entries) { + bool set_id_pos = !evlist->nr_entries; + list_splice_tail(list, &evlist->entries); evlist->nr_entries += nr_entries; + if (set_id_pos) + perf_evlist__set_id_pos(evlist); } void __perf_evlist__set_leader(struct list_head *list) @@ -209,6 +231,21 @@ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) return NULL; } +struct perf_evsel * +perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, + const char *name) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) && + (strcmp(evsel->name, name) == 0)) + return evsel; + } + + return NULL; +} + int perf_evlist__add_newtp(struct perf_evlist *evlist, const char *sys, const char *name, void *handler) { @@ -218,7 +255,7 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist, if (evsel == NULL) return -1; - evsel->handler.func = handler; + evsel->handler = handler; perf_evlist__add(evlist, evsel); return 0; } @@ -232,7 +269,7 @@ void perf_evlist__disable(struct perf_evlist *evlist) for (cpu = 0; cpu < nr_cpus; cpu++) { list_for_each_entry(pos, &evlist->entries, node) { - if (!perf_evsel__is_group_leader(pos)) + if (!perf_evsel__is_group_leader(pos) || !pos->fd) continue; for (thread = 0; thread < nr_threads; thread++) ioctl(FD(pos, cpu, thread), @@ -250,7 +287,7 @@ void perf_evlist__enable(struct perf_evlist *evlist) for (cpu = 0; cpu < nr_cpus; cpu++) { list_for_each_entry(pos, &evlist->entries, node) { - if (!perf_evsel__is_group_leader(pos)) + if (!perf_evsel__is_group_leader(pos) || !pos->fd) continue; for (thread = 0; thread < nr_threads; thread++) ioctl(FD(pos, cpu, thread), @@ -259,6 +296,44 @@ void perf_evlist__enable(struct perf_evlist *evlist) } } +int perf_evlist__disable_event(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + int cpu, thread, err; + + if (!evsel->fd) + return 0; + + for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + for (thread = 0; thread < evlist->threads->nr; thread++) { + err = ioctl(FD(evsel, cpu, thread), + PERF_EVENT_IOC_DISABLE, 0); + if (err) + return err; + } + } + return 0; +} + +int perf_evlist__enable_event(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + int cpu, thread, err; + + if (!evsel->fd) + return -EINVAL; + + for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + for (thread = 0; thread < evlist->threads->nr; thread++) { + err = ioctl(FD(evsel, cpu, thread), + PERF_EVENT_IOC_ENABLE, 0); + if (err) + return err; + } + } + return 0; +} + static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) { int nr_cpus = cpu_map__nr(evlist->cpus); @@ -302,6 +377,24 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist, { u64 read_data[4] = { 0, }; int id_idx = 1; /* The first entry is the counter value */ + u64 id; + int ret; + + ret = ioctl(fd, PERF_EVENT_IOC_ID, &id); + if (!ret) + goto add; + + if (errno != ENOTTY) + return -1; + + /* Legacy way to get event id.. All hail to old kernels! */ + + /* + * This way does not work with group format read, so bail + * out in that case. + */ + if (perf_evlist__read_format(evlist) & PERF_FORMAT_GROUP) + return -1; if (!(evsel->attr.read_format & PERF_FORMAT_ID) || read(fd, &read_data, sizeof(read_data)) == -1) @@ -312,25 +405,39 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist, if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) ++id_idx; - perf_evlist__id_add(evlist, evsel, cpu, thread, read_data[id_idx]); + id = read_data[id_idx]; + + add: + perf_evlist__id_add(evlist, evsel, cpu, thread, id); return 0; } -struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) +struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id) { struct hlist_head *head; struct perf_sample_id *sid; int hash; - if (evlist->nr_entries == 1) - return perf_evlist__first(evlist); - hash = hash_64(id, PERF_EVLIST__HLIST_BITS); head = &evlist->heads[hash]; hlist_for_each_entry(sid, head, node) if (sid->id == id) - return sid->evsel; + return sid; + + return NULL; +} + +struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) +{ + struct perf_sample_id *sid; + + if (evlist->nr_entries == 1) + return perf_evlist__first(evlist); + + sid = perf_evlist__id2sid(evlist, id); + if (sid) + return sid->evsel; if (!perf_evlist__sample_id_all(evlist)) return perf_evlist__first(evlist); @@ -338,6 +445,60 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) return NULL; } +static int perf_evlist__event2id(struct perf_evlist *evlist, + union perf_event *event, u64 *id) +{ + const u64 *array = event->sample.array; + ssize_t n; + + n = (event->header.size - sizeof(event->header)) >> 3; + + if (event->header.type == PERF_RECORD_SAMPLE) { + if (evlist->id_pos >= n) + return -1; + *id = array[evlist->id_pos]; + } else { + if (evlist->is_pos > n) + return -1; + n -= evlist->is_pos; + *id = array[n]; + } + return 0; +} + +static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, + union perf_event *event) +{ + struct perf_evsel *first = perf_evlist__first(evlist); + struct hlist_head *head; + struct perf_sample_id *sid; + int hash; + u64 id; + + if (evlist->nr_entries == 1) + return first; + + if (!first->attr.sample_id_all && + event->header.type != PERF_RECORD_SAMPLE) + return first; + + if (perf_evlist__event2id(evlist, event, &id)) + return NULL; + + /* Synthesized events have an id of zero */ + if (!id) + return first; + + hash = hash_64(id, PERF_EVLIST__HLIST_BITS); + head = &evlist->heads[hash]; + + hlist_for_each_entry(sid, head, node) { + if (sid->id == id) + return sid->evsel; + } + return NULL; +} + union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) { struct perf_mmap *md = &evlist->mmap[idx]; @@ -379,7 +540,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) if ((old & md->mask) + size != ((old + size) & md->mask)) { unsigned int offset = old; unsigned int len = min(sizeof(*event), size), cpy; - void *dst = &md->event_copy; + void *dst = md->event_copy; do { cpy = min(md->mask + 1 - (offset & md->mask), len); @@ -389,7 +550,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) len -= cpy; } while (len); - event = &md->event_copy; + event = (union perf_event *) md->event_copy; } old += size; @@ -397,22 +558,33 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) md->prev = old; - if (!evlist->overwrite) + return event; +} + +void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) +{ + if (!evlist->overwrite) { + struct perf_mmap *md = &evlist->mmap[idx]; + unsigned int old = md->prev; + perf_mmap__write_tail(md, old); + } +} - return event; +static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx) +{ + if (evlist->mmap[idx].base != NULL) { + munmap(evlist->mmap[idx].base, evlist->mmap_len); + evlist->mmap[idx].base = NULL; + } } void perf_evlist__munmap(struct perf_evlist *evlist) { int i; - for (i = 0; i < evlist->nr_mmaps; i++) { - if (evlist->mmap[i].base != NULL) { - munmap(evlist->mmap[i].base, evlist->mmap_len); - evlist->mmap[i].base = NULL; - } - } + for (i = 0; i < evlist->nr_mmaps; i++) + __perf_evlist__munmap(evlist, i); free(evlist->mmap); evlist->mmap = NULL; @@ -421,7 +593,7 @@ void perf_evlist__munmap(struct perf_evlist *evlist) static int perf_evlist__alloc_mmap(struct perf_evlist *evlist) { evlist->nr_mmaps = cpu_map__nr(evlist->cpus); - if (cpu_map__all(evlist->cpus)) + if (cpu_map__empty(evlist->cpus)) evlist->nr_mmaps = thread_map__nr(evlist->threads); evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); return evlist->mmap != NULL ? 0 : -ENOMEM; @@ -435,6 +607,8 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot, MAP_SHARED, fd, 0); if (evlist->mmap[idx].base == MAP_FAILED) { + pr_debug2("failed to mmap perf event ring buffer, error %d\n", + errno); evlist->mmap[idx].base = NULL; return -1; } @@ -443,103 +617,152 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, return 0; } -static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask) +static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, + int prot, int mask, int cpu, int thread, + int *output) { struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + int fd = FD(evsel, cpu, thread); + + if (*output == -1) { + *output = fd; + if (__perf_evlist__mmap(evlist, idx, prot, mask, + *output) < 0) + return -1; + } else { + if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) + return -1; + } + + if ((evsel->attr.read_format & PERF_FORMAT_ID) && + perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) + return -1; + } + + return 0; +} + +static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, + int mask) +{ int cpu, thread; int nr_cpus = cpu_map__nr(evlist->cpus); int nr_threads = thread_map__nr(evlist->threads); + pr_debug2("perf event ring buffer mmapped per cpu\n"); for (cpu = 0; cpu < nr_cpus; cpu++) { int output = -1; for (thread = 0; thread < nr_threads; thread++) { - list_for_each_entry(evsel, &evlist->entries, node) { - int fd = FD(evsel, cpu, thread); - - if (output == -1) { - output = fd; - if (__perf_evlist__mmap(evlist, cpu, - prot, mask, output) < 0) - goto out_unmap; - } else { - if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0) - goto out_unmap; - } - - if ((evsel->attr.read_format & PERF_FORMAT_ID) && - perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) - goto out_unmap; - } + if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask, + cpu, thread, &output)) + goto out_unmap; } } return 0; out_unmap: - for (cpu = 0; cpu < nr_cpus; cpu++) { - if (evlist->mmap[cpu].base != NULL) { - munmap(evlist->mmap[cpu].base, evlist->mmap_len); - evlist->mmap[cpu].base = NULL; - } - } + for (cpu = 0; cpu < nr_cpus; cpu++) + __perf_evlist__munmap(evlist, cpu); return -1; } -static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask) +static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, + int mask) { - struct perf_evsel *evsel; int thread; int nr_threads = thread_map__nr(evlist->threads); + pr_debug2("perf event ring buffer mmapped per thread\n"); for (thread = 0; thread < nr_threads; thread++) { int output = -1; - list_for_each_entry(evsel, &evlist->entries, node) { - int fd = FD(evsel, 0, thread); - - if (output == -1) { - output = fd; - if (__perf_evlist__mmap(evlist, thread, - prot, mask, output) < 0) - goto out_unmap; - } else { - if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0) - goto out_unmap; - } - - if ((evsel->attr.read_format & PERF_FORMAT_ID) && - perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0) - goto out_unmap; - } + if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0, + thread, &output)) + goto out_unmap; } return 0; out_unmap: - for (thread = 0; thread < nr_threads; thread++) { - if (evlist->mmap[thread].base != NULL) { - munmap(evlist->mmap[thread].base, evlist->mmap_len); - evlist->mmap[thread].base = NULL; + for (thread = 0; thread < nr_threads; thread++) + __perf_evlist__munmap(evlist, thread); + return -1; +} + +static size_t perf_evlist__mmap_size(unsigned long pages) +{ + /* 512 kiB: default amount of unprivileged mlocked memory */ + if (pages == UINT_MAX) + pages = (512 * 1024) / page_size; + else if (!is_power_of_2(pages)) + return 0; + + return (pages + 1) * page_size; +} + +int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + unsigned int *mmap_pages = opt->value; + unsigned long pages, val; + size_t size; + static struct parse_tag tags[] = { + { .tag = 'B', .mult = 1 }, + { .tag = 'K', .mult = 1 << 10 }, + { .tag = 'M', .mult = 1 << 20 }, + { .tag = 'G', .mult = 1 << 30 }, + { .tag = 0 }, + }; + + val = parse_tag_value(str, tags); + if (val != (unsigned long) -1) { + /* we got file size value */ + pages = PERF_ALIGN(val, page_size) / page_size; + if (pages < (1UL << 31) && !is_power_of_2(pages)) { + pages = next_pow2(pages); + pr_info("rounding mmap pages size to %lu (%lu pages)\n", + pages * page_size, pages); + } + } else { + /* we got pages count value */ + char *eptr; + pages = strtoul(str, &eptr, 10); + if (*eptr != '\0') { + pr_err("failed to parse --mmap_pages/-m value\n"); + return -1; } } - return -1; + + if (pages > UINT_MAX || pages > SIZE_MAX / page_size) { + pr_err("--mmap_pages/-m value too big\n"); + return -1; + } + + size = perf_evlist__mmap_size(pages); + if (!size) { + pr_err("--mmap_pages/-m value must be a power of two."); + return -1; + } + + *mmap_pages = pages; + return 0; } -/** perf_evlist__mmap - Create per cpu maps to receive events - * - * @evlist - list of events - * @pages - map length in pages - * @overwrite - overwrite older events? +/** + * perf_evlist__mmap - Create mmaps to receive events. + * @evlist: list of events + * @pages: map length in pages + * @overwrite: overwrite older events? * - * If overwrite is false the user needs to signal event consuption using: + * If @overwrite is %false the user needs to signal event consumption using + * perf_mmap__write_tail(). Using perf_evlist__mmap_read() does this + * automatically. * - * struct perf_mmap *m = &evlist->mmap[cpu]; - * unsigned int head = perf_mmap__read_head(m); - * - * perf_mmap__write_tail(m, head) - * - * Using perf_evlist__read_on_cpu does this automatically. + * Return: %0 on success, negative error code otherwise. */ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, bool overwrite) @@ -549,14 +772,6 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, const struct thread_map *threads = evlist->threads; int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask; - /* 512 kiB: default amount of unprivileged mlocked memory */ - if (pages == UINT_MAX) - pages = (512 * 1024) / page_size; - else if (!is_power_of_2(pages)) - return -EINVAL; - - mask = pages * page_size - 1; - if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0) return -ENOMEM; @@ -564,7 +779,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, return -ENOMEM; evlist->overwrite = overwrite; - evlist->mmap_len = (pages + 1) * page_size; + evlist->mmap_len = perf_evlist__mmap_size(pages); + pr_debug("mmap size %zuB\n", evlist->mmap_len); + mask = evlist->mmap_len - page_size - 1; list_for_each_entry(evsel, &evlist->entries, node) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && @@ -573,7 +790,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, return -ENOMEM; } - if (cpu_map__all(cpus)) + if (cpu_map__empty(cpus)) return perf_evlist__mmap_per_thread(evlist, prot, mask); return perf_evlist__mmap_per_cpu(evlist, prot, mask); @@ -650,20 +867,66 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) { + struct perf_evsel *pos; + + if (evlist->nr_entries == 1) + return true; + + if (evlist->id_pos < 0 || evlist->is_pos < 0) + return false; + + list_for_each_entry(pos, &evlist->entries, node) { + if (pos->id_pos != evlist->id_pos || + pos->is_pos != evlist->is_pos) + return false; + } + + return true; +} + +u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + if (evlist->combined_sample_type) + return evlist->combined_sample_type; + + list_for_each_entry(evsel, &evlist->entries, node) + evlist->combined_sample_type |= evsel->attr.sample_type; + + return evlist->combined_sample_type; +} + +u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist) +{ + evlist->combined_sample_type = 0; + return __perf_evlist__combined_sample_type(evlist); +} + +bool perf_evlist__valid_read_format(struct perf_evlist *evlist) +{ struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; + u64 read_format = first->attr.read_format; + u64 sample_type = first->attr.sample_type; list_for_each_entry_continue(pos, &evlist->entries, node) { - if (first->attr.sample_type != pos->attr.sample_type) + if (read_format != pos->attr.read_format) return false; } + /* PERF_SAMPLE_READ imples PERF_FORMAT_ID. */ + if ((sample_type & PERF_SAMPLE_READ) && + !(read_format & PERF_FORMAT_ID)) { + return false; + } + return true; } -u64 perf_evlist__sample_type(struct perf_evlist *evlist) +u64 perf_evlist__read_format(struct perf_evlist *evlist) { struct perf_evsel *first = perf_evlist__first(evlist); - return first->attr.sample_type; + return first->attr.read_format; } u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist) @@ -692,6 +955,9 @@ u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist) if (sample_type & PERF_SAMPLE_CPU) size += sizeof(data->cpu) * 2; + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + size += sizeof(data->id); out: return size; } @@ -735,6 +1001,8 @@ int perf_evlist__open(struct perf_evlist *evlist) struct perf_evsel *evsel; int err; + perf_evlist__update_id_pos(evlist); + list_for_each_entry(evsel, &evlist->entries, node) { err = perf_evsel__open(evsel, evlist->cpus, evlist->threads); if (err < 0) @@ -783,13 +1051,6 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); /* - * Do a dummy execvp to get the PLT entry resolved, - * so we avoid the resolver overhead on the real - * execvp call. - */ - execvp("", (char **)argv); - - /* * Tell the parent we're ready to go */ close(child_ready_pipe[1]); @@ -838,7 +1099,7 @@ out_close_ready_pipe: int perf_evlist__start_workload(struct perf_evlist *evlist) { if (evlist->workload.cork_fd > 0) { - char bf; + char bf = 0; int ret; /* * Remove the cork, let it rip! @@ -857,7 +1118,10 @@ int perf_evlist__start_workload(struct perf_evlist *evlist) int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event, struct perf_sample *sample) { - struct perf_evsel *evsel = perf_evlist__first(evlist); + struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event); + + if (!evsel) + return -EFAULT; return perf_evsel__parse_sample(evsel, event, sample); } @@ -873,3 +1137,66 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp) return printed + fprintf(fp, "\n");; } + +int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused, + int err, char *buf, size_t size) +{ + char sbuf[128]; + + switch (err) { + case ENOENT: + scnprintf(buf, size, "%s", + "Error:\tUnable to find debugfs\n" + "Hint:\tWas your kernel was compiled with debugfs support?\n" + "Hint:\tIs the debugfs filesystem mounted?\n" + "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'"); + break; + case EACCES: + scnprintf(buf, size, + "Error:\tNo permissions to read %s/tracing/events/raw_syscalls\n" + "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n", + debugfs_mountpoint, debugfs_mountpoint); + break; + default: + scnprintf(buf, size, "%s", strerror_r(err, sbuf, sizeof(sbuf))); + break; + } + + return 0; +} + +int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused, + int err, char *buf, size_t size) +{ + int printed, value; + char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf)); + + switch (err) { + case EACCES: + case EPERM: + printed = scnprintf(buf, size, + "Error:\t%s.\n" + "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.", emsg); + + if (filename__read_int("/proc/sys/kernel/perf_event_paranoid", &value)) + break; + + printed += scnprintf(buf + printed, size - printed, "\nHint:\t"); + + if (value >= 2) { + printed += scnprintf(buf + printed, size - printed, + "For your workloads it needs to be <= 1\nHint:\t"); + } + printed += scnprintf(buf + printed, size - printed, + "For system wide tracing it needs to be set to -1"); + + printed += scnprintf(buf + printed, size - printed, + ".\nHint:\tThe current value is %d.", value); + break; + default: + scnprintf(buf, size, "%s", emsg); + break; + } + + return 0; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 0583d36252b..ecaa582f40e 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -21,7 +21,7 @@ struct perf_mmap { void *base; int mask; unsigned int prev; - union perf_event event_copy; + char event_copy[PERF_SAMPLE_MAX_SIZE]; }; struct perf_evlist { @@ -31,7 +31,10 @@ struct perf_evlist { int nr_groups; int nr_fds; int nr_mmaps; - int mmap_len; + size_t mmap_len; + int id_pos; + int is_pos; + u64 combined_sample_type; struct { int cork_fd; pid_t pid; @@ -50,6 +53,7 @@ struct perf_evsel_str_handler { }; struct perf_evlist *perf_evlist__new(void); +struct perf_evlist *perf_evlist__new_default(void); void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, struct thread_map *threads); void perf_evlist__exit(struct perf_evlist *evlist); @@ -71,6 +75,10 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter); struct perf_evsel * perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id); +struct perf_evsel * +perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, + const char *name); + void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu, int thread, u64 id); @@ -78,13 +86,20 @@ void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id); -union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx); +struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id); + +union perf_event *perf_evlist__mmap_read(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); void perf_evlist__close(struct perf_evlist *evlist); +void perf_evlist__set_id_pos(struct perf_evlist *evlist); +bool perf_can_sample_identifier(void); void perf_evlist__config(struct perf_evlist *evlist, struct perf_record_opts *opts); +int perf_record_opts__config(struct perf_record_opts *opts); int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct perf_target *target, @@ -92,6 +107,10 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, bool want_signal); int perf_evlist__start_workload(struct perf_evlist *evlist); +int perf_evlist__parse_mmap_pages(const struct option *opt, + const char *str, + int unset); + int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, bool overwrite); void perf_evlist__munmap(struct perf_evlist *evlist); @@ -99,6 +118,11 @@ void perf_evlist__munmap(struct perf_evlist *evlist); void perf_evlist__disable(struct perf_evlist *evlist); void perf_evlist__enable(struct perf_evlist *evlist); +int perf_evlist__disable_event(struct perf_evlist *evlist, + struct perf_evsel *evsel); +int perf_evlist__enable_event(struct perf_evlist *evlist, + struct perf_evsel *evsel); + void perf_evlist__set_selected(struct perf_evlist *evlist, struct perf_evsel *evsel); @@ -118,7 +142,9 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist); void __perf_evlist__set_leader(struct list_head *list); void perf_evlist__set_leader(struct perf_evlist *evlist); -u64 perf_evlist__sample_type(struct perf_evlist *evlist); +u64 perf_evlist__read_format(struct perf_evlist *evlist); +u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist); +u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist); bool perf_evlist__sample_id_all(struct perf_evlist *evlist); u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist); @@ -127,6 +153,7 @@ int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *even bool perf_evlist__valid_sample_type(struct perf_evlist *evlist); bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist); +bool perf_evlist__valid_read_format(struct perf_evlist *evlist); void perf_evlist__splice_list_tail(struct perf_evlist *evlist, struct list_head *list, @@ -144,10 +171,13 @@ static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist) size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); +int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size); +int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size); + static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm) { struct perf_event_mmap_page *pc = mm->base; - int head = pc->data_head; + int head = ACCESS_ONCE(pc->data_head); rmb(); return head; } @@ -160,7 +190,7 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, /* * ensure all reads are done before we write the tail out. */ - /* mb(); */ + mb(); pc->data_tail = tail; } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index c9c7494506a..5280820ed38 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -9,27 +9,30 @@ #include <byteswap.h> #include <linux/bitops.h> -#include "asm/bug.h" #include <lk/debugfs.h> -#include "event-parse.h" +#include <traceevent/event-parse.h> +#include <linux/hw_breakpoint.h> +#include <linux/perf_event.h> +#include <sys/resource.h> +#include "asm/bug.h" #include "evsel.h" #include "evlist.h" #include "util.h" #include "cpumap.h" #include "thread_map.h" #include "target.h" -#include <linux/hw_breakpoint.h> -#include <linux/perf_event.h> #include "perf_regs.h" +#include "debug.h" static struct { bool sample_id_all; bool exclude_guest; + bool mmap2; } perf_missing_features; #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) -static int __perf_evsel__sample_size(u64 sample_type) +int __perf_evsel__sample_size(u64 sample_type) { u64 mask = sample_type & PERF_SAMPLE_MASK; int size = 0; @@ -45,6 +48,72 @@ static int __perf_evsel__sample_size(u64 sample_type) return size; } +/** + * __perf_evsel__calc_id_pos - calculate id_pos. + * @sample_type: sample type + * + * This function returns the position of the event id (PERF_SAMPLE_ID or + * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct + * sample_event. + */ +static int __perf_evsel__calc_id_pos(u64 sample_type) +{ + int idx = 0; + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + return 0; + + if (!(sample_type & PERF_SAMPLE_ID)) + return -1; + + if (sample_type & PERF_SAMPLE_IP) + idx += 1; + + if (sample_type & PERF_SAMPLE_TID) + idx += 1; + + if (sample_type & PERF_SAMPLE_TIME) + idx += 1; + + if (sample_type & PERF_SAMPLE_ADDR) + idx += 1; + + return idx; +} + +/** + * __perf_evsel__calc_is_pos - calculate is_pos. + * @sample_type: sample type + * + * This function returns the position (counting backwards) of the event id + * (PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if + * sample_id_all is used there is an id sample appended to non-sample events. + */ +static int __perf_evsel__calc_is_pos(u64 sample_type) +{ + int idx = 1; + + if (sample_type & PERF_SAMPLE_IDENTIFIER) + return 1; + + if (!(sample_type & PERF_SAMPLE_ID)) + return -1; + + if (sample_type & PERF_SAMPLE_CPU) + idx += 1; + + if (sample_type & PERF_SAMPLE_STREAM_ID) + idx += 1; + + return idx; +} + +void perf_evsel__calc_id_pos(struct perf_evsel *evsel) +{ + evsel->id_pos = __perf_evsel__calc_id_pos(evsel->attr.sample_type); + evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type); +} + void hists__init(struct hists *hists) { memset(hists, 0, sizeof(*hists)); @@ -61,6 +130,7 @@ void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, if (!(evsel->attr.sample_type & bit)) { evsel->attr.sample_type |= bit; evsel->sample_size += sizeof(u64); + perf_evsel__calc_id_pos(evsel); } } @@ -70,12 +140,19 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, if (evsel->attr.sample_type & bit) { evsel->attr.sample_type &= ~bit; evsel->sample_size -= sizeof(u64); + perf_evsel__calc_id_pos(evsel); } } -void perf_evsel__set_sample_id(struct perf_evsel *evsel) +void perf_evsel__set_sample_id(struct perf_evsel *evsel, + bool can_sample_identifier) { - perf_evsel__set_sample_bit(evsel, ID); + if (can_sample_identifier) { + perf_evsel__reset_sample_bit(evsel, ID); + perf_evsel__set_sample_bit(evsel, IDENTIFIER); + } else { + perf_evsel__set_sample_bit(evsel, ID); + } evsel->attr.read_format |= PERF_FORMAT_ID; } @@ -88,6 +165,7 @@ void perf_evsel__init(struct perf_evsel *evsel, INIT_LIST_HEAD(&evsel->node); hists__init(&evsel->hists); evsel->sample_size = __perf_evsel__sample_size(attr->sample_type); + perf_evsel__calc_id_pos(evsel); } struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx) @@ -246,6 +324,7 @@ const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = { "major-faults", "alignment-faults", "emulation-faults", + "dummy", }; static const char *__perf_evsel__sw_name(u64 config) @@ -490,6 +569,7 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts) { + struct perf_evsel *leader = evsel->leader; struct perf_event_attr *attr = &evsel->attr; int track = !evsel->idx; /* only the first counter needs these */ @@ -499,6 +579,25 @@ void perf_evsel__config(struct perf_evsel *evsel, perf_evsel__set_sample_bit(evsel, IP); perf_evsel__set_sample_bit(evsel, TID); + if (evsel->sample_read) { + perf_evsel__set_sample_bit(evsel, READ); + + /* + * We need ID even in case of single event, because + * PERF_SAMPLE_READ process ID specific data. + */ + perf_evsel__set_sample_id(evsel, false); + + /* + * Apply group format only if we belong to group + * with more than one members. + */ + if (leader->nr_members > 1) { + attr->read_format |= PERF_FORMAT_GROUP; + attr->inherit = 0; + } + } + /* * We default some events to a 1 default interval. But keep * it a weak assumption overridable by the user. @@ -514,6 +613,15 @@ void perf_evsel__config(struct perf_evsel *evsel, } } + /* + * Disable sampling for all group members other + * than leader in case leader 'leads' the sampling. + */ + if ((leader != evsel) && leader->sample_read) { + attr->sample_freq = 0; + attr->sample_period = 0; + } + if (opts->no_samples) attr->sample_freq = 0; @@ -555,7 +663,7 @@ void perf_evsel__config(struct perf_evsel *evsel, } if (opts->sample_address) - attr->sample_type |= PERF_SAMPLE_DATA_SRC; + perf_evsel__set_sample_bit(evsel, DATA_SRC); if (opts->no_delay) { attr->watermark = 0; @@ -567,10 +675,13 @@ void perf_evsel__config(struct perf_evsel *evsel, } if (opts->sample_weight) - attr->sample_type |= PERF_SAMPLE_WEIGHT; + perf_evsel__set_sample_bit(evsel, WEIGHT); + + attr->mmap = track; + attr->comm = track; - attr->mmap = track; - attr->comm = track; + if (opts->sample_transaction) + perf_evsel__set_sample_bit(evsel, TRANSACTION); /* * XXX see the function comment above @@ -605,15 +716,15 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) return evsel->fd != NULL ? 0 : -ENOMEM; } -int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, - const char *filter) +static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthreads, + int ioc, void *arg) { int cpu, thread; for (cpu = 0; cpu < ncpus; cpu++) { for (thread = 0; thread < nthreads; thread++) { int fd = FD(evsel, cpu, thread), - err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter); + err = ioctl(fd, ioc, arg); if (err) return err; @@ -623,6 +734,21 @@ int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, return 0; } +int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, + const char *filter) +{ + return perf_evsel__run_ioctl(evsel, ncpus, nthreads, + PERF_EVENT_IOC_SET_FILTER, + (void *)filter); +} + +int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + return perf_evsel__run_ioctl(evsel, ncpus, nthreads, + PERF_EVENT_IOC_ENABLE, + 0); +} + int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) { evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); @@ -817,12 +943,73 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) return fd; } +#define __PRINT_ATTR(fmt, cast, field) \ + fprintf(fp, " %-19s "fmt"\n", #field, cast attr->field) + +#define PRINT_ATTR_U32(field) __PRINT_ATTR("%u" , , field) +#define PRINT_ATTR_X32(field) __PRINT_ATTR("%#x", , field) +#define PRINT_ATTR_U64(field) __PRINT_ATTR("%" PRIu64, (uint64_t), field) +#define PRINT_ATTR_X64(field) __PRINT_ATTR("%#"PRIx64, (uint64_t), field) + +#define PRINT_ATTR2N(name1, field1, name2, field2) \ + fprintf(fp, " %-19s %u %-19s %u\n", \ + name1, attr->field1, name2, attr->field2) + +#define PRINT_ATTR2(field1, field2) \ + PRINT_ATTR2N(#field1, field1, #field2, field2) + +static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) +{ + size_t ret = 0; + + ret += fprintf(fp, "%.60s\n", graph_dotted_line); + ret += fprintf(fp, "perf_event_attr:\n"); + + ret += PRINT_ATTR_U32(type); + ret += PRINT_ATTR_U32(size); + ret += PRINT_ATTR_X64(config); + ret += PRINT_ATTR_U64(sample_period); + ret += PRINT_ATTR_U64(sample_freq); + ret += PRINT_ATTR_X64(sample_type); + ret += PRINT_ATTR_X64(read_format); + + ret += PRINT_ATTR2(disabled, inherit); + ret += PRINT_ATTR2(pinned, exclusive); + ret += PRINT_ATTR2(exclude_user, exclude_kernel); + ret += PRINT_ATTR2(exclude_hv, exclude_idle); + ret += PRINT_ATTR2(mmap, comm); + ret += PRINT_ATTR2(freq, inherit_stat); + ret += PRINT_ATTR2(enable_on_exec, task); + ret += PRINT_ATTR2(watermark, precise_ip); + ret += PRINT_ATTR2(mmap_data, sample_id_all); + ret += PRINT_ATTR2(exclude_host, exclude_guest); + ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel, + "excl.callchain_user", exclude_callchain_user); + ret += PRINT_ATTR_U32(mmap2); + + ret += PRINT_ATTR_U32(wakeup_events); + ret += PRINT_ATTR_U32(wakeup_watermark); + ret += PRINT_ATTR_X32(bp_type); + ret += PRINT_ATTR_X64(bp_addr); + ret += PRINT_ATTR_X64(config1); + ret += PRINT_ATTR_U64(bp_len); + ret += PRINT_ATTR_X64(config2); + ret += PRINT_ATTR_X64(branch_sample_type); + ret += PRINT_ATTR_X64(sample_regs_user); + ret += PRINT_ATTR_U32(sample_stack_user); + + ret += fprintf(fp, "%.60s\n", graph_dotted_line); + + return ret; +} + static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { int cpu, thread; unsigned long flags = 0; int pid = -1, err; + enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE; if (evsel->fd == NULL && perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) @@ -834,12 +1021,17 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, } fallback_missing_features: + if (perf_missing_features.mmap2) + evsel->attr.mmap2 = 0; if (perf_missing_features.exclude_guest) evsel->attr.exclude_guest = evsel->attr.exclude_host = 0; retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; + if (verbose >= 2) + perf_event_attr__fprintf(&evsel->attr, stderr); + for (cpu = 0; cpu < cpus->nr; cpu++) { for (thread = 0; thread < threads->nr; thread++) { @@ -849,6 +1041,9 @@ retry_sample_id: pid = threads->map[thread]; group_fd = get_group_fd(evsel, cpu, thread); +retry_open: + pr_debug2("perf_event_open: pid %d cpu %d group_fd %d flags %#lx\n", + pid, cpus->map[cpu], group_fd, flags); FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr, pid, @@ -856,19 +1051,49 @@ retry_sample_id: group_fd, flags); if (FD(evsel, cpu, thread) < 0) { err = -errno; + pr_debug2("perf_event_open failed, error %d\n", + err); goto try_fallback; } + set_rlimit = NO_CHANGE; } } return 0; try_fallback: + /* + * perf stat needs between 5 and 22 fds per CPU. When we run out + * of them try to increase the limits. + */ + if (err == -EMFILE && set_rlimit < INCREASED_MAX) { + struct rlimit l; + int old_errno = errno; + + if (getrlimit(RLIMIT_NOFILE, &l) == 0) { + if (set_rlimit == NO_CHANGE) + l.rlim_cur = l.rlim_max; + else { + l.rlim_cur = l.rlim_max + 1000; + l.rlim_max = l.rlim_cur; + } + if (setrlimit(RLIMIT_NOFILE, &l) == 0) { + set_rlimit++; + errno = old_errno; + goto retry_open; + } + } + errno = old_errno; + } + if (err != -EINVAL || cpu > 0 || thread > 0) goto out_close; - if (!perf_missing_features.exclude_guest && - (evsel->attr.exclude_guest || evsel->attr.exclude_host)) { + if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { + perf_missing_features.mmap2 = true; + goto fallback_missing_features; + } else if (!perf_missing_features.exclude_guest && + (evsel->attr.exclude_guest || evsel->attr.exclude_host)) { perf_missing_features.exclude_guest = true; goto fallback_missing_features; } else if (!perf_missing_features.sample_id_all) { @@ -951,6 +1176,11 @@ static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel, array += ((event->header.size - sizeof(event->header)) / sizeof(u64)) - 1; + if (type & PERF_SAMPLE_IDENTIFIER) { + sample->id = *array; + array--; + } + if (type & PERF_SAMPLE_CPU) { u.val64 = *array; if (swapped) { @@ -989,29 +1219,36 @@ static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel, sample->pid = u.val32[0]; sample->tid = u.val32[1]; + array--; } return 0; } -static bool sample_overlap(const union perf_event *event, - const void *offset, u64 size) +static inline bool overflow(const void *endp, u16 max_size, const void *offset, + u64 size) { - const void *base = event; + return size > max_size || offset + size > endp; +} - if (offset + size > base + event->header.size) - return true; +#define OVERFLOW_CHECK(offset, size, max_size) \ + do { \ + if (overflow(endp, (max_size), (offset), (size))) \ + return -EFAULT; \ + } while (0) - return false; -} +#define OVERFLOW_CHECK_u64(offset) \ + OVERFLOW_CHECK(offset, sizeof(u64), sizeof(u64)) int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *data) { u64 type = evsel->attr.sample_type; - u64 regs_user = evsel->attr.sample_regs_user; bool swapped = evsel->needs_swap; const u64 *array; + u16 max_size = event->header.size; + const void *endp = (void *)event + max_size; + u64 sz; /* * used for cross-endian analysis. See git commit 65014ab3 @@ -1033,11 +1270,22 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array = event->sample.array; + /* + * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes + * up to PERF_SAMPLE_PERIOD. After that overflow() must be used to + * check the format does not go past the end of the event. + */ if (evsel->sample_size + sizeof(event->header) > event->header.size) return -EFAULT; + data->id = -1ULL; + if (type & PERF_SAMPLE_IDENTIFIER) { + data->id = *array; + array++; + } + if (type & PERF_SAMPLE_IP) { - data->ip = event->ip.ip; + data->ip = *array; array++; } @@ -1066,7 +1314,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array++; } - data->id = -1ULL; if (type & PERF_SAMPLE_ID) { data->id = *array; array++; @@ -1096,25 +1343,62 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } if (type & PERF_SAMPLE_READ) { - fprintf(stderr, "PERF_SAMPLE_READ is unsupported for now\n"); - return -1; + u64 read_format = evsel->attr.read_format; + + OVERFLOW_CHECK_u64(array); + if (read_format & PERF_FORMAT_GROUP) + data->read.group.nr = *array; + else + data->read.one.value = *array; + + array++; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + OVERFLOW_CHECK_u64(array); + data->read.time_enabled = *array; + array++; + } + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + OVERFLOW_CHECK_u64(array); + data->read.time_running = *array; + array++; + } + + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_GROUP) { + const u64 max_group_nr = UINT64_MAX / + sizeof(struct sample_read_value); + + if (data->read.group.nr > max_group_nr) + return -EFAULT; + sz = data->read.group.nr * + sizeof(struct sample_read_value); + OVERFLOW_CHECK(array, sz, max_size); + data->read.group.values = + (struct sample_read_value *)array; + array = (void *)array + sz; + } else { + OVERFLOW_CHECK_u64(array); + data->read.one.id = *array; + array++; + } } if (type & PERF_SAMPLE_CALLCHAIN) { - if (sample_overlap(event, array, sizeof(data->callchain->nr))) - return -EFAULT; - - data->callchain = (struct ip_callchain *)array; + const u64 max_callchain_nr = UINT64_MAX / sizeof(u64); - if (sample_overlap(event, array, data->callchain->nr)) + OVERFLOW_CHECK_u64(array); + data->callchain = (struct ip_callchain *)array++; + if (data->callchain->nr > max_callchain_nr) return -EFAULT; - - array += 1 + data->callchain->nr; + sz = data->callchain->nr * sizeof(u64); + OVERFLOW_CHECK(array, sz, max_size); + array = (void *)array + sz; } if (type & PERF_SAMPLE_RAW) { - const u64 *pdata; - + OVERFLOW_CHECK_u64(array); u.val64 = *array; if (WARN_ONCE(swapped, "Endianness of raw data not corrected!\n")) { @@ -1123,78 +1407,190 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, u.val32[0] = bswap_32(u.val32[0]); u.val32[1] = bswap_32(u.val32[1]); } - - if (sample_overlap(event, array, sizeof(u32))) - return -EFAULT; - data->raw_size = u.val32[0]; - pdata = (void *) array + sizeof(u32); - - if (sample_overlap(event, pdata, data->raw_size)) - return -EFAULT; + array = (void *)array + sizeof(u32); - data->raw_data = (void *) pdata; - - array = (void *)array + data->raw_size + sizeof(u32); + OVERFLOW_CHECK(array, data->raw_size, max_size); + data->raw_data = (void *)array; + array = (void *)array + data->raw_size; } if (type & PERF_SAMPLE_BRANCH_STACK) { - u64 sz; + const u64 max_branch_nr = UINT64_MAX / + sizeof(struct branch_entry); - data->branch_stack = (struct branch_stack *)array; - array++; /* nr */ + OVERFLOW_CHECK_u64(array); + data->branch_stack = (struct branch_stack *)array++; + if (data->branch_stack->nr > max_branch_nr) + return -EFAULT; sz = data->branch_stack->nr * sizeof(struct branch_entry); - sz /= sizeof(u64); - array += sz; + OVERFLOW_CHECK(array, sz, max_size); + array = (void *)array + sz; } if (type & PERF_SAMPLE_REGS_USER) { - /* First u64 tells us if we have any regs in sample. */ - u64 avail = *array++; + OVERFLOW_CHECK_u64(array); + data->user_regs.abi = *array; + array++; + + if (data->user_regs.abi) { + u64 regs_user = evsel->attr.sample_regs_user; - if (avail) { + sz = hweight_long(regs_user) * sizeof(u64); + OVERFLOW_CHECK(array, sz, max_size); data->user_regs.regs = (u64 *)array; - array += hweight_long(regs_user); + array = (void *)array + sz; } } if (type & PERF_SAMPLE_STACK_USER) { - u64 size = *array++; + OVERFLOW_CHECK_u64(array); + sz = *array++; data->user_stack.offset = ((char *)(array - 1) - (char *) event); - if (!size) { + if (!sz) { data->user_stack.size = 0; } else { + OVERFLOW_CHECK(array, sz, max_size); data->user_stack.data = (char *)array; - array += size / sizeof(*array); + array = (void *)array + sz; + OVERFLOW_CHECK_u64(array); data->user_stack.size = *array++; + if (WARN_ONCE(data->user_stack.size > sz, + "user stack dump failure\n")) + return -EFAULT; } } data->weight = 0; if (type & PERF_SAMPLE_WEIGHT) { + OVERFLOW_CHECK_u64(array); data->weight = *array; array++; } data->data_src = PERF_MEM_DATA_SRC_NONE; if (type & PERF_SAMPLE_DATA_SRC) { + OVERFLOW_CHECK_u64(array); data->data_src = *array; array++; } + data->transaction = 0; + if (type & PERF_SAMPLE_TRANSACTION) { + OVERFLOW_CHECK_u64(array); + data->transaction = *array; + array++; + } + return 0; } +size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, + u64 sample_regs_user, u64 read_format) +{ + size_t sz, result = sizeof(struct sample_event); + + if (type & PERF_SAMPLE_IDENTIFIER) + result += sizeof(u64); + + if (type & PERF_SAMPLE_IP) + result += sizeof(u64); + + if (type & PERF_SAMPLE_TID) + result += sizeof(u64); + + if (type & PERF_SAMPLE_TIME) + result += sizeof(u64); + + if (type & PERF_SAMPLE_ADDR) + result += sizeof(u64); + + if (type & PERF_SAMPLE_ID) + result += sizeof(u64); + + if (type & PERF_SAMPLE_STREAM_ID) + result += sizeof(u64); + + if (type & PERF_SAMPLE_CPU) + result += sizeof(u64); + + if (type & PERF_SAMPLE_PERIOD) + result += sizeof(u64); + + if (type & PERF_SAMPLE_READ) { + result += sizeof(u64); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + result += sizeof(u64); + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + result += sizeof(u64); + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_GROUP) { + sz = sample->read.group.nr * + sizeof(struct sample_read_value); + result += sz; + } else { + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_CALLCHAIN) { + sz = (sample->callchain->nr + 1) * sizeof(u64); + result += sz; + } + + if (type & PERF_SAMPLE_RAW) { + result += sizeof(u32); + result += sample->raw_size; + } + + if (type & PERF_SAMPLE_BRANCH_STACK) { + sz = sample->branch_stack->nr * sizeof(struct branch_entry); + sz += sizeof(u64); + result += sz; + } + + if (type & PERF_SAMPLE_REGS_USER) { + if (sample->user_regs.abi) { + result += sizeof(u64); + sz = hweight_long(sample_regs_user) * sizeof(u64); + result += sz; + } else { + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_STACK_USER) { + sz = sample->user_stack.size; + result += sizeof(u64); + if (sz) { + result += sz; + result += sizeof(u64); + } + } + + if (type & PERF_SAMPLE_WEIGHT) + result += sizeof(u64); + + if (type & PERF_SAMPLE_DATA_SRC) + result += sizeof(u64); + + if (type & PERF_SAMPLE_TRANSACTION) + result += sizeof(u64); + + return result; +} + int perf_event__synthesize_sample(union perf_event *event, u64 type, + u64 sample_regs_user, u64 read_format, const struct perf_sample *sample, bool swapped) { u64 *array; - + size_t sz; /* * used for cross-endian analysis. See git commit 65014ab3 * for why this goofiness is needed. @@ -1203,8 +1599,13 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, array = event->sample.array; + if (type & PERF_SAMPLE_IDENTIFIER) { + *array = sample->id; + array++; + } + if (type & PERF_SAMPLE_IP) { - event->ip.ip = sample->ip; + *array = sample->ip; array++; } @@ -1262,6 +1663,102 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, array++; } + if (type & PERF_SAMPLE_READ) { + if (read_format & PERF_FORMAT_GROUP) + *array = sample->read.group.nr; + else + *array = sample->read.one.value; + array++; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + *array = sample->read.time_enabled; + array++; + } + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + *array = sample->read.time_running; + array++; + } + + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_GROUP) { + sz = sample->read.group.nr * + sizeof(struct sample_read_value); + memcpy(array, sample->read.group.values, sz); + array = (void *)array + sz; + } else { + *array = sample->read.one.id; + array++; + } + } + + if (type & PERF_SAMPLE_CALLCHAIN) { + sz = (sample->callchain->nr + 1) * sizeof(u64); + memcpy(array, sample->callchain, sz); + array = (void *)array + sz; + } + + if (type & PERF_SAMPLE_RAW) { + u.val32[0] = sample->raw_size; + if (WARN_ONCE(swapped, + "Endianness of raw data not corrected!\n")) { + /* + * Inverse of what is done in perf_evsel__parse_sample + */ + u.val32[0] = bswap_32(u.val32[0]); + u.val32[1] = bswap_32(u.val32[1]); + u.val64 = bswap_64(u.val64); + } + *array = u.val64; + array = (void *)array + sizeof(u32); + + memcpy(array, sample->raw_data, sample->raw_size); + array = (void *)array + sample->raw_size; + } + + if (type & PERF_SAMPLE_BRANCH_STACK) { + sz = sample->branch_stack->nr * sizeof(struct branch_entry); + sz += sizeof(u64); + memcpy(array, sample->branch_stack, sz); + array = (void *)array + sz; + } + + if (type & PERF_SAMPLE_REGS_USER) { + if (sample->user_regs.abi) { + *array++ = sample->user_regs.abi; + sz = hweight_long(sample_regs_user) * sizeof(u64); + memcpy(array, sample->user_regs.regs, sz); + array = (void *)array + sz; + } else { + *array++ = 0; + } + } + + if (type & PERF_SAMPLE_STACK_USER) { + sz = sample->user_stack.size; + *array++ = sz; + if (sz) { + memcpy(array, sample->user_stack.data, sz); + array = (void *)array + sz; + *array++ = sz; + } + } + + if (type & PERF_SAMPLE_WEIGHT) { + *array = sample->weight; + array++; + } + + if (type & PERF_SAMPLE_DATA_SRC) { + *array = sample->data_src; + array++; + } + + if (type & PERF_SAMPLE_TRANSACTION) { + *array = sample->transaction; + array++; + } + return 0; } @@ -1391,6 +1888,7 @@ static int sample_type__fprintf(FILE *fp, bool *first, u64 value) bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), + bit_name(IDENTIFIER), { .name = NULL, } }; #undef bit_name @@ -1458,6 +1956,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, if_print(exclude_hv); if_print(exclude_idle); if_print(mmap); + if_print(mmap2); if_print(comm); if_print(freq); if_print(inherit_stat); @@ -1482,7 +1981,7 @@ out: bool perf_evsel__fallback(struct perf_evsel *evsel, int err, char *msg, size_t msgsize) { - if ((err == ENOENT || err == ENXIO) && + if ((err == ENOENT || err == ENXIO || err == ENODEV) && evsel->attr.type == PERF_TYPE_HARDWARE && evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) { /* diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 3f156ccc1ac..64ec8e1a7a2 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -38,6 +38,9 @@ struct perf_sample_id { struct hlist_node node; u64 id; struct perf_evsel *evsel; + + /* Holds total ID period value for PERF_SAMPLE_READ processing. */ + u64 period; }; /** struct perf_evsel - event selector @@ -45,6 +48,12 @@ struct perf_sample_id { * @name - Can be set to retain the original event name passed by the user, * so that when showing results in tools such as 'perf stat', we * show the name used, not some alias. + * @id_pos: the position of the event id (PERF_SAMPLE_ID or + * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of + * struct sample_event + * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or + * PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all + * is used there is an id sample appended to non-sample events */ struct perf_evsel { struct list_head node; @@ -65,17 +74,17 @@ struct perf_evsel { off_t id_offset; }; struct cgroup_sel *cgrp; - struct { - void *func; - void *data; - } handler; + void *handler; struct cpu_map *cpus; unsigned int sample_size; + int id_pos; + int is_pos; bool supported; bool needs_swap; /* parse modifier helper */ int exclude_GH; int nr_members; + int sample_read; struct perf_evsel *leader; char *group_name; }; @@ -100,6 +109,9 @@ void perf_evsel__delete(struct perf_evsel *evsel); void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts); +int __perf_evsel__sample_size(u64 sample_type); +void perf_evsel__calc_id_pos(struct perf_evsel *evsel); + bool perf_evsel__is_cache_op_valid(u8 type, u8 op); #define PERF_EVSEL__MAX_ALIASES 8 @@ -138,10 +150,12 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, #define perf_evsel__reset_sample_bit(evsel, bit) \ __perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit) -void perf_evsel__set_sample_id(struct perf_evsel *evsel); +void perf_evsel__set_sample_id(struct perf_evsel *evsel, + bool use_sample_identifier); int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, const char *filter); +int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus); @@ -180,6 +194,12 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1, (e1->attr.config == e2->attr.config); } +#define perf_evsel__cmp(a, b) \ + ((a) && \ + (b) && \ + (a)->attr.type == (b)->attr.type && \ + (a)->attr.config == (b)->attr.config) + int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, int cpu, int thread, bool scale); diff --git a/tools/perf/util/fs.c b/tools/perf/util/fs.c new file mode 100644 index 00000000000..f5be1f26e72 --- /dev/null +++ b/tools/perf/util/fs.c @@ -0,0 +1,119 @@ + +/* TODO merge/factor into tools/lib/lk/debugfs.c */ + +#include "util.h" +#include "util/fs.h" + +static const char * const sysfs__fs_known_mountpoints[] = { + "/sys", + 0, +}; + +static const char * const procfs__known_mountpoints[] = { + "/proc", + 0, +}; + +struct fs { + const char *name; + const char * const *mounts; + char path[PATH_MAX + 1]; + bool found; + long magic; +}; + +enum { + FS__SYSFS = 0, + FS__PROCFS = 1, +}; + +static struct fs fs__entries[] = { + [FS__SYSFS] = { + .name = "sysfs", + .mounts = sysfs__fs_known_mountpoints, + .magic = SYSFS_MAGIC, + }, + [FS__PROCFS] = { + .name = "proc", + .mounts = procfs__known_mountpoints, + .magic = PROC_SUPER_MAGIC, + }, +}; + +static bool fs__read_mounts(struct fs *fs) +{ + bool found = false; + char type[100]; + FILE *fp; + + fp = fopen("/proc/mounts", "r"); + if (fp == NULL) + return NULL; + + while (!found && + fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n", + fs->path, type) == 2) { + + if (strcmp(type, fs->name) == 0) + found = true; + } + + fclose(fp); + return fs->found = found; +} + +static int fs__valid_mount(const char *fs, long magic) +{ + struct statfs st_fs; + + if (statfs(fs, &st_fs) < 0) + return -ENOENT; + else if (st_fs.f_type != magic) + return -ENOENT; + + return 0; +} + +static bool fs__check_mounts(struct fs *fs) +{ + const char * const *ptr; + + ptr = fs->mounts; + while (*ptr) { + if (fs__valid_mount(*ptr, fs->magic) == 0) { + fs->found = true; + strcpy(fs->path, *ptr); + return true; + } + ptr++; + } + + return false; +} + +static const char *fs__get_mountpoint(struct fs *fs) +{ + if (fs__check_mounts(fs)) + return fs->path; + + return fs__read_mounts(fs) ? fs->path : NULL; +} + +static const char *fs__mountpoint(int idx) +{ + struct fs *fs = &fs__entries[idx]; + + if (fs->found) + return (const char *)fs->path; + + return fs__get_mountpoint(fs); +} + +#define FS__MOUNTPOINT(name, idx) \ +const char *name##__mountpoint(void) \ +{ \ + return fs__mountpoint(idx); \ +} + +FS__MOUNTPOINT(sysfs, FS__SYSFS); +FS__MOUNTPOINT(procfs, FS__PROCFS); diff --git a/tools/perf/util/fs.h b/tools/perf/util/fs.h new file mode 100644 index 00000000000..5e09ce1bab0 --- /dev/null +++ b/tools/perf/util/fs.h @@ -0,0 +1,7 @@ +#ifndef __PERF_FS +#define __PERF_FS + +const char *sysfs__mountpoint(void); +const char *procfs__mountpoint(void); + +#endif /* __PERF_FS */ diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh index 3ac38031d53..36a885d2cd2 100755 --- a/tools/perf/util/generate-cmdlist.sh +++ b/tools/perf/util/generate-cmdlist.sh @@ -22,7 +22,7 @@ do }' "Documentation/perf-$cmd.txt" done -echo "#ifdef LIBELF_SUPPORT" +echo "#ifdef HAVE_LIBELF_SUPPORT" sed -n -e 's/^perf-\([^ ]*\)[ ].* full.*/\1/p' command-list.txt | sort | while read cmd @@ -35,5 +35,5 @@ do p }' "Documentation/perf-$cmd.txt" done -echo "#endif /* LIBELF_SUPPORT */" +echo "#endif /* HAVE_LIBELF_SUPPORT */" echo "};" diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index a4dafbee251..26d9520a0c1 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -22,44 +22,13 @@ #include "vdso.h" #include "strbuf.h" #include "build-id.h" +#include "data.h" static bool no_buildid_cache = false; -static int trace_event_count; -static struct perf_trace_event_type *trace_events; - static u32 header_argc; static const char **header_argv; -int perf_header__push_event(u64 id, const char *name) -{ - struct perf_trace_event_type *nevents; - - if (strlen(name) > MAX_EVENT_NAME) - pr_warning("Event %s will be truncated\n", name); - - nevents = realloc(trace_events, (trace_event_count + 1) * sizeof(*trace_events)); - if (nevents == NULL) - return -ENOMEM; - trace_events = nevents; - - memset(&trace_events[trace_event_count], 0, sizeof(struct perf_trace_event_type)); - trace_events[trace_event_count].event_id = id; - strncpy(trace_events[trace_event_count].name, name, MAX_EVENT_NAME - 1); - trace_event_count++; - return 0; -} - -char *perf_header__find_event(u64 id) -{ - int i; - for (i = 0 ; i < trace_event_count; i++) { - if (trace_events[i].event_id == id) - return trace_events[i].name; - } - return NULL; -} - /* * magic2 = "PERFILE2" * must be a numerical value to let the endianness @@ -231,9 +200,11 @@ static int write_buildid(char *name, size_t name_len, u8 *build_id, return write_padded(fd, name, name_len + 1, len); } -static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, - u16 misc, int fd) +static int __dsos__write_buildid_table(struct list_head *head, + struct machine *machine, + pid_t pid, u16 misc, int fd) { + char nm[PATH_MAX]; struct dso *pos; dsos__for_each_with_build_id(pos, head) { @@ -247,6 +218,10 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, if (is_vdso_map(pos->short_name)) { name = (char *) VDSO__MAP_NAME; name_len = sizeof(VDSO__MAP_NAME) + 1; + } else if (dso__is_kcore(pos)) { + machine__mmap_name(machine, nm, sizeof(nm)); + name = nm; + name_len = strlen(nm) + 1; } else { name = pos->long_name; name_len = pos->long_name_len + 1; @@ -272,10 +247,10 @@ static int machine__write_buildid_table(struct machine *machine, int fd) umisc = PERF_RECORD_MISC_GUEST_USER; } - err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid, - kmisc, fd); + err = __dsos__write_buildid_table(&machine->kernel_dsos, machine, + machine->pid, kmisc, fd); if (err == 0) - err = __dsos__write_buildid_table(&machine->user_dsos, + err = __dsos__write_buildid_table(&machine->user_dsos, machine, machine->pid, umisc, fd); return err; } @@ -407,23 +382,31 @@ out_free: return err; } -static int dso__cache_build_id(struct dso *dso, const char *debugdir) +static int dso__cache_build_id(struct dso *dso, struct machine *machine, + const char *debugdir) { bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; bool is_vdso = is_vdso_map(dso->short_name); + char *name = dso->long_name; + char nm[PATH_MAX]; - return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), - dso->long_name, debugdir, - is_kallsyms, is_vdso); + if (dso__is_kcore(dso)) { + is_kallsyms = true; + machine__mmap_name(machine, nm, sizeof(nm)); + name = nm; + } + return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, + debugdir, is_kallsyms, is_vdso); } -static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) +static int __dsos__cache_build_ids(struct list_head *head, + struct machine *machine, const char *debugdir) { struct dso *pos; int err = 0; dsos__for_each_with_build_id(pos, head) - if (dso__cache_build_id(pos, debugdir)) + if (dso__cache_build_id(pos, machine, debugdir)) err = -1; return err; @@ -431,8 +414,9 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) static int machine__cache_build_ids(struct machine *machine, const char *debugdir) { - int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir); - ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir); + int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine, + debugdir); + ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir); return ret; } @@ -748,18 +732,19 @@ static int build_cpu_topo(struct cpu_topo *tp, int cpu) char filename[MAXPATHLEN]; char *buf = NULL, *p; size_t len = 0; + ssize_t sret; u32 i = 0; int ret = -1; sprintf(filename, CORE_SIB_FMT, cpu); fp = fopen(filename, "r"); if (!fp) - return -1; - - if (getline(&buf, &len, fp) <= 0) - goto done; + goto try_threads; + sret = getline(&buf, &len, fp); fclose(fp); + if (sret <= 0) + goto try_threads; p = strchr(buf, '\n'); if (p) @@ -775,7 +760,9 @@ static int build_cpu_topo(struct cpu_topo *tp, int cpu) buf = NULL; len = 0; } + ret = 0; +try_threads: sprintf(filename, THRD_SIB_FMT, cpu); fp = fopen(filename, "r"); if (!fp) @@ -1380,6 +1367,9 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp) fprintf(fp, ", precise_ip = %d", evsel->attr.precise_ip); + fprintf(fp, ", attr_mmap2 = %d", evsel->attr.mmap2); + fprintf(fp, ", attr_mmap = %d", evsel->attr.mmap); + fprintf(fp, ", attr_mmap_data = %d", evsel->attr.mmap_data); if (evsel->ids) { fprintf(fp, ", id = {"); for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) { @@ -2200,7 +2190,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) { struct header_print_data hd; struct perf_header *header = &session->header; - int fd = session->fd; + int fd = perf_data_file__fd(session->file); hd.fp = fp; hd.full = full; @@ -2257,7 +2247,7 @@ static int perf_header__adds_write(struct perf_header *header, sec_size = sizeof(*feat_sec) * nr_sections; - sec_start = header->data_offset + header->data_size; + sec_start = header->feat_offset; lseek(fd, sec_start + sec_size, SEEK_SET); for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) { @@ -2304,6 +2294,7 @@ int perf_session__write_header(struct perf_session *session, struct perf_file_attr f_attr; struct perf_header *header = &session->header; struct perf_evsel *evsel; + u64 attr_offset; int err; lseek(fd, sizeof(f_header), SEEK_SET); @@ -2317,7 +2308,7 @@ int perf_session__write_header(struct perf_session *session, } } - header->attr_offset = lseek(fd, 0, SEEK_CUR); + attr_offset = lseek(fd, 0, SEEK_CUR); list_for_each_entry(evsel, &evlist->entries, node) { f_attr = (struct perf_file_attr){ @@ -2334,17 +2325,8 @@ int perf_session__write_header(struct perf_session *session, } } - header->event_offset = lseek(fd, 0, SEEK_CUR); - header->event_size = trace_event_count * sizeof(struct perf_trace_event_type); - if (trace_events) { - err = do_write(fd, trace_events, header->event_size); - if (err < 0) { - pr_debug("failed to write perf header events\n"); - return err; - } - } - header->data_offset = lseek(fd, 0, SEEK_CUR); + header->feat_offset = header->data_offset + header->data_size; if (at_exit) { err = perf_header__adds_write(header, evlist, fd); @@ -2357,17 +2339,14 @@ int perf_session__write_header(struct perf_session *session, .size = sizeof(f_header), .attr_size = sizeof(f_attr), .attrs = { - .offset = header->attr_offset, + .offset = attr_offset, .size = evlist->nr_entries * sizeof(f_attr), }, .data = { .offset = header->data_offset, .size = header->data_size, }, - .event_types = { - .offset = header->event_offset, - .size = header->event_size, - }, + /* event_types is ignored, store zeros */ }; memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features)); @@ -2417,7 +2396,7 @@ int perf_header__process_sections(struct perf_header *header, int fd, sec_size = sizeof(*feat_sec) * nr_sections; - lseek(fd, header->data_offset + header->data_size, SEEK_SET); + lseek(fd, header->feat_offset, SEEK_SET); err = perf_header__getbuffer64(header, fd, feat_sec, sec_size); if (err < 0) @@ -2523,6 +2502,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz, /* check for legacy format */ ret = memcmp(&magic, __perf_magic1, sizeof(magic)); if (ret == 0) { + ph->version = PERF_HEADER_VERSION_1; pr_debug("legacy perf.data format\n"); if (is_pipe) return try_all_pipe_abis(hdr_sz, ph); @@ -2544,6 +2524,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz, return -1; ph->needs_swap = true; + ph->version = PERF_HEADER_VERSION_2; return 0; } @@ -2614,10 +2595,9 @@ int perf_file_header__read(struct perf_file_header *header, memcpy(&ph->adds_features, &header->adds_features, sizeof(ph->adds_features)); - ph->event_offset = header->event_types.offset; - ph->event_size = header->event_types.size; ph->data_offset = header->data.offset; ph->data_size = header->data.size; + ph->feat_offset = header->data.offset + header->data.size; return 0; } @@ -2666,19 +2646,18 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, return 0; } -static int perf_header__read_pipe(struct perf_session *session, int fd) +static int perf_header__read_pipe(struct perf_session *session) { struct perf_header *header = &session->header; struct perf_pipe_file_header f_header; - if (perf_file_header__read_pipe(&f_header, header, fd, + if (perf_file_header__read_pipe(&f_header, header, + perf_data_file__fd(session->file), session->repipe) < 0) { pr_debug("incompatible file format\n"); return -EINVAL; } - session->fd = fd; - return 0; } @@ -2772,24 +2751,38 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist, return 0; } -int perf_session__read_header(struct perf_session *session, int fd) +int perf_session__read_header(struct perf_session *session) { + struct perf_data_file *file = session->file; struct perf_header *header = &session->header; struct perf_file_header f_header; struct perf_file_attr f_attr; u64 f_id; int nr_attrs, nr_ids, i, j; + int fd = perf_data_file__fd(file); session->evlist = perf_evlist__new(); if (session->evlist == NULL) return -ENOMEM; - if (session->fd_pipe) - return perf_header__read_pipe(session, fd); + if (perf_data_file__is_pipe(file)) + return perf_header__read_pipe(session); if (perf_file_header__read(&f_header, header, fd) < 0) return -EINVAL; + /* + * Sanity check that perf.data was written cleanly; data size is + * initialized to 0 and updated only if the on_exit function is run. + * If data size is still 0 then the file contains only partial + * information. Just warn user and process it as much as it can. + */ + if (f_header.data.size == 0) { + pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n" + "Was the 'perf record' command properly terminated?\n", + file->path); + } + nr_attrs = f_header.attrs.size / f_header.attr_size; lseek(fd, f_header.attrs.offset, SEEK_SET); @@ -2839,22 +2832,9 @@ int perf_session__read_header(struct perf_session *session, int fd) symbol_conf.nr_events = nr_attrs; - if (f_header.event_types.size) { - lseek(fd, f_header.event_types.offset, SEEK_SET); - trace_events = malloc(f_header.event_types.size); - if (trace_events == NULL) - return -ENOMEM; - if (perf_header__getbuffer64(header, fd, trace_events, - f_header.event_types.size)) - goto out_errno; - trace_event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type); - } - perf_header__process_sections(header, fd, &session->pevent, perf_file_section__process); - lseek(fd, header->data_offset, SEEK_SET); - if (perf_evlist__prepare_tracepoint_events(session->evlist, session->pevent)) goto out_delete_evlist; @@ -2922,7 +2902,8 @@ int perf_event__synthesize_attrs(struct perf_tool *tool, return err; } -int perf_event__process_attr(union perf_event *event, +int perf_event__process_attr(struct perf_tool *tool __maybe_unused, + union perf_event *event, struct perf_evlist **pevlist) { u32 i, ids, n_ids; @@ -2961,64 +2942,6 @@ int perf_event__process_attr(union perf_event *event, return 0; } -int perf_event__synthesize_event_type(struct perf_tool *tool, - u64 event_id, char *name, - perf_event__handler_t process, - struct machine *machine) -{ - union perf_event ev; - size_t size = 0; - int err = 0; - - memset(&ev, 0, sizeof(ev)); - - ev.event_type.event_type.event_id = event_id; - memset(ev.event_type.event_type.name, 0, MAX_EVENT_NAME); - strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1); - - ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE; - size = strlen(ev.event_type.event_type.name); - size = PERF_ALIGN(size, sizeof(u64)); - ev.event_type.header.size = sizeof(ev.event_type) - - (sizeof(ev.event_type.event_type.name) - size); - - err = process(tool, &ev, NULL, machine); - - return err; -} - -int perf_event__synthesize_event_types(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) -{ - struct perf_trace_event_type *type; - int i, err = 0; - - for (i = 0; i < trace_event_count; i++) { - type = &trace_events[i]; - - err = perf_event__synthesize_event_type(tool, type->event_id, - type->name, process, - machine); - if (err) { - pr_debug("failed to create perf header event type\n"); - return err; - } - } - - return err; -} - -int perf_event__process_event_type(struct perf_tool *tool __maybe_unused, - union perf_event *event) -{ - if (perf_header__push_event(event->event_type.event_type.event_id, - event->event_type.event_type.name) < 0) - return -ENOMEM; - - return 0; -} - int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct perf_evlist *evlist, perf_event__handler_t process) @@ -3065,22 +2988,24 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, return aligned_size; } -int perf_event__process_tracing_data(union perf_event *event, +int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused, + union perf_event *event, struct perf_session *session) { ssize_t size_read, padding, size = event->tracing_data.size; - off_t offset = lseek(session->fd, 0, SEEK_CUR); + int fd = perf_data_file__fd(session->file); + off_t offset = lseek(fd, 0, SEEK_CUR); char buf[BUFSIZ]; /* setup for reading amidst mmap */ - lseek(session->fd, offset + sizeof(struct tracing_data_event), + lseek(fd, offset + sizeof(struct tracing_data_event), SEEK_SET); - size_read = trace_report(session->fd, &session->pevent, + size_read = trace_report(fd, &session->pevent, session->repipe); padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read; - if (readn(session->fd, buf, padding) < 0) { + if (readn(fd, buf, padding) < 0) { pr_err("%s: reading input file", __func__); return -1; } diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 16a3e83c584..307c9aed972 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -34,6 +34,11 @@ enum { HEADER_FEAT_BITS = 256, }; +enum perf_header_version { + PERF_HEADER_VERSION_1, + PERF_HEADER_VERSION_2, +}; + struct perf_file_section { u64 offset; u64 size; @@ -45,6 +50,7 @@ struct perf_file_header { u64 attr_size; struct perf_file_section attrs; struct perf_file_section data; + /* event_types is ignored */ struct perf_file_section event_types; DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS); }; @@ -84,28 +90,24 @@ struct perf_session_env { }; struct perf_header { - bool needs_swap; - s64 attr_offset; - u64 data_offset; - u64 data_size; - u64 event_offset; - u64 event_size; + enum perf_header_version version; + bool needs_swap; + u64 data_offset; + u64 data_size; + u64 feat_offset; DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS); - struct perf_session_env env; + struct perf_session_env env; }; struct perf_evlist; struct perf_session; -int perf_session__read_header(struct perf_session *session, int fd); +int perf_session__read_header(struct perf_session *session); int perf_session__write_header(struct perf_session *session, struct perf_evlist *evlist, int fd, bool at_exit); int perf_header__write_pipe(int fd); -int perf_header__push_event(u64 id, const char *name); -char *perf_header__find_event(u64 id); - void perf_header__set_feat(struct perf_header *header, int feat); void perf_header__clear_feat(struct perf_header *header, int feat); bool perf_header__has_feat(const struct perf_header *header, int feat); @@ -130,22 +132,14 @@ int perf_event__synthesize_attr(struct perf_tool *tool, int perf_event__synthesize_attrs(struct perf_tool *tool, struct perf_session *session, perf_event__handler_t process); -int perf_event__process_attr(union perf_event *event, struct perf_evlist **pevlist); - -int perf_event__synthesize_event_type(struct perf_tool *tool, - u64 event_id, char *name, - perf_event__handler_t process, - struct machine *machine); -int perf_event__synthesize_event_types(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine); -int perf_event__process_event_type(struct perf_tool *tool, - union perf_event *event); +int perf_event__process_attr(struct perf_tool *tool, union perf_event *event, + struct perf_evlist **pevlist); int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct perf_evlist *evlist, perf_event__handler_t process); -int perf_event__process_tracing_data(union perf_event *event, +int perf_event__process_tracing_data(struct perf_tool *tool, + union perf_event *event, struct perf_session *session); int perf_event__synthesize_build_id(struct perf_tool *tool, diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index b11a6cfdb41..822903eaa20 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -24,7 +24,8 @@ enum hist_filter { struct callchain_param callchain_param = { .mode = CHAIN_GRAPH_REL, .min_percent = 0.5, - .order = ORDER_CALLEE + .order = ORDER_CALLEE, + .key = CCKEY_FUNCTION }; u16 hists__col_len(struct hists *hists, enum hist_column col) @@ -159,6 +160,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3); hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12); hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12); + + if (h->transaction) + hists__new_col_len(hists, HISTC_TRANSACTION, + hist_entry__transaction_len()); } void hists__output_recalc_col_len(struct hists *hists, int max_rows) @@ -345,7 +350,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists, struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; - int cmp; + int64_t cmp; p = &hists->entries_in->rb_node; @@ -394,6 +399,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists, if (!he) return NULL; + hists->nr_entries++; rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, hists->entries_in); out: @@ -401,74 +407,16 @@ out: return he; } -struct hist_entry *__hists__add_mem_entry(struct hists *self, - struct addr_location *al, - struct symbol *sym_parent, - struct mem_info *mi, - u64 period, - u64 weight) -{ - struct hist_entry entry = { - .thread = al->thread, - .ms = { - .map = al->map, - .sym = al->sym, - }, - .stat = { - .period = period, - .weight = weight, - .nr_events = 1, - }, - .cpu = al->cpu, - .ip = al->addr, - .level = al->level, - .parent = sym_parent, - .filtered = symbol__parent_filter(sym_parent), - .hists = self, - .mem_info = mi, - .branch_info = NULL, - }; - return add_hist_entry(self, &entry, al, period, weight); -} - -struct hist_entry *__hists__add_branch_entry(struct hists *self, - struct addr_location *al, - struct symbol *sym_parent, - struct branch_info *bi, - u64 period, - u64 weight) -{ - struct hist_entry entry = { - .thread = al->thread, - .ms = { - .map = bi->to.map, - .sym = bi->to.sym, - }, - .cpu = al->cpu, - .ip = bi->to.addr, - .level = al->level, - .stat = { - .period = period, - .nr_events = 1, - .weight = weight, - }, - .parent = sym_parent, - .filtered = symbol__parent_filter(sym_parent), - .branch_info = bi, - .hists = self, - .mem_info = NULL, - }; - - return add_hist_entry(self, &entry, al, period, weight); -} - -struct hist_entry *__hists__add_entry(struct hists *self, +struct hist_entry *__hists__add_entry(struct hists *hists, struct addr_location *al, - struct symbol *sym_parent, u64 period, - u64 weight) + struct symbol *sym_parent, + struct branch_info *bi, + struct mem_info *mi, + u64 period, u64 weight, u64 transaction) { struct hist_entry entry = { .thread = al->thread, + .comm = thread__comm(al->thread), .ms = { .map = al->map, .sym = al->sym, @@ -477,18 +425,19 @@ struct hist_entry *__hists__add_entry(struct hists *self, .ip = al->addr, .level = al->level, .stat = { - .period = period, .nr_events = 1, + .period = period, .weight = weight, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent), - .hists = self, - .branch_info = NULL, - .mem_info = NULL, + .hists = hists, + .branch_info = bi, + .mem_info = mi, + .transaction = transaction, }; - return add_hist_entry(self, &entry, al, period, weight); + return add_hist_entry(hists, &entry, al, period, weight); } int64_t @@ -529,6 +478,7 @@ void hist_entry__free(struct hist_entry *he) { free(he->branch_info); free(he->mem_info); + free_srcline(he->srcline); free(he); } @@ -597,7 +547,7 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he) hists__filter_entry_by_symbol(hists, he); } -void hists__collapse_resort(struct hists *hists) +void hists__collapse_resort(struct hists *hists, struct ui_progress *prog) { struct rb_root *root; struct rb_node *next; @@ -610,6 +560,8 @@ void hists__collapse_resort(struct hists *hists) next = rb_first(root); while (next) { + if (session_done()) + break; n = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&n->rb_node_in); @@ -622,6 +574,8 @@ void hists__collapse_resort(struct hists *hists) */ hists__apply_filters(hists, n); } + if (prog) + ui_progress__update(prog, 1); } } @@ -881,7 +835,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists, struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; - int cmp; + int64_t cmp; if (sort__need_collapse) root = &hists->entries_collapsed; @@ -912,6 +866,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists, rb_link_node(&he->rb_node_in, parent, p); rb_insert_color(&he->rb_node_in, root); hists__inc_nr_entries(hists, he); + he->dummy = true; } out: return he; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 2d3790fd99b..b621347a158 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -5,6 +5,8 @@ #include <pthread.h> #include "callchain.h" #include "header.h" +#include "color.h" +#include "ui/progress.h" extern struct callchain_param callchain_param; @@ -45,6 +47,8 @@ enum hist_column { HISTC_CPU, HISTC_SRCLINE, HISTC_MISPREDICT, + HISTC_IN_TX, + HISTC_ABORT, HISTC_SYMBOL_FROM, HISTC_SYMBOL_TO, HISTC_DSO_FROM, @@ -57,6 +61,7 @@ enum hist_column { HISTC_MEM_TLB, HISTC_MEM_LVL, HISTC_MEM_SNOOP, + HISTC_TRANSACTION, HISTC_NR_COLS, /* Last entry */ }; @@ -79,54 +84,43 @@ struct hists { u16 col_len[HISTC_NR_COLS]; }; -struct hist_entry *__hists__add_entry(struct hists *self, +struct hist_entry *__hists__add_entry(struct hists *hists, struct addr_location *al, - struct symbol *parent, u64 period, - u64 weight); + struct symbol *parent, + struct branch_info *bi, + struct mem_info *mi, u64 period, + u64 weight, u64 transaction); int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); -int hist_entry__sort_snprintf(struct hist_entry *self, char *bf, size_t size, +int hist_entry__transaction_len(void); +int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size, struct hists *hists); void hist_entry__free(struct hist_entry *); -struct hist_entry *__hists__add_branch_entry(struct hists *self, - struct addr_location *al, - struct symbol *sym_parent, - struct branch_info *bi, - u64 period, - u64 weight); - -struct hist_entry *__hists__add_mem_entry(struct hists *self, - struct addr_location *al, - struct symbol *sym_parent, - struct mem_info *mi, - u64 period, - u64 weight); - -void hists__output_resort(struct hists *self); -void hists__collapse_resort(struct hists *self); +void hists__output_resort(struct hists *hists); +void hists__collapse_resort(struct hists *hists, struct ui_progress *prog); void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel); void hists__output_recalc_col_len(struct hists *hists, int max_rows); void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h); -void hists__inc_nr_events(struct hists *self, u32 type); +void hists__inc_nr_events(struct hists *hists, u32 type); void events_stats__inc(struct events_stats *stats, u32 type); size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); -size_t hists__fprintf(struct hists *self, bool show_header, int max_rows, +size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp); -int hist_entry__inc_addr_samples(struct hist_entry *self, int evidx, u64 addr); -int hist_entry__annotate(struct hist_entry *self, size_t privsize); +int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr); +int hist_entry__annotate(struct hist_entry *he, size_t privsize); void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); void hists__filter_by_symbol(struct hists *hists); -u16 hists__col_len(struct hists *self, enum hist_column col); -void hists__set_col_len(struct hists *self, enum hist_column col, u16 len); -bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len); +u16 hists__col_len(struct hists *hists, enum hist_column col); +void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len); +bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len); void hists__reset_col_len(struct hists *hists); void hists__calc_col_len(struct hists *hists, struct hist_entry *he); @@ -141,10 +135,12 @@ struct perf_hpp { }; struct perf_hpp_fmt { - int (*header)(struct perf_hpp *hpp); - int (*width)(struct perf_hpp *hpp); - int (*color)(struct perf_hpp *hpp, struct hist_entry *he); - int (*entry)(struct perf_hpp *hpp, struct hist_entry *he); + int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp); + int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp); + int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he); + int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he); struct list_head list; }; @@ -157,7 +153,7 @@ extern struct list_head perf_hpp__list; extern struct perf_hpp_fmt perf_hpp__format[]; enum { - PERF_HPP__BASELINE, + /* Matches perf_hpp__format array. */ PERF_HPP__OVERHEAD, PERF_HPP__OVERHEAD_SYS, PERF_HPP__OVERHEAD_US, @@ -165,11 +161,6 @@ enum { PERF_HPP__OVERHEAD_GUEST_US, PERF_HPP__SAMPLES, PERF_HPP__PERIOD, - PERF_HPP__PERIOD_BASELINE, - PERF_HPP__DELTA, - PERF_HPP__RATIO, - PERF_HPP__WEIGHTED_DIFF, - PERF_HPP__FORMULA, PERF_HPP__MAX_INDEX }; @@ -177,8 +168,18 @@ enum { void perf_hpp__init(void); void perf_hpp__column_register(struct perf_hpp_fmt *format); void perf_hpp__column_enable(unsigned col); -int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he, - bool color); + +static inline size_t perf_hpp__use_color(void) +{ + return !symbol_conf.field_sep; +} + +static inline size_t perf_hpp__color_overhead(void) +{ + return perf_hpp__use_color() ? + (COLOR_MAXLEN + sizeof(PERF_COLOR_RESET)) * PERF_HPP__MAX_INDEX + : 0; +} struct perf_evlist; @@ -188,7 +189,7 @@ struct hist_browser_timer { int refresh; }; -#ifdef SLANG_SUPPORT +#ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel, struct hist_browser_timer *hbt); @@ -209,12 +210,9 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused, return 0; } -static inline int hist_entry__tui_annotate(struct hist_entry *self - __maybe_unused, - struct perf_evsel *evsel - __maybe_unused, - struct hist_browser_timer *hbt - __maybe_unused) +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) { return 0; } @@ -229,27 +227,5 @@ static inline int script_browse(const char *script_opt __maybe_unused) #define K_SWITCH_INPUT_DATA -3000 #endif -#ifdef GTK2_SUPPORT -int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help, - struct hist_browser_timer *hbt __maybe_unused, - float min_pcnt); -#else -static inline -int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused, - const char *help __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused, - float min_pcnt __maybe_unused) -{ - return 0; -} -#endif - -unsigned int hists__sort_list_width(struct hists *self); - -double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair); -double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair); -s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair); -int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair, - char *buf, size_t size); -double perf_diff__period_percent(struct hist_entry *he, u64 period); +unsigned int hists__sort_list_width(struct hists *hists); #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h index cf6727e99c4..8f149655f49 100644 --- a/tools/perf/util/include/dwarf-regs.h +++ b/tools/perf/util/include/dwarf-regs.h @@ -1,7 +1,7 @@ #ifndef _PERF_DWARF_REGS_H_ #define _PERF_DWARF_REGS_H_ -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT const char *get_arch_regstr(unsigned int n); #endif diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h index 96b919dae11..b003ad7200b 100644 --- a/tools/perf/util/include/linux/compiler.h +++ b/tools/perf/util/include/linux/compiler.h @@ -2,20 +2,29 @@ #define _PERF_LINUX_COMPILER_H_ #ifndef __always_inline -#define __always_inline inline +# define __always_inline inline __attribute__((always_inline)) #endif + #define __user + #ifndef __attribute_const__ -#define __attribute_const__ +# define __attribute_const__ #endif #ifndef __maybe_unused -#define __maybe_unused __attribute__((unused)) +# define __maybe_unused __attribute__((unused)) +#endif + +#ifndef __packed +# define __packed __attribute__((__packed__)) #endif -#define __packed __attribute__((__packed__)) #ifndef __force -#define __force +# define __force +#endif + +#ifndef __weak +# define __weak __attribute__((weak)) #endif #endif diff --git a/tools/perf/util/include/linux/magic.h b/tools/perf/util/include/linux/magic.h index 58b64ed4da1..07d63cf3e0f 100644 --- a/tools/perf/util/include/linux/magic.h +++ b/tools/perf/util/include/linux/magic.h @@ -9,4 +9,8 @@ #define SYSFS_MAGIC 0x62656572 #endif +#ifndef PROC_SUPER_MAGIC +#define PROC_SUPER_MAGIC 0x9fa0 +#endif + #endif diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h index 6f19c548ecc..97a80073822 100644 --- a/tools/perf/util/include/linux/string.h +++ b/tools/perf/util/include/linux/string.h @@ -1,3 +1,4 @@ #include <string.h> void *memdup(const void *src, size_t len); +int str_append(char **s, int *len, const char *a); diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c index 11a8d86f7fe..89715b64a31 100644 --- a/tools/perf/util/intlist.c +++ b/tools/perf/util/intlist.c @@ -20,6 +20,7 @@ static struct rb_node *intlist__node_new(struct rblist *rblist __maybe_unused, if (node != NULL) { node->i = i; + node->priv = NULL; rc = &node->rb_node; } @@ -57,22 +58,36 @@ void intlist__remove(struct intlist *ilist, struct int_node *node) rblist__remove_node(&ilist->rblist, &node->rb_node); } -struct int_node *intlist__find(struct intlist *ilist, int i) +static struct int_node *__intlist__findnew(struct intlist *ilist, + int i, bool create) { - struct int_node *node; + struct int_node *node = NULL; struct rb_node *rb_node; if (ilist == NULL) return NULL; - node = NULL; - rb_node = rblist__find(&ilist->rblist, (void *)((long)i)); + if (create) + rb_node = rblist__findnew(&ilist->rblist, (void *)((long)i)); + else + rb_node = rblist__find(&ilist->rblist, (void *)((long)i)); + if (rb_node) node = container_of(rb_node, struct int_node, rb_node); return node; } +struct int_node *intlist__find(struct intlist *ilist, int i) +{ + return __intlist__findnew(ilist, i, false); +} + +struct int_node *intlist__findnew(struct intlist *ilist, int i) +{ + return __intlist__findnew(ilist, i, true); +} + static int intlist__parse_list(struct intlist *ilist, const char *s) { char *sep; diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h index 62351dad848..aa6877d3685 100644 --- a/tools/perf/util/intlist.h +++ b/tools/perf/util/intlist.h @@ -9,6 +9,7 @@ struct int_node { struct rb_node rb_node; int i; + void *priv; }; struct intlist { @@ -23,6 +24,7 @@ int intlist__add(struct intlist *ilist, int i); struct int_node *intlist__entry(const struct intlist *ilist, unsigned int idx); struct int_node *intlist__find(struct intlist *ilist, int i); +struct int_node *intlist__findnew(struct intlist *ilist, int i); static inline bool intlist__has_entry(struct intlist *ilist, int i) { diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b2ecad6ec46..ce034c183a7 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -25,24 +25,44 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->kmaps.machine = machine; machine->pid = pid; + machine->symbol_filter = NULL; + machine->root_dir = strdup(root_dir); if (machine->root_dir == NULL) return -ENOMEM; if (pid != HOST_KERNEL_ID) { - struct thread *thread = machine__findnew_thread(machine, pid); + struct thread *thread = machine__findnew_thread(machine, 0, + pid); char comm[64]; if (thread == NULL) return -ENOMEM; snprintf(comm, sizeof(comm), "[guest/%d]", pid); - thread__set_comm(thread, comm); + thread__set_comm(thread, comm, 0); } return 0; } +struct machine *machine__new_host(void) +{ + struct machine *machine = malloc(sizeof(*machine)); + + if (machine != NULL) { + machine__init(machine, "", HOST_KERNEL_ID); + + if (machine__create_kernel_maps(machine) < 0) + goto out_delete; + } + + return machine; +out_delete: + free(machine); + return NULL; +} + static void dsos__delete(struct list_head *dsos) { struct dso *pos, *n; @@ -95,6 +115,7 @@ void machines__init(struct machines *machines) { machine__init(&machines->host, "", HOST_KERNEL_ID); machines->guests = RB_ROOT; + machines->symbol_filter = NULL; } void machines__exit(struct machines *machines) @@ -118,6 +139,8 @@ struct machine *machines__add(struct machines *machines, pid_t pid, return NULL; } + machine->symbol_filter = machines->symbol_filter; + while (*p != NULL) { parent = *p; pos = rb_entry(parent, struct machine, rb_node); @@ -133,6 +156,21 @@ struct machine *machines__add(struct machines *machines, pid_t pid, return machine; } +void machines__set_symbol_filter(struct machines *machines, + symbol_filter_t symbol_filter) +{ + struct rb_node *nd; + + machines->symbol_filter = symbol_filter; + machines->host.symbol_filter = symbol_filter; + + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + struct machine *machine = rb_entry(nd, struct machine, rb_node); + + machine->symbol_filter = symbol_filter; + } +} + struct machine *machines__find(struct machines *machines, pid_t pid) { struct rb_node **p = &machines->guests.rb_node; @@ -233,7 +271,8 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size) return; } -static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, +static struct thread *__machine__findnew_thread(struct machine *machine, + pid_t pid, pid_t tid, bool create) { struct rb_node **p = &machine->threads.rb_node; @@ -241,23 +280,28 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p struct thread *th; /* - * Font-end cache - PID lookups come in blocks, + * Front-end cache - TID lookups come in blocks, * so most of the time we dont have to look up * the full rbtree: */ - if (machine->last_match && machine->last_match->pid == pid) + if (machine->last_match && machine->last_match->tid == tid) { + if (pid && pid != machine->last_match->pid_) + machine->last_match->pid_ = pid; return machine->last_match; + } while (*p != NULL) { parent = *p; th = rb_entry(parent, struct thread, rb_node); - if (th->pid == pid) { + if (th->tid == tid) { machine->last_match = th; + if (pid && pid != th->pid_) + th->pid_ = pid; return th; } - if (pid < th->pid) + if (tid < th->tid) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -266,7 +310,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p if (!create) return NULL; - th = thread__new(pid); + th = thread__new(pid, tid); if (th != NULL) { rb_link_node(&th->rb_node, parent, p); rb_insert_color(&th->rb_node, &machine->threads); @@ -276,24 +320,28 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p return th; } -struct thread *machine__findnew_thread(struct machine *machine, pid_t pid) +struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, + pid_t tid) { - return __machine__findnew_thread(machine, pid, true); + return __machine__findnew_thread(machine, pid, tid, true); } -struct thread *machine__find_thread(struct machine *machine, pid_t pid) +struct thread *machine__find_thread(struct machine *machine, pid_t tid) { - return __machine__findnew_thread(machine, pid, false); + return __machine__findnew_thread(machine, 0, tid, false); } -int machine__process_comm_event(struct machine *machine, union perf_event *event) +int machine__process_comm_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample) { - struct thread *thread = machine__findnew_thread(machine, event->comm.tid); + struct thread *thread = machine__findnew_thread(machine, + event->comm.pid, + event->comm.tid); if (dump_trace) perf_event__fprintf_comm(event, stdout); - if (thread == NULL || thread__set_comm(thread, event->comm.comm)) { + if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) { dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); return -1; } @@ -302,7 +350,7 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event } int machine__process_lost_event(struct machine *machine __maybe_unused, - union perf_event *event) + union perf_event *event, struct perf_sample *sample __maybe_unused) { dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", event->lost.id, event->lost.lost); @@ -628,10 +676,8 @@ int machine__load_vmlinux_path(struct machine *machine, enum map_type type, struct map *map = machine->vmlinux_maps[type]; int ret = dso__load_vmlinux_path(map->dso, map, filter); - if (ret > 0) { + if (ret > 0) dso__set_loaded(map->dso, type); - map__reloc_vmlinux(map); - } return ret; } @@ -748,72 +794,44 @@ static int machine__set_modules_path(struct machine *machine) return map_groups__set_modules_path_dir(&machine->kmaps, modules_path); } -static int machine__create_modules(struct machine *machine) +static int machine__create_module(void *arg, const char *name, u64 start) { - char *line = NULL; - size_t n; - FILE *file; + struct machine *machine = arg; struct map *map; + + map = machine__new_module(machine, start, name); + if (map == NULL) + return -1; + + dso__kernel_module_get_build_id(map->dso, machine->root_dir); + + return 0; +} + +static int machine__create_modules(struct machine *machine) +{ const char *modules; char path[PATH_MAX]; - if (machine__is_default_guest(machine)) + if (machine__is_default_guest(machine)) { modules = symbol_conf.default_guest_modules; - else { - sprintf(path, "%s/proc/modules", machine->root_dir); + } else { + snprintf(path, PATH_MAX, "%s/proc/modules", machine->root_dir); modules = path; } - if (symbol__restricted_filename(path, "/proc/modules")) + if (symbol__restricted_filename(modules, "/proc/modules")) return -1; - file = fopen(modules, "r"); - if (file == NULL) + if (modules__parse(modules, machine, machine__create_module)) return -1; - while (!feof(file)) { - char name[PATH_MAX]; - u64 start; - char *sep; - int line_len; - - line_len = getline(&line, &n, file); - if (line_len < 0) - break; - - if (!line) - goto out_failure; - - line[--line_len] = '\0'; /* \n */ - - sep = strrchr(line, 'x'); - if (sep == NULL) - continue; - - hex2u64(sep + 1, &start); - - sep = strchr(line, ' '); - if (sep == NULL) - continue; - - *sep = '\0'; - - snprintf(name, sizeof(name), "[%s]", line); - map = machine__new_module(machine, start, name); - if (map == NULL) - goto out_delete_line; - dso__kernel_module_get_build_id(map->dso, machine->root_dir); - } - - free(line); - fclose(file); + if (!machine__set_modules_path(machine)) + return 0; - return machine__set_modules_path(machine); + pr_debug("Problems setting modules path maps, continuing anyway...\n"); -out_delete_line: - free(line); -out_failure: - return -1; + return 0; } int machine__create_kernel_maps(struct machine *machine) @@ -858,6 +876,18 @@ static void machine__set_kernel_mmap_len(struct machine *machine, } } +static bool machine__uses_kcore(struct machine *machine) +{ + struct dso *dso; + + list_for_each_entry(dso, &machine->kernel_dsos, node) { + if (dso__is_kcore(dso)) + return true; + } + + return false; +} + static int machine__process_kernel_mmap_event(struct machine *machine, union perf_event *event) { @@ -866,6 +896,10 @@ static int machine__process_kernel_mmap_event(struct machine *machine, enum dso_kernel_type kernel_type; bool is_kernel_mmap; + /* If we have maps from kcore then we do not need or want any others */ + 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; @@ -950,7 +984,9 @@ out_problem: return -1; } -int machine__process_mmap_event(struct machine *machine, union perf_event *event) +int machine__process_mmap2_event(struct machine *machine, + union perf_event *event, + struct perf_sample *sample __maybe_unused) { u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; struct thread *thread; @@ -959,7 +995,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event int ret = 0; if (dump_trace) - perf_event__fprintf_mmap(event, stdout); + perf_event__fprintf_mmap2(event, stdout); if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || cpumode == PERF_RECORD_MISC_KERNEL) { @@ -969,7 +1005,8 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event return 0; } - thread = machine__findnew_thread(machine, event->mmap.pid); + thread = machine__findnew_thread(machine, event->mmap2.pid, + event->mmap2.pid); if (thread == NULL) goto out_problem; @@ -978,10 +1015,12 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event else type = MAP__FUNCTION; - map = map__new(&machine->user_dsos, event->mmap.start, - event->mmap.len, event->mmap.pgoff, - event->mmap.pid, event->mmap.filename, - type); + map = map__new(&machine->user_dsos, event->mmap2.start, + event->mmap2.len, event->mmap2.pgoff, + event->mmap2.pid, event->mmap2.maj, + event->mmap2.min, event->mmap2.ino, + event->mmap2.ino_generation, + event->mmap2.filename, type); if (map == NULL) goto out_problem; @@ -990,24 +1029,54 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event return 0; out_problem: - dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n"); + dump_printf("problem processing PERF_RECORD_MMAP2, skipping event.\n"); return 0; } -int machine__process_fork_event(struct machine *machine, union perf_event *event) +int machine__process_mmap_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample __maybe_unused) { - struct thread *thread = machine__findnew_thread(machine, event->fork.tid); - struct thread *parent = machine__findnew_thread(machine, event->fork.ptid); + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + struct thread *thread; + struct map *map; + enum map_type type; + int ret = 0; if (dump_trace) - perf_event__fprintf_task(event, stdout); + perf_event__fprintf_mmap(event, stdout); - if (thread == NULL || parent == NULL || - thread__fork(thread, parent) < 0) { - dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); - return -1; + if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || + cpumode == PERF_RECORD_MISC_KERNEL) { + ret = machine__process_kernel_mmap_event(machine, event); + if (ret < 0) + goto out_problem; + return 0; } + thread = machine__findnew_thread(machine, event->mmap.pid, + event->mmap.pid); + 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->user_dsos, event->mmap.start, + event->mmap.len, event->mmap.pgoff, + event->mmap.pid, 0, 0, 0, 0, + event->mmap.filename, + type); + + if (map == NULL) + goto out_problem; + + thread__insert_map(thread, map); + return 0; + +out_problem: + dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n"); return 0; } @@ -1022,7 +1091,34 @@ static void machine__remove_thread(struct machine *machine, struct thread *th) list_add_tail(&th->node, &machine->dead_threads); } -int machine__process_exit_event(struct machine *machine, union perf_event *event) +int machine__process_fork_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample) +{ + struct thread *thread = machine__find_thread(machine, event->fork.tid); + struct thread *parent = machine__findnew_thread(machine, + event->fork.ppid, + event->fork.ptid); + + /* if a thread currently exists for the thread id remove it */ + if (thread != NULL) + machine__remove_thread(machine, thread); + + thread = machine__findnew_thread(machine, event->fork.pid, + event->fork.tid); + if (dump_trace) + perf_event__fprintf_task(event, stdout); + + if (thread == NULL || parent == NULL || + thread__fork(thread, parent, sample->time) < 0) { + dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); + return -1; + } + + return 0; +} + +int machine__process_exit_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample __maybe_unused) { struct thread *thread = machine__find_thread(machine, event->fork.tid); @@ -1030,26 +1126,29 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event perf_event__fprintf_task(event, stdout); if (thread != NULL) - machine__remove_thread(machine, thread); + thread__exited(thread); return 0; } -int machine__process_event(struct machine *machine, union perf_event *event) +int machine__process_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample) { int ret; switch (event->header.type) { case PERF_RECORD_COMM: - ret = machine__process_comm_event(machine, event); break; + ret = machine__process_comm_event(machine, event, sample); break; case PERF_RECORD_MMAP: - ret = machine__process_mmap_event(machine, event); break; + ret = machine__process_mmap_event(machine, event, sample); break; + case PERF_RECORD_MMAP2: + ret = machine__process_mmap2_event(machine, event, sample); break; case PERF_RECORD_FORK: - ret = machine__process_fork_event(machine, event); break; + ret = machine__process_fork_event(machine, event, sample); break; case PERF_RECORD_EXIT: - ret = machine__process_exit_event(machine, event); break; + ret = machine__process_exit_event(machine, event, sample); break; case PERF_RECORD_LOST: - ret = machine__process_lost_event(machine, event); break; + ret = machine__process_lost_event(machine, event, sample); break; default: ret = -1; break; @@ -1058,11 +1157,10 @@ int machine__process_event(struct machine *machine, union perf_event *event) return ret; } -static bool symbol__match_parent_regex(struct symbol *sym) +static bool symbol__match_regex(struct symbol *sym, regex_t *regex) { - if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0)) + if (sym->name && !regexec(regex, sym->name, 0, NULL, 0)) return 1; - return 0; } @@ -1094,7 +1192,7 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread, * or else, the symbol is unknown */ thread__find_addr_location(thread, machine, m, MAP__FUNCTION, - ip, &al, NULL); + ip, &al); if (al.sym) goto found; } @@ -1112,8 +1210,8 @@ static void ip__resolve_data(struct machine *machine, struct thread *thread, memset(&al, 0, sizeof(al)); - thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr, &al, - NULL); + thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr, + &al); ams->addr = addr; ams->al_addr = al.addr; ams->sym = al.sym; @@ -1159,11 +1257,13 @@ struct branch_info *machine__resolve_bstack(struct machine *machine, static int machine__resolve_callchain_sample(struct machine *machine, struct thread *thread, struct ip_callchain *chain, - struct symbol **parent) - + struct symbol **parent, + struct addr_location *root_al, + int max_stack) { u8 cpumode = PERF_RECORD_MISC_USER; - unsigned int i; + int chain_nr = min(max_stack, (int)chain->nr); + int i; int err; callchain_cursor_reset(&callchain_cursor); @@ -1173,7 +1273,7 @@ static int machine__resolve_callchain_sample(struct machine *machine, return 0; } - for (i = 0; i < chain->nr; i++) { + for (i = 0; i < chain_nr; i++) { u64 ip; struct addr_location al; @@ -1208,11 +1308,18 @@ static int machine__resolve_callchain_sample(struct machine *machine, al.filtered = false; thread__find_addr_location(thread, machine, cpumode, - MAP__FUNCTION, ip, &al, NULL); + MAP__FUNCTION, ip, &al); if (al.sym != NULL) { if (sort__has_parent && !*parent && - symbol__match_parent_regex(al.sym)) + symbol__match_regex(al.sym, &parent_regex)) *parent = al.sym; + else if (have_ignore_callees && root_al && + symbol__match_regex(al.sym, &ignore_callees_regex)) { + /* Treat this symbol as the root, + forgetting its callees. */ + *root_al = al; + callchain_cursor_reset(&callchain_cursor); + } if (!symbol_conf.use_callchain) break; } @@ -1237,15 +1344,15 @@ int machine__resolve_callchain(struct machine *machine, struct perf_evsel *evsel, struct thread *thread, struct perf_sample *sample, - struct symbol **parent) - + struct symbol **parent, + struct addr_location *root_al, + int max_stack) { int ret; - callchain_cursor_reset(&callchain_cursor); - ret = machine__resolve_callchain_sample(machine, thread, - sample->callchain, parent); + sample->callchain, parent, + root_al, max_stack); if (ret) return ret; @@ -1264,3 +1371,26 @@ int machine__resolve_callchain(struct machine *machine, sample); } + +int machine__for_each_thread(struct machine *machine, + int (*fn)(struct thread *thread, void *p), + void *priv) +{ + struct rb_node *nd; + struct thread *thread; + int rc = 0; + + for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) { + thread = rb_entry(nd, struct thread, rb_node); + rc = fn(thread, priv); + if (rc != 0) + return rc; + } + + list_for_each_entry(thread, &machine->dead_threads, node) { + rc = fn(thread, priv); + if (rc != 0) + return rc; + } + return rc; +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 77940680f1f..2389ba81faf 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -5,6 +5,7 @@ #include <linux/rbtree.h> #include "map.h" +struct addr_location; struct branch_stack; struct perf_evsel; struct perf_sample; @@ -28,6 +29,7 @@ struct machine { struct list_head kernel_dsos; struct map_groups kmaps; struct map *vmlinux_maps[MAP__NR_TYPES]; + symbol_filter_t symbol_filter; }; static inline @@ -36,20 +38,29 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type) return machine->vmlinux_maps[type]; } -struct thread *machine__find_thread(struct machine *machine, pid_t pid); - -int machine__process_comm_event(struct machine *machine, union perf_event *event); -int machine__process_exit_event(struct machine *machine, union perf_event *event); -int machine__process_fork_event(struct machine *machine, union perf_event *event); -int machine__process_lost_event(struct machine *machine, union perf_event *event); -int machine__process_mmap_event(struct machine *machine, union perf_event *event); -int machine__process_event(struct machine *machine, union perf_event *event); +struct thread *machine__find_thread(struct machine *machine, pid_t tid); + +int machine__process_comm_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_exit_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_fork_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_lost_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_mmap_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_mmap2_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); +int machine__process_event(struct machine *machine, union perf_event *event, + struct perf_sample *sample); typedef void (*machine__process_t)(struct machine *machine, void *data); struct machines { struct machine host; struct rb_root guests; + symbol_filter_t symbol_filter; }; void machines__init(struct machines *machines); @@ -67,6 +78,10 @@ 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_symbol_filter(struct machines *machines, + symbol_filter_t symbol_filter); + +struct machine *machine__new_host(void); int machine__init(struct machine *machine, const char *root_dir, pid_t pid); void machine__exit(struct machine *machine); void machine__delete_dead_threads(struct machine *machine); @@ -83,7 +98,9 @@ int machine__resolve_callchain(struct machine *machine, struct perf_evsel *evsel, struct thread *thread, struct perf_sample *sample, - struct symbol **parent); + struct symbol **parent, + struct addr_location *root_al, + int max_stack); /* * Default guest kernel is defined by parameter --guestkallsyms @@ -99,7 +116,8 @@ static inline bool machine__is_host(struct machine *machine) return machine ? machine->pid == HOST_KERNEL_ID : false; } -struct thread *machine__findnew_thread(struct machine *machine, pid_t pid); +struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, + pid_t tid); size_t machine__fprintf(struct machine *machine, FILE *fp); @@ -156,4 +174,8 @@ void machines__destroy_kernel_maps(struct machines *machines); size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp); +int machine__for_each_thread(struct machine *machine, + int (*fn)(struct thread *thread, void *p), + void *priv); + #endif /* __PERF_MACHINE_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 8bcdf9e5408..ef5bc913ca7 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -48,7 +48,8 @@ void map__init(struct map *map, enum map_type type, } struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, - u64 pgoff, u32 pid, char *filename, + u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, + u64 ino_gen, char *filename, enum map_type type) { struct map *map = malloc(sizeof(*map)); @@ -62,6 +63,11 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, vdso = is_vdso_map(filename); no_dso = is_no_dso_memory(filename); + map->maj = d_maj; + map->min = d_min; + map->ino = ino; + map->ino_generation = ino_gen; + if (anon) { snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid); filename = newfilename; @@ -166,7 +172,7 @@ int map__load(struct map *map, symbol_filter_t filter) pr_warning(", continuing without symbols\n"); return -1; } else if (nr == 0) { -#ifdef LIBELF_SUPPORT +#ifdef HAVE_LIBELF_SUPPORT const size_t len = strlen(name); const size_t real_len = len - sizeof(DSO__DELETED); @@ -182,12 +188,6 @@ int map__load(struct map *map, symbol_filter_t filter) #endif return -1; } - /* - * Only applies to the kernel, as its symtabs aren't relative like the - * module ones. - */ - if (map->dso->kernel) - map__reloc_vmlinux(map); return 0; } @@ -252,16 +252,49 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp) return fprintf(fp, "%s", dsoname); } -/* +/** + * map__rip_2objdump - convert symbol start address to objdump address. + * @map: memory map + * @rip: symbol start address + * * objdump wants/reports absolute IPs for ET_EXEC, and RIPs for ET_DYN. - * map->dso->adjust_symbols==1 for ET_EXEC-like cases. + * map->dso->adjust_symbols==1 for ET_EXEC-like cases except ET_REL which is + * relative to section start. + * + * Return: Address suitable for passing to "objdump --start-address=" */ u64 map__rip_2objdump(struct map *map, u64 rip) { - u64 addr = map->dso->adjust_symbols ? - map->unmap_ip(map, rip) : /* RIP -> IP */ - rip; - return addr; + if (!map->dso->adjust_symbols) + return rip; + + if (map->dso->rel) + return rip - map->pgoff; + + return map->unmap_ip(map, rip); +} + +/** + * map__objdump_2mem - convert objdump address to a memory address. + * @map: memory map + * @ip: objdump address + * + * Closely related to map__rip_2objdump(), this function takes an address from + * objdump and converts it to a memory address. Note this assumes that @map + * contains the address. To be sure the result is valid, check it forwards + * e.g. map__rip_2objdump(map->map_ip(map, map__objdump_2mem(map, ip))) == ip + * + * Return: Memory address. + */ +u64 map__objdump_2mem(struct map *map, u64 ip) +{ + if (!map->dso->adjust_symbols) + return map->unmap_ip(map, ip); + + if (map->dso->rel) + return map->unmap_ip(map, ip + map->pgoff); + + return ip; } void map_groups__init(struct map_groups *mg) @@ -367,6 +400,23 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, return NULL; } +int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter) +{ + 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); + if (ams->map == NULL) + return -1; + } + + ams->al_addr = ams->map->map_ip(ams->map, ams->addr); + ams->sym = map__find_symbol(ams->map, ams->al_addr, filter); + + return ams->sym ? 0 : -1; +} + size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, int verbose, FILE *fp) { @@ -513,35 +563,6 @@ int map_groups__clone(struct map_groups *mg, return 0; } -static u64 map__reloc_map_ip(struct map *map, u64 ip) -{ - return ip + (s64)map->pgoff; -} - -static u64 map__reloc_unmap_ip(struct map *map, u64 ip) -{ - return ip - (s64)map->pgoff; -} - -void map__reloc_vmlinux(struct map *map) -{ - struct kmap *kmap = map__kmap(map); - s64 reloc; - - if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr) - return; - - reloc = (kmap->ref_reloc_sym->unrelocated_addr - - kmap->ref_reloc_sym->addr); - - if (!reloc) - return; - - map->map_ip = map__reloc_map_ip; - map->unmap_ip = map__reloc_unmap_ip; - map->pgoff = reloc; -} - void maps__insert(struct rb_root *maps, struct map *map) { struct rb_node **p = &maps->rb_node; @@ -586,3 +607,21 @@ struct map *maps__find(struct rb_root *maps, u64 ip) return NULL; } + +struct map *maps__first(struct rb_root *maps) +{ + struct rb_node *first = rb_first(maps); + + if (first) + return rb_entry(first, struct map, rb_node); + return NULL; +} + +struct map *maps__next(struct map *map) +{ + struct rb_node *next = rb_next(&map->rb_node); + + if (next) + return rb_entry(next, struct map, rb_node); + return NULL; +} diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index a887f2c9dfb..e4e259c3ba1 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -36,6 +36,9 @@ struct map { bool erange_warned; u32 priv; u64 pgoff; + u32 maj, min; /* only valid for MMAP2 record */ + u64 ino; /* only valid for MMAP2 record */ + u64 ino_generation;/* only valid for MMAP2 record */ /* ip -> dso rip */ u64 (*map_ip)(struct map *, u64); @@ -81,6 +84,9 @@ static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip) /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */ u64 map__rip_2objdump(struct map *map, u64 rip); +/* objdump address -> memory address */ +u64 map__objdump_2mem(struct map *map, u64 ip); + struct symbol; typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); @@ -88,8 +94,9 @@ typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, - u64 pgoff, u32 pid, char *filename, - enum map_type type); + u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino, + u64 ino_gen, + char *filename, enum map_type type); struct map *map__new2(u64 start, struct dso *dso, enum map_type type); void map__delete(struct map *map); struct map *map__clone(struct map *map); @@ -112,6 +119,8 @@ size_t __map_groups__fprintf_maps(struct map_groups *mg, void maps__insert(struct rb_root *maps, struct map *map); void maps__remove(struct rb_root *maps, struct map *map); struct map *maps__find(struct rb_root *maps, u64 addr); +struct map *maps__first(struct rb_root *maps); +struct map *maps__next(struct map *map); void map_groups__init(struct map_groups *mg); void map_groups__exit(struct map_groups *mg); int map_groups__clone(struct map_groups *mg, @@ -139,6 +148,17 @@ static inline struct map *map_groups__find(struct map_groups *mg, return maps__find(&mg->maps[type], addr); } +static inline struct map *map_groups__first(struct map_groups *mg, + enum map_type type) +{ + return maps__first(&mg->maps[type]); +} + +static inline struct map *map_groups__next(struct map *map) +{ + return maps__next(map); +} + struct symbol *map_groups__find_symbol(struct map_groups *mg, enum map_type type, u64 addr, struct map **mapp, @@ -150,6 +170,10 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, struct map **mapp, symbol_filter_t filter); +struct addr_map_symbol; + +int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter); + static inline struct symbol *map_groups__find_function_by_name(struct map_groups *mg, const char *name, struct map **mapp, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 995fc25db8c..c90e55cf7e8 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -6,7 +6,7 @@ #include "parse-options.h" #include "parse-events.h" #include "exec_cmd.h" -#include "string.h" +#include "linux/string.h" #include "symbol.h" #include "cache.h" #include "header.h" @@ -15,6 +15,7 @@ #define YY_EXTRA_TYPE int #include "parse-events-flex.h" #include "pmu.h" +#include "thread_map.h" #define MAX_NAME_LEN 100 @@ -108,6 +109,10 @@ static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { .symbol = "emulation-faults", .alias = "", }, + [PERF_COUNT_SW_DUMMY] = { + .symbol = "dummy", + .alias = "", + }, }; #define __PERF_EVENT_FIELD(config, name) \ @@ -217,6 +222,29 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) return NULL; } +struct tracepoint_path *tracepoint_name_to_path(const char *name) +{ + struct tracepoint_path *path = zalloc(sizeof(*path)); + char *str = strchr(name, ':'); + + if (path == NULL || str == NULL) { + free(path); + return NULL; + } + + path->system = strndup(name, str - name); + path->name = strdup(str+1); + + if (path->system == NULL || path->name == NULL) { + free(path->system); + free(path->name); + free(path); + path = NULL; + } + + return path; +} + const char *event_type(int type) { switch (type) { @@ -241,40 +269,29 @@ const char *event_type(int type) -static int __add_event(struct list_head **_list, int *idx, +static int __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name, struct cpu_map *cpus) { struct perf_evsel *evsel; - struct list_head *list = *_list; - - if (!list) { - list = malloc(sizeof(*list)); - if (!list) - return -ENOMEM; - INIT_LIST_HEAD(list); - } event_attr_init(attr); evsel = perf_evsel__new(attr, (*idx)++); - if (!evsel) { - free(list); + if (!evsel) return -ENOMEM; - } evsel->cpus = cpus; if (name) evsel->name = strdup(name); list_add_tail(&evsel->node, list); - *_list = list; return 0; } -static int add_event(struct list_head **_list, int *idx, +static int add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, char *name) { - return __add_event(_list, idx, attr, name, NULL); + return __add_event(list, idx, attr, name, NULL); } static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size) @@ -295,7 +312,7 @@ static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES] return -1; } -int parse_events_add_cache(struct list_head **list, int *idx, +int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2) { struct perf_event_attr attr; @@ -356,31 +373,21 @@ int parse_events_add_cache(struct list_head **list, int *idx, return add_event(list, idx, &attr, name); } -static int add_tracepoint(struct list_head **listp, int *idx, +static int add_tracepoint(struct list_head *list, int *idx, char *sys_name, char *evt_name) { struct perf_evsel *evsel; - struct list_head *list = *listp; - - if (!list) { - list = malloc(sizeof(*list)); - if (!list) - return -ENOMEM; - INIT_LIST_HEAD(list); - } evsel = perf_evsel__newtp(sys_name, evt_name, (*idx)++); - if (!evsel) { - free(list); + if (!evsel) return -ENOMEM; - } list_add_tail(&evsel->node, list); - *listp = list; + return 0; } -static int add_tracepoint_multi_event(struct list_head **list, int *idx, +static int add_tracepoint_multi_event(struct list_head *list, int *idx, char *sys_name, char *evt_name) { char evt_path[MAXPATHLEN]; @@ -412,7 +419,7 @@ static int add_tracepoint_multi_event(struct list_head **list, int *idx, return ret; } -static int add_tracepoint_event(struct list_head **list, int *idx, +static int add_tracepoint_event(struct list_head *list, int *idx, char *sys_name, char *evt_name) { return strpbrk(evt_name, "*?") ? @@ -420,7 +427,7 @@ static int add_tracepoint_event(struct list_head **list, int *idx, add_tracepoint(list, idx, sys_name, evt_name); } -static int add_tracepoint_multi_sys(struct list_head **list, int *idx, +static int add_tracepoint_multi_sys(struct list_head *list, int *idx, char *sys_name, char *evt_name) { struct dirent *events_ent; @@ -452,7 +459,7 @@ static int add_tracepoint_multi_sys(struct list_head **list, int *idx, return ret; } -int parse_events_add_tracepoint(struct list_head **list, int *idx, +int parse_events_add_tracepoint(struct list_head *list, int *idx, char *sys, char *event) { int ret; @@ -507,7 +514,7 @@ do { \ return 0; } -int parse_events_add_breakpoint(struct list_head **list, int *idx, +int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type) { struct perf_event_attr attr; @@ -588,7 +595,7 @@ static int config_attr(struct perf_event_attr *attr, return 0; } -int parse_events_add_numeric(struct list_head **list, int *idx, +int parse_events_add_numeric(struct list_head *list, int *idx, u32 type, u64 config, struct list_head *head_config) { @@ -621,7 +628,7 @@ static char *pmu_event_name(struct list_head *head_terms) return NULL; } -int parse_events_add_pmu(struct list_head **list, int *idx, +int parse_events_add_pmu(struct list_head *list, int *idx, char *name, struct list_head *head_config) { struct perf_event_attr attr; @@ -664,6 +671,7 @@ void parse_events__set_leader(char *name, struct list_head *list) leader->group_name = name ? strdup(name) : NULL; } +/* list_event is assumed to point to malloc'ed memory */ void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all) { @@ -684,6 +692,8 @@ struct event_modifier { int eG; int precise; int exclude_GH; + int sample_read; + int pinned; }; static int get_event_modifier(struct event_modifier *mod, char *str, @@ -695,6 +705,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str, int eH = evsel ? evsel->attr.exclude_host : 0; int eG = evsel ? evsel->attr.exclude_guest : 0; int precise = evsel ? evsel->attr.precise_ip : 0; + int sample_read = 0; + int pinned = evsel ? evsel->attr.pinned : 0; int exclude = eu | ek | eh; int exclude_GH = evsel ? evsel->exclude_GH : 0; @@ -727,6 +739,10 @@ static int get_event_modifier(struct event_modifier *mod, char *str, /* use of precise requires exclude_guest */ if (!exclude_GH) eG = 1; + } else if (*str == 'S') { + sample_read = 1; + } else if (*str == 'D') { + pinned = 1; } else break; @@ -753,6 +769,9 @@ static int get_event_modifier(struct event_modifier *mod, char *str, mod->eG = eG; mod->precise = precise; mod->exclude_GH = exclude_GH; + mod->sample_read = sample_read; + mod->pinned = pinned; + return 0; } @@ -765,7 +784,7 @@ static int check_modifier(char *str) char *p = str; /* The sizeof includes 0 byte as well. */ - if (strlen(str) > (sizeof("ukhGHppp") - 1)) + if (strlen(str) > (sizeof("ukhGHpppSD") - 1)) return -1; while (*p) { @@ -803,6 +822,10 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) evsel->attr.exclude_host = mod.eH; evsel->attr.exclude_guest = mod.eG; evsel->exclude_GH = mod.exclude_GH; + evsel->sample_read = mod.sample_read; + + if (perf_evsel__is_group_leader(evsel)) + evsel->attr.pinned = mod.pinned; } return 0; @@ -820,6 +843,32 @@ int parse_events_name(struct list_head *list, char *name) return 0; } +static int parse_events__scanner(const char *str, void *data, int start_token); + +static int parse_events_fixup(int ret, const char *str, void *data, + int start_token) +{ + char *o = strdup(str); + char *s = NULL; + char *t = o; + char *p; + int len = 0; + + if (!o) + return ret; + while ((p = strsep(&t, ",")) != NULL) { + if (s) + str_append(&s, &len, ","); + str_append(&s, &len, "cpu/"); + str_append(&s, &len, p); + str_append(&s, &len, "/"); + } + free(o); + if (!s) + return -ENOMEM; + return parse_events__scanner(s, data, start_token); +} + static int parse_events__scanner(const char *str, void *data, int start_token) { YY_BUFFER_STATE buffer; @@ -840,6 +889,8 @@ static int parse_events__scanner(const char *str, void *data, int start_token) parse_events__flush_buffer(buffer, scanner); parse_events__delete_buffer(buffer, scanner); parse_events_lex_destroy(scanner); + if (ret && !strchr(str, '/')) + ret = parse_events_fixup(ret, str, data, start_token); return ret; } @@ -947,8 +998,10 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; - if (debugfs_valid_mountpoint(tracing_events_path)) + if (debugfs_valid_mountpoint(tracing_events_path)) { + printf(" [ Tracepoints not available: %s ]\n", strerror(errno)); return; + } sys_dir = opendir(tracing_events_path); if (!sys_dir) @@ -1026,6 +1079,33 @@ int is_valid_tracepoint(const char *event_string) return 0; } +static bool is_event_supported(u8 type, unsigned config) +{ + bool ret = true; + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = type, + .config = config, + .disabled = 1, + .exclude_kernel = 1, + }; + struct { + struct thread_map map; + int threads[1]; + } tmap = { + .map.nr = 1, + .threads = { 0 }, + }; + + evsel = perf_evsel__new(&attr, 0); + if (evsel) { + ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0; + perf_evsel__delete(evsel); + } + + return ret; +} + static void __print_events_type(u8 type, struct event_symbol *syms, unsigned max) { @@ -1033,14 +1113,16 @@ static void __print_events_type(u8 type, struct event_symbol *syms, unsigned i; for (i = 0; i < max ; i++, syms++) { + if (!is_event_supported(type, i)) + continue; + if (strlen(syms->alias)) snprintf(name, sizeof(name), "%s OR %s", syms->symbol, syms->alias); else snprintf(name, sizeof(name), "%s", syms->symbol); - printf(" %-50s [%s]\n", name, - event_type_descriptors[type]); + printf(" %-50s [%s]\n", name, event_type_descriptors[type]); } } @@ -1069,6 +1151,10 @@ int print_hwcache_events(const char *event_glob, bool name_only) if (event_glob != NULL && !strglobmatch(name, event_glob)) continue; + if (!is_event_supported(PERF_TYPE_HW_CACHE, + type | (op << 8) | (i << 16))) + continue; + if (name_only) printf("%s ", name); else @@ -1079,6 +1165,8 @@ int print_hwcache_events(const char *event_glob, bool name_only) } } + if (printed) + printf("\n"); return printed; } @@ -1096,6 +1184,9 @@ static void print_symbol_events(const char *event_glob, unsigned type, (syms->alias && strglobmatch(syms->alias, event_glob)))) continue; + if (!is_event_supported(type, i)) + continue; + if (name_only) { printf("%s ", syms->symbol); continue; @@ -1133,11 +1224,12 @@ void print_events(const char *event_glob, bool name_only) print_hwcache_events(event_glob, name_only); + print_pmu_events(event_glob, name_only); + if (event_glob != NULL) return; if (!name_only) { - printf("\n"); printf(" %-50s [%s]\n", "rNNN", event_type_descriptors[PERF_TYPE_RAW]); @@ -1237,6 +1329,4 @@ void parse_events__free_terms(struct list_head *terms) list_for_each_entry_safe(term, h, terms, list) free(term); - - free(terms); } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 8a4859315fd..f1cb4c4b3c7 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -23,6 +23,7 @@ struct tracepoint_path { }; extern struct tracepoint_path *tracepoint_id_to_path(u64 config); +extern struct tracepoint_path *tracepoint_name_to_path(const char *name); extern bool have_tracepoints(struct list_head *evlist); const char *event_type(int type); @@ -84,16 +85,16 @@ void parse_events__free_terms(struct list_head *terms); int parse_events__modifier_event(struct list_head *list, char *str, bool add); int parse_events__modifier_group(struct list_head *list, char *event_mod); int parse_events_name(struct list_head *list, char *name); -int parse_events_add_tracepoint(struct list_head **list, int *idx, +int parse_events_add_tracepoint(struct list_head *list, int *idx, char *sys, char *event); -int parse_events_add_numeric(struct list_head **list, int *idx, +int parse_events_add_numeric(struct list_head *list, int *idx, u32 type, u64 config, struct list_head *head_config); -int parse_events_add_cache(struct list_head **list, int *idx, +int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2); -int parse_events_add_breakpoint(struct list_head **list, int *idx, +int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type); -int parse_events_add_pmu(struct list_head **list, int *idx, +int parse_events_add_pmu(struct list_head *list, int *idx, char *pmu , struct list_head *head_config); void parse_events__set_leader(char *name, struct list_head *list); void parse_events_update_lists(struct list_head *list_event, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index e9d1134c2c6..343299575b3 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -82,7 +82,8 @@ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ name [a-zA-Z_*?][a-zA-Z0-9_*?]* name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?]* -modifier_event [ukhpGH]+ +/* If you add a modifier you need to update check_modifier() */ +modifier_event [ukhpGHSD]+ modifier_bp [rwx]{1,3} %% @@ -125,6 +126,37 @@ modifier_bp [rwx]{1,3} } +<config>{ +config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); } +config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); } +config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); } +name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); } +period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } +branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); } +, { return ','; } +"/" { BEGIN(INITIAL); return '/'; } +{name_minus} { return str(yyscanner, PE_NAME); } +} + +<mem>{ +{modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); } +: { return ':'; } +{num_dec} { return value(yyscanner, 10); } +{num_hex} { return value(yyscanner, 16); } + /* + * We need to separate 'mem:' scanner part, in order to get specific + * modifier bits parsed out. Otherwise we would need to handle PE_NAME + * and we'd need to parse it manually. During the escape from <mem> + * state we need to put the escaping char back, so we dont miss it. + */ +. { unput(*yytext); BEGIN(INITIAL); } + /* + * We destroy the scanner after reaching EOF, + * but anyway just to be sure get back to INIT state. + */ +<<EOF>> { BEGIN(INITIAL); } +} + cpu-cycles|cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); } stalled-cycles-frontend|idle-cycles-frontend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } stalled-cycles-backend|idle-cycles-backend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } @@ -144,6 +176,7 @@ context-switches|cs { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); } alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } +dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } L1-dcache|l1-d|l1d|L1-data | L1-icache|l1-i|l1i|L1-instruction | @@ -160,18 +193,6 @@ speculative-read|speculative-load | refs|Reference|ops|access | misses|miss { return str(yyscanner, PE_NAME_CACHE_OP_RESULT); } -<config>{ -config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); } -config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); } -config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); } -name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); } -period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } -branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); } -, { return ','; } -"/" { BEGIN(INITIAL); return '/'; } -{name_minus} { return str(yyscanner, PE_NAME); } -} - mem: { BEGIN(mem); return PE_PREFIX_MEM; } r{num_raw_hex} { return raw(yyscanner); } {num_dec} { return value(yyscanner, 10); } @@ -187,25 +208,7 @@ r{num_raw_hex} { return raw(yyscanner); } "}" { return '}'; } = { return '='; } \n { } - -<mem>{ -{modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); } -: { return ':'; } -{num_dec} { return value(yyscanner, 10); } -{num_hex} { return value(yyscanner, 16); } - /* - * We need to separate 'mem:' scanner part, in order to get specific - * modifier bits parsed out. Otherwise we would need to handle PE_NAME - * and we'd need to parse it manually. During the escape from <mem> - * state we need to put the escaping char back, so we dont miss it. - */ -. { unput(*yytext); BEGIN(INITIAL); } - /* - * We destroy the scanner after reaching EOF, - * but anyway just to be sure get back to INIT state. - */ -<<EOF>> { BEGIN(INITIAL); } -} +. { } %% diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index afc44c18dfe..4eb67ec333f 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -22,6 +22,13 @@ do { \ YYABORT; \ } while (0) +#define ALLOC_LIST(list) \ +do { \ + list = malloc(sizeof(*list)); \ + ABORT_ON(!list); \ + INIT_LIST_HEAD(list); \ +} while (0) + static inc_group_count(struct list_head *list, struct parse_events_evlist *data) { @@ -196,9 +203,10 @@ event_pmu: PE_NAME '/' event_config '/' { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_pmu(&list, &data->idx, $1, $3)); + ALLOC_LIST(list); + ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, $3)); parse_events__free_terms($3); $$ = list; } @@ -212,11 +220,12 @@ event_legacy_symbol: value_sym '/' event_config '/' { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; int type = $1 >> 16; int config = $1 & 255; - ABORT_ON(parse_events_add_numeric(&list, &data->idx, + ALLOC_LIST(list); + ABORT_ON(parse_events_add_numeric(list, &data->idx, type, config, $3)); parse_events__free_terms($3); $$ = list; @@ -225,11 +234,12 @@ value_sym '/' event_config '/' value_sym sep_slash_dc { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; int type = $1 >> 16; int config = $1 & 255; - ABORT_ON(parse_events_add_numeric(&list, &data->idx, + ALLOC_LIST(list); + ABORT_ON(parse_events_add_numeric(list, &data->idx, type, config, NULL)); $$ = list; } @@ -238,27 +248,30 @@ event_legacy_cache: PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, $5)); + ALLOC_LIST(list); + ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5)); $$ = list; } | PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, NULL)); + ALLOC_LIST(list); + ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL)); $$ = list; } | PE_NAME_CACHE_TYPE { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, NULL, NULL)); + ALLOC_LIST(list); + ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL)); $$ = list; } @@ -266,9 +279,10 @@ event_legacy_mem: PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_breakpoint(&list, &data->idx, + ALLOC_LIST(list); + ABORT_ON(parse_events_add_breakpoint(list, &data->idx, (void *) $2, $4)); $$ = list; } @@ -276,9 +290,10 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc PE_PREFIX_MEM PE_VALUE sep_dc { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_breakpoint(&list, &data->idx, + ALLOC_LIST(list); + ABORT_ON(parse_events_add_breakpoint(list, &data->idx, (void *) $2, NULL)); $$ = list; } @@ -287,9 +302,10 @@ event_legacy_tracepoint: PE_NAME ':' PE_NAME { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_tracepoint(&list, &data->idx, $1, $3)); + ALLOC_LIST(list); + ABORT_ON(parse_events_add_tracepoint(list, &data->idx, $1, $3)); $$ = list; } @@ -297,9 +313,10 @@ event_legacy_numeric: PE_VALUE ':' PE_VALUE { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_numeric(&list, &data->idx, (u32)$1, $3, NULL)); + ALLOC_LIST(list); + ABORT_ON(parse_events_add_numeric(list, &data->idx, (u32)$1, $3, NULL)); $$ = list; } @@ -307,9 +324,10 @@ event_legacy_raw: PE_RAW { struct parse_events_evlist *data = _data; - struct list_head *list = NULL; + struct list_head *list; - ABORT_ON(parse_events_add_numeric(&list, &data->idx, + ALLOC_LIST(list); + ABORT_ON(parse_events_add_numeric(list, &data->idx, PERF_TYPE_RAW, $1, NULL)); $$ = list; } diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c index 2bc9e70df7e..31f404a032a 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/perf/util/parse-options.c @@ -339,10 +339,10 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, if (arg[1] != '-') { ctx->opt = arg + 1; if (internal_help && *ctx->opt == 'h') - return parse_options_usage(usagestr, options); + return usage_with_options_internal(usagestr, options, 0); switch (parse_short_opt(ctx, options)) { case -1: - return parse_options_usage(usagestr, options); + return parse_options_usage(usagestr, options, arg + 1, 1); case -2: goto unknown; default: @@ -352,10 +352,11 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, check_typos(arg + 1, options); while (ctx->opt) { if (internal_help && *ctx->opt == 'h') - return parse_options_usage(usagestr, options); + return usage_with_options_internal(usagestr, options, 0); + arg = ctx->opt; switch (parse_short_opt(ctx, options)) { case -1: - return parse_options_usage(usagestr, options); + return parse_options_usage(usagestr, options, arg, 1); case -2: /* fake a short option thing to hide the fact that we may have * started to parse aggregated stuff @@ -383,12 +384,12 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, if (internal_help && !strcmp(arg + 2, "help-all")) return usage_with_options_internal(usagestr, options, 1); if (internal_help && !strcmp(arg + 2, "help")) - return parse_options_usage(usagestr, options); + return usage_with_options_internal(usagestr, options, 0); if (!strcmp(arg + 2, "list-opts")) return PARSE_OPT_LIST; switch (parse_long_opt(ctx, arg + 2, options)) { case -1: - return parse_options_usage(usagestr, options); + return parse_options_usage(usagestr, options, arg + 2, 0); case -2: goto unknown; default: @@ -445,6 +446,89 @@ int parse_options(int argc, const char **argv, const struct option *options, #define USAGE_OPTS_WIDTH 24 #define USAGE_GAP 2 +static void print_option_help(const struct option *opts, int full) +{ + size_t pos; + int pad; + + if (opts->type == OPTION_GROUP) { + fputc('\n', stderr); + if (*opts->help) + fprintf(stderr, "%s\n", opts->help); + return; + } + if (!full && (opts->flags & PARSE_OPT_HIDDEN)) + return; + + pos = fprintf(stderr, " "); + if (opts->short_name) + pos += fprintf(stderr, "-%c", opts->short_name); + else + pos += fprintf(stderr, " "); + + if (opts->long_name && opts->short_name) + pos += fprintf(stderr, ", "); + if (opts->long_name) + pos += fprintf(stderr, "--%s", opts->long_name); + + switch (opts->type) { + case OPTION_ARGUMENT: + break; + case OPTION_LONG: + case OPTION_U64: + case OPTION_INTEGER: + case OPTION_UINTEGER: + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=<n>]"); + else + pos += fprintf(stderr, "[<n>]"); + else + pos += fprintf(stderr, " <n>"); + break; + case OPTION_CALLBACK: + if (opts->flags & PARSE_OPT_NOARG) + break; + /* FALLTHROUGH */ + case OPTION_STRING: + if (opts->argh) { + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=<%s>]", opts->argh); + else + pos += fprintf(stderr, "[<%s>]", opts->argh); + else + pos += fprintf(stderr, " <%s>", opts->argh); + } else { + if (opts->flags & PARSE_OPT_OPTARG) + if (opts->long_name) + pos += fprintf(stderr, "[=...]"); + else + pos += fprintf(stderr, "[...]"); + else + pos += fprintf(stderr, " ..."); + } + break; + default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */ + case OPTION_END: + case OPTION_GROUP: + case OPTION_BIT: + case OPTION_BOOLEAN: + case OPTION_INCR: + case OPTION_SET_UINT: + case OPTION_SET_PTR: + break; + } + + if (pos <= USAGE_OPTS_WIDTH) + pad = USAGE_OPTS_WIDTH - pos; + else { + fputc('\n', stderr); + pad = USAGE_OPTS_WIDTH; + } + fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help); +} + int usage_with_options_internal(const char * const *usagestr, const struct option *opts, int full) { @@ -464,87 +548,9 @@ int usage_with_options_internal(const char * const *usagestr, if (opts->type != OPTION_GROUP) fputc('\n', stderr); - for (; opts->type != OPTION_END; opts++) { - size_t pos; - int pad; - - if (opts->type == OPTION_GROUP) { - fputc('\n', stderr); - if (*opts->help) - fprintf(stderr, "%s\n", opts->help); - continue; - } - if (!full && (opts->flags & PARSE_OPT_HIDDEN)) - continue; - - pos = fprintf(stderr, " "); - if (opts->short_name) - pos += fprintf(stderr, "-%c", opts->short_name); - else - pos += fprintf(stderr, " "); - - if (opts->long_name && opts->short_name) - pos += fprintf(stderr, ", "); - if (opts->long_name) - pos += fprintf(stderr, "--%s", opts->long_name); - - switch (opts->type) { - case OPTION_ARGUMENT: - break; - case OPTION_LONG: - case OPTION_U64: - case OPTION_INTEGER: - case OPTION_UINTEGER: - if (opts->flags & PARSE_OPT_OPTARG) - if (opts->long_name) - pos += fprintf(stderr, "[=<n>]"); - else - pos += fprintf(stderr, "[<n>]"); - else - pos += fprintf(stderr, " <n>"); - break; - case OPTION_CALLBACK: - if (opts->flags & PARSE_OPT_NOARG) - break; - /* FALLTHROUGH */ - case OPTION_STRING: - if (opts->argh) { - if (opts->flags & PARSE_OPT_OPTARG) - if (opts->long_name) - pos += fprintf(stderr, "[=<%s>]", opts->argh); - else - pos += fprintf(stderr, "[<%s>]", opts->argh); - else - pos += fprintf(stderr, " <%s>", opts->argh); - } else { - if (opts->flags & PARSE_OPT_OPTARG) - if (opts->long_name) - pos += fprintf(stderr, "[=...]"); - else - pos += fprintf(stderr, "[...]"); - else - pos += fprintf(stderr, " ..."); - } - break; - default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */ - case OPTION_END: - case OPTION_GROUP: - case OPTION_BIT: - case OPTION_BOOLEAN: - case OPTION_INCR: - case OPTION_SET_UINT: - case OPTION_SET_PTR: - break; - } + for ( ; opts->type != OPTION_END; opts++) + print_option_help(opts, full); - if (pos <= USAGE_OPTS_WIDTH) - pad = USAGE_OPTS_WIDTH - pos; - else { - fputc('\n', stderr); - pad = USAGE_OPTS_WIDTH; - } - fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help); - } fputc('\n', stderr); return PARSE_OPT_HELP; @@ -559,9 +565,45 @@ void usage_with_options(const char * const *usagestr, } int parse_options_usage(const char * const *usagestr, - const struct option *opts) + const struct option *opts, + const char *optstr, bool short_opt) { - return usage_with_options_internal(usagestr, opts, 0); + if (!usagestr) + goto opt; + + fprintf(stderr, "\n usage: %s\n", *usagestr++); + while (*usagestr && **usagestr) + fprintf(stderr, " or: %s\n", *usagestr++); + while (*usagestr) { + fprintf(stderr, "%s%s\n", + **usagestr ? " " : "", + *usagestr); + usagestr++; + } + fputc('\n', stderr); + +opt: + for ( ; opts->type != OPTION_END; opts++) { + if (short_opt) { + if (opts->short_name == *optstr) + break; + continue; + } + + if (opts->long_name == NULL) + continue; + + if (!prefixcmp(optstr, opts->long_name)) + break; + if (!prefixcmp(optstr, "no-") && + !prefixcmp(optstr + 3, opts->long_name)) + break; + } + + if (opts->type != OPTION_END) + print_option_help(opts, 0); + + return PARSE_OPT_HELP; } diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h index 7bb5999940c..b0241e28eaf 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/perf/util/parse-options.h @@ -158,7 +158,9 @@ struct parse_opt_ctx_t { }; extern int parse_options_usage(const char * const *usagestr, - const struct option *opts); + const struct option *opts, + const char *optstr, + bool short_opt); extern void parse_options_start(struct parse_opt_ctx_t *ctx, int argc, const char **argv, int flags); diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index a8c49548ca4..5d13cb45b31 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -22,19 +22,23 @@ static const char *get_perf_dir(void) return "."; } -#ifndef HAVE_STRLCPY -size_t strlcpy(char *dest, const char *src, size_t size) +/* + * If libc has strlcpy() then that version will override this + * implementation: + */ +size_t __weak strlcpy(char *dest, const char *src, size_t size) { size_t ret = strlen(src); if (size) { size_t len = (ret >= size) ? size - 1 : ret; + memcpy(dest, src, len); dest[len] = '\0'; } + return ret; } -#endif static char *get_pathname(void) { diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index 5a4f2b6f373..a3d42cd7491 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -1,7 +1,7 @@ #ifndef __PERF_REGS_H #define __PERF_REGS_H -#ifdef HAVE_PERF_REGS +#ifdef HAVE_PERF_REGS_SUPPORT #include <perf_regs.h> #else #define PERF_REGS_MASK 0 @@ -10,5 +10,5 @@ static inline const char *perf_reg_name(int id __maybe_unused) { return NULL; } -#endif /* HAVE_PERF_REGS */ +#endif /* HAVE_PERF_REGS_SUPPORT */ #endif /* __PERF_REGS_H */ diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 4c6f9c490a8..c232d8dd410 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -4,7 +4,7 @@ #include <unistd.h> #include <stdio.h> #include <dirent.h> -#include "sysfs.h" +#include "fs.h" #include "util.h" #include "pmu.h" #include "parse-events.h" @@ -73,13 +73,12 @@ int perf_pmu__format_parse(char *dir, struct list_head *head) * located at: * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes. */ -static int pmu_format(char *name, struct list_head *format) +static int pmu_format(const char *name, struct list_head *format) { struct stat st; char path[PATH_MAX]; - const char *sysfs; + const char *sysfs = sysfs__mountpoint(); - sysfs = sysfs_find_mountpoint(); if (!sysfs) return -1; @@ -162,13 +161,12 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) * Reading the pmu event aliases definition, which should be located at: * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes. */ -static int pmu_aliases(char *name, struct list_head *head) +static int pmu_aliases(const char *name, struct list_head *head) { struct stat st; char path[PATH_MAX]; - const char *sysfs; + const char *sysfs = sysfs__mountpoint(); - sysfs = sysfs_find_mountpoint(); if (!sysfs) return -1; @@ -208,15 +206,14 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias, * located at: * /sys/bus/event_source/devices/<dev>/type as sysfs attribute. */ -static int pmu_type(char *name, __u32 *type) +static int pmu_type(const char *name, __u32 *type) { struct stat st; char path[PATH_MAX]; - const char *sysfs; FILE *file; int ret = 0; + const char *sysfs = sysfs__mountpoint(); - sysfs = sysfs_find_mountpoint(); if (!sysfs) return -1; @@ -241,11 +238,10 @@ static int pmu_type(char *name, __u32 *type) static void pmu_read_sysfs(void) { char path[PATH_MAX]; - const char *sysfs; DIR *dir; struct dirent *dent; + const char *sysfs = sysfs__mountpoint(); - sysfs = sysfs_find_mountpoint(); if (!sysfs) return; @@ -266,15 +262,14 @@ static void pmu_read_sysfs(void) closedir(dir); } -static struct cpu_map *pmu_cpumask(char *name) +static struct cpu_map *pmu_cpumask(const char *name) { struct stat st; char path[PATH_MAX]; - const char *sysfs; FILE *file; struct cpu_map *cpus; + const char *sysfs = sysfs__mountpoint(); - sysfs = sysfs_find_mountpoint(); if (!sysfs) return NULL; @@ -293,7 +288,7 @@ static struct cpu_map *pmu_cpumask(char *name) return cpus; } -static struct perf_pmu *pmu_lookup(char *name) +static struct perf_pmu *pmu_lookup(const char *name) { struct perf_pmu *pmu; LIST_HEAD(format); @@ -330,7 +325,7 @@ static struct perf_pmu *pmu_lookup(char *name) return pmu; } -static struct perf_pmu *pmu_find(char *name) +static struct perf_pmu *pmu_find(const char *name) { struct perf_pmu *pmu; @@ -356,7 +351,7 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu) return NULL; } -struct perf_pmu *perf_pmu__find(char *name) +struct perf_pmu *perf_pmu__find(const char *name) { struct perf_pmu *pmu; @@ -564,3 +559,92 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to) for (b = from; b <= to; b++) set_bit(b, bits); } + +static char *format_alias(char *buf, int len, struct perf_pmu *pmu, + struct perf_pmu_alias *alias) +{ + snprintf(buf, len, "%s/%s/", pmu->name, alias->name); + return buf; +} + +static char *format_alias_or(char *buf, int len, struct perf_pmu *pmu, + struct perf_pmu_alias *alias) +{ + snprintf(buf, len, "%s OR %s/%s/", alias->name, pmu->name, alias->name); + return buf; +} + +static int cmp_string(const void *a, const void *b) +{ + const char * const *as = a; + const char * const *bs = b; + return strcmp(*as, *bs); +} + +void print_pmu_events(const char *event_glob, bool name_only) +{ + struct perf_pmu *pmu; + struct perf_pmu_alias *alias; + char buf[1024]; + int printed = 0; + int len, j; + char **aliases; + + pmu = NULL; + len = 0; + while ((pmu = perf_pmu__scan(pmu)) != NULL) + list_for_each_entry(alias, &pmu->aliases, list) + len++; + aliases = malloc(sizeof(char *) * len); + if (!aliases) + return; + pmu = NULL; + j = 0; + while ((pmu = perf_pmu__scan(pmu)) != NULL) + list_for_each_entry(alias, &pmu->aliases, list) { + char *name = format_alias(buf, sizeof(buf), pmu, alias); + bool is_cpu = !strcmp(pmu->name, "cpu"); + + if (event_glob != NULL && + !(strglobmatch(name, event_glob) || + (!is_cpu && strglobmatch(alias->name, + event_glob)))) + continue; + aliases[j] = name; + if (is_cpu && !name_only) + aliases[j] = format_alias_or(buf, sizeof(buf), + pmu, alias); + aliases[j] = strdup(aliases[j]); + j++; + } + len = j; + qsort(aliases, len, sizeof(char *), cmp_string); + for (j = 0; j < len; j++) { + if (name_only) { + printf("%s ", aliases[j]); + continue; + } + printf(" %-50s [Kernel PMU event]\n", aliases[j]); + free(aliases[j]); + printed++; + } + if (printed) + printf("\n"); + free(aliases); +} + +bool pmu_have_event(const char *pname, const char *name) +{ + struct perf_pmu *pmu; + struct perf_pmu_alias *alias; + + pmu = NULL; + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + if (strcmp(pname, pmu->name)) + continue; + list_for_each_entry(alias, &pmu->aliases, list) + if (!strcmp(alias->name, name)) + return true; + } + return false; +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 32fe55b659f..1179b26f244 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -3,6 +3,7 @@ #include <linux/bitops.h> #include <linux/perf_event.h> +#include <stdbool.h> enum { PERF_PMU_FORMAT_VALUE_CONFIG, @@ -21,7 +22,7 @@ struct perf_pmu { struct list_head list; }; -struct perf_pmu *perf_pmu__find(char *name); +struct perf_pmu *perf_pmu__find(const char *name); int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms); int perf_pmu__config_terms(struct list_head *formats, @@ -40,5 +41,8 @@ int perf_pmu__format_parse(char *dir, struct list_head *head); struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); +void print_pmu_events(const char *event_glob, bool name_only); +bool pmu_have_event(const char *pname, const char *name); + int perf_pmu__test(void); #endif /* __PMU_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index aa04bf9c9ad..9c6989ca2be 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -47,7 +47,6 @@ #include "session.h" #define MAX_CMDLEN 256 -#define MAX_PROBE_ARGS 128 #define PERFPROBE_GROUP "probe" bool probe_event_dry_run; /* Dry run flag */ @@ -201,7 +200,7 @@ static int convert_to_perf_probe_point(struct probe_trace_point *tp, return 0; } -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT /* Open new debuginfo of given module */ static struct debuginfo *open_debuginfo(const char *module) { @@ -630,7 +629,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, return ret; } -#else /* !DWARF_SUPPORT */ +#else /* !HAVE_DWARF_SUPPORT */ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp, struct perf_probe_point *pp) diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index be0329394d5..ffb657ffd32 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -115,35 +115,34 @@ static const Dwfl_Callbacks offline_callbacks = { }; /* Get a Dwarf from offline image */ -static int debuginfo__init_offline_dwarf(struct debuginfo *self, +static int debuginfo__init_offline_dwarf(struct debuginfo *dbg, const char *path) { - Dwfl_Module *mod; int fd; fd = open(path, O_RDONLY); if (fd < 0) return fd; - self->dwfl = dwfl_begin(&offline_callbacks); - if (!self->dwfl) + dbg->dwfl = dwfl_begin(&offline_callbacks); + if (!dbg->dwfl) goto error; - mod = dwfl_report_offline(self->dwfl, "", "", fd); - if (!mod) + dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd); + if (!dbg->mod) goto error; - self->dbg = dwfl_module_getdwarf(mod, &self->bias); - if (!self->dbg) + dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias); + if (!dbg->dbg) goto error; return 0; error: - if (self->dwfl) - dwfl_end(self->dwfl); + if (dbg->dwfl) + dwfl_end(dbg->dwfl); else close(fd); - memset(self, 0, sizeof(*self)); + memset(dbg, 0, sizeof(*dbg)); return -ENOENT; } @@ -181,24 +180,24 @@ static const Dwfl_Callbacks kernel_callbacks = { }; /* Get a Dwarf from live kernel image */ -static int debuginfo__init_online_kernel_dwarf(struct debuginfo *self, +static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg, Dwarf_Addr addr) { - self->dwfl = dwfl_begin(&kernel_callbacks); - if (!self->dwfl) + dbg->dwfl = dwfl_begin(&kernel_callbacks); + if (!dbg->dwfl) return -EINVAL; /* Load the kernel dwarves: Don't care the result here */ - dwfl_linux_kernel_report_kernel(self->dwfl); - dwfl_linux_kernel_report_modules(self->dwfl); + dwfl_linux_kernel_report_kernel(dbg->dwfl); + dwfl_linux_kernel_report_modules(dbg->dwfl); - self->dbg = dwfl_addrdwarf(self->dwfl, addr, &self->bias); + dbg->dbg = dwfl_addrdwarf(dbg->dwfl, addr, &dbg->bias); /* Here, check whether we could get a real dwarf */ - if (!self->dbg) { + if (!dbg->dbg) { pr_debug("Failed to find kernel dwarf at %lx\n", (unsigned long)addr); - dwfl_end(self->dwfl); - memset(self, 0, sizeof(*self)); + dwfl_end(dbg->dwfl); + memset(dbg, 0, sizeof(*dbg)); return -ENOENT; } @@ -206,7 +205,7 @@ static int debuginfo__init_online_kernel_dwarf(struct debuginfo *self, } #else /* With older elfutils, this just support kernel module... */ -static int debuginfo__init_online_kernel_dwarf(struct debuginfo *self, +static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg, Dwarf_Addr addr __maybe_unused) { const char *path = kernel_get_module_path("kernel"); @@ -217,44 +216,45 @@ static int debuginfo__init_online_kernel_dwarf(struct debuginfo *self, } pr_debug2("Use file %s for debuginfo\n", path); - return debuginfo__init_offline_dwarf(self, path); + return debuginfo__init_offline_dwarf(dbg, path); } #endif struct debuginfo *debuginfo__new(const char *path) { - struct debuginfo *self = zalloc(sizeof(struct debuginfo)); - if (!self) + struct debuginfo *dbg = zalloc(sizeof(*dbg)); + if (!dbg) return NULL; - if (debuginfo__init_offline_dwarf(self, path) < 0) { - free(self); - self = NULL; + if (debuginfo__init_offline_dwarf(dbg, path) < 0) { + free(dbg); + dbg = NULL; } - return self; + return dbg; } struct debuginfo *debuginfo__new_online_kernel(unsigned long addr) { - struct debuginfo *self = zalloc(sizeof(struct debuginfo)); - if (!self) + struct debuginfo *dbg = zalloc(sizeof(*dbg)); + + if (!dbg) return NULL; - if (debuginfo__init_online_kernel_dwarf(self, (Dwarf_Addr)addr) < 0) { - free(self); - self = NULL; + if (debuginfo__init_online_kernel_dwarf(dbg, (Dwarf_Addr)addr) < 0) { + free(dbg); + dbg = NULL; } - return self; + return dbg; } -void debuginfo__delete(struct debuginfo *self) +void debuginfo__delete(struct debuginfo *dbg) { - if (self) { - if (self->dwfl) - dwfl_end(self->dwfl); - free(self); + if (dbg) { + if (dbg->dwfl) + dwfl_end(dbg->dwfl); + free(dbg); } } @@ -274,12 +274,15 @@ static struct probe_trace_arg_ref *alloc_trace_arg_ref(long offs) /* * Convert a location into trace_arg. * If tvar == NULL, this just checks variable can be converted. + * If fentry == true and vr_die is a parameter, do huristic search + * for the location fuzzed by function entry mcount. */ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr, - Dwarf_Op *fb_ops, + Dwarf_Op *fb_ops, Dwarf_Die *sp_die, struct probe_trace_arg *tvar) { Dwarf_Attribute attr; + Dwarf_Addr tmp = 0; Dwarf_Op *op; size_t nops; unsigned int regn; @@ -292,12 +295,29 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr, goto static_var; /* TODO: handle more than 1 exprs */ - if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL || - dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0 || - nops == 0) { - /* TODO: Support const_value */ + if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL) + return -EINVAL; /* Broken DIE ? */ + if (dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0) { + ret = dwarf_entrypc(sp_die, &tmp); + if (ret || addr != tmp || + dwarf_tag(vr_die) != DW_TAG_formal_parameter || + dwarf_highpc(sp_die, &tmp)) + return -ENOENT; + /* + * This is fuzzed by fentry mcount. We try to find the + * parameter location at the earliest address. + */ + for (addr += 1; addr <= tmp; addr++) { + if (dwarf_getlocation_addr(&attr, addr, &op, + &nops, 1) > 0) + goto found; + } return -ENOENT; } +found: + if (nops == 0) + /* TODO: Support const_value */ + return -ENOENT; if (op->atom == DW_OP_addr) { static_var: @@ -564,7 +584,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, } if (die_find_member(&type, field->name, die_mem) == NULL) { - pr_warning("%s(tyep:%s) has no member %s.\n", varname, + pr_warning("%s(type:%s) has no member %s.\n", varname, dwarf_diename(&type), field->name); return -EINVAL; } @@ -601,7 +621,7 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) dwarf_diename(vr_die)); ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops, - pf->tvar); + &pf->sp_die, pf->tvar); if (ret == -ENOENT) pr_err("Failed to find the location of %s at this address.\n" " Perhaps, it has been optimized out.\n", pf->pvar->var); @@ -676,37 +696,42 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) } /* Convert subprogram DIE to trace point */ -static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr, - bool retprobe, struct probe_trace_point *tp) +static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, + Dwarf_Addr paddr, bool retprobe, + struct probe_trace_point *tp) { Dwarf_Addr eaddr, highaddr; - const char *name; - - /* Copy the name of probe point */ - name = dwarf_diename(sp_die); - if (name) { - if (dwarf_entrypc(sp_die, &eaddr) != 0) { - pr_warning("Failed to get entry address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (dwarf_highpc(sp_die, &highaddr) != 0) { - pr_warning("Failed to get end address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (paddr > highaddr) { - pr_warning("Offset specified is greater than size of %s\n", - dwarf_diename(sp_die)); - return -EINVAL; - } - tp->symbol = strdup(name); - if (tp->symbol == NULL) - return -ENOMEM; - tp->offset = (unsigned long)(paddr - eaddr); - } else - /* This function has no name. */ - tp->offset = (unsigned long)paddr; + GElf_Sym sym; + const char *symbol; + + /* Verify the address is correct */ + if (dwarf_entrypc(sp_die, &eaddr) != 0) { + pr_warning("Failed to get entry address of %s\n", + dwarf_diename(sp_die)); + return -ENOENT; + } + if (dwarf_highpc(sp_die, &highaddr) != 0) { + pr_warning("Failed to get end address of %s\n", + dwarf_diename(sp_die)); + return -ENOENT; + } + if (paddr > highaddr) { + pr_warning("Offset specified is greater than size of %s\n", + dwarf_diename(sp_die)); + return -EINVAL; + } + + /* Get an appropriate symbol from symtab */ + symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); + if (!symbol) { + pr_warning("Failed to find symbol at 0x%lx\n", + (unsigned long)paddr); + return -ENOENT; + } + tp->offset = (unsigned long)(paddr - sym.st_value); + tp->symbol = strdup(symbol); + if (!tp->symbol) + return -ENOMEM; /* Return probe must be on the head of a subprogram */ if (retprobe) { @@ -734,7 +759,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) } /* If not a real subprogram, find a real one */ - if (dwarf_tag(sc_die) != DW_TAG_subprogram) { + if (!die_is_func_def(sc_die)) { if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) { pr_warning("Failed to find probe point in any " "functions.\n"); @@ -980,12 +1005,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) struct dwarf_callback_param *param = data; struct probe_finder *pf = param->data; struct perf_probe_point *pp = &pf->pev->point; - Dwarf_Attribute attr; /* Check tag and diename */ - if (dwarf_tag(sp_die) != DW_TAG_subprogram || - !die_compare_name(sp_die, pp->function) || - dwarf_attr(sp_die, DW_AT_declaration, &attr)) + if (!die_is_func_def(sp_die) || + !die_compare_name(sp_die, pp->function)) return DWARF_CB_OK; /* Check declared file */ @@ -1061,7 +1084,7 @@ static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data) } /* Find probe points from debuginfo */ -static int debuginfo__find_probes(struct debuginfo *self, +static int debuginfo__find_probes(struct debuginfo *dbg, struct probe_finder *pf) { struct perf_probe_point *pp = &pf->pev->point; @@ -1072,7 +1095,7 @@ static int debuginfo__find_probes(struct debuginfo *self, #if _ELFUTILS_PREREQ(0, 142) /* Get the call frame information from this dwarf */ - pf->cfi = dwarf_getcfi(self->dbg); + pf->cfi = dwarf_getcfi(dbg->dbg); #endif off = 0; @@ -1091,7 +1114,7 @@ static int debuginfo__find_probes(struct debuginfo *self, .data = pf, }; - dwarf_getpubnames(self->dbg, pubname_search_cb, + dwarf_getpubnames(dbg->dbg, pubname_search_cb, &pubname_param, 0); if (pubname_param.found) { ret = probe_point_search_cb(&pf->sp_die, &probe_param); @@ -1101,9 +1124,9 @@ static int debuginfo__find_probes(struct debuginfo *self, } /* Loop on CUs (Compilation Unit) */ - while (!dwarf_nextcu(self->dbg, off, &noff, &cuhl, NULL, NULL, NULL)) { + while (!dwarf_nextcu(dbg->dbg, off, &noff, &cuhl, NULL, NULL, NULL)) { /* Get the DIE(Debugging Information Entry) of this CU */ - diep = dwarf_offdie(self->dbg, off + cuhl, &pf->cu_die); + diep = dwarf_offdie(dbg->dbg, off + cuhl, &pf->cu_die); if (!diep) continue; @@ -1134,12 +1157,80 @@ found: return ret; } +struct local_vars_finder { + struct probe_finder *pf; + struct perf_probe_arg *args; + int max_args; + int nargs; + int ret; +}; + +/* Collect available variables in this scope */ +static int copy_variables_cb(Dwarf_Die *die_mem, void *data) +{ + struct local_vars_finder *vf = data; + struct probe_finder *pf = vf->pf; + int tag; + + tag = dwarf_tag(die_mem); + if (tag == DW_TAG_formal_parameter || + tag == DW_TAG_variable) { + if (convert_variable_location(die_mem, vf->pf->addr, + vf->pf->fb_ops, &pf->sp_die, + NULL) == 0) { + vf->args[vf->nargs].var = (char *)dwarf_diename(die_mem); + if (vf->args[vf->nargs].var == NULL) { + vf->ret = -ENOMEM; + return DIE_FIND_CB_END; + } + pr_debug(" %s", vf->args[vf->nargs].var); + vf->nargs++; + } + } + + if (dwarf_haspc(die_mem, vf->pf->addr)) + return DIE_FIND_CB_CONTINUE; + else + return DIE_FIND_CB_SIBLING; +} + +static int expand_probe_args(Dwarf_Die *sc_die, struct probe_finder *pf, + struct perf_probe_arg *args) +{ + Dwarf_Die die_mem; + int i; + int n = 0; + struct local_vars_finder vf = {.pf = pf, .args = args, + .max_args = MAX_PROBE_ARGS, .ret = 0}; + + for (i = 0; i < pf->pev->nargs; i++) { + /* var never be NULL */ + if (strcmp(pf->pev->args[i].var, "$vars") == 0) { + pr_debug("Expanding $vars into:"); + vf.nargs = n; + /* Special local variables */ + die_find_child(sc_die, copy_variables_cb, (void *)&vf, + &die_mem); + pr_debug(" (%d)\n", vf.nargs - n); + if (vf.ret < 0) + return vf.ret; + n = vf.nargs; + } else { + /* Copy normal argument */ + args[n] = pf->pev->args[i]; + n++; + } + } + return n; +} + /* Add a found probe point into trace event list */ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) { struct trace_event_finder *tf = container_of(pf, struct trace_event_finder, pf); struct probe_trace_event *tev; + struct perf_probe_arg *args; int ret, i; /* Check number of tevs */ @@ -1151,7 +1242,7 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) tev = &tf->tevs[tf->ntevs++]; /* Trace point should be converted from subprogram DIE */ - ret = convert_to_trace_point(&pf->sp_die, pf->addr, + ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr, pf->pev->point.retprobe, &tev->point); if (ret < 0) return ret; @@ -1159,31 +1250,45 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) pr_debug("Probe point found: %s+%lu\n", tev->point.symbol, tev->point.offset); - /* Find each argument */ - tev->nargs = pf->pev->nargs; - tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); - if (tev->args == NULL) + /* Expand special probe argument if exist */ + args = zalloc(sizeof(struct perf_probe_arg) * MAX_PROBE_ARGS); + if (args == NULL) return -ENOMEM; - for (i = 0; i < pf->pev->nargs; i++) { - pf->pvar = &pf->pev->args[i]; + + ret = expand_probe_args(sc_die, pf, args); + if (ret < 0) + goto end; + + tev->nargs = ret; + tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); + if (tev->args == NULL) { + ret = -ENOMEM; + goto end; + } + + /* Find each argument */ + for (i = 0; i < tev->nargs; i++) { + pf->pvar = &args[i]; pf->tvar = &tev->args[i]; /* Variable should be found from scope DIE */ ret = find_variable(sc_die, pf); if (ret != 0) - return ret; + break; } - return 0; +end: + free(args); + return ret; } /* Find probe_trace_events specified by perf_probe_event from debuginfo */ -int debuginfo__find_trace_events(struct debuginfo *self, +int debuginfo__find_trace_events(struct debuginfo *dbg, struct perf_probe_event *pev, struct probe_trace_event **tevs, int max_tevs) { struct trace_event_finder tf = { .pf = {.pev = pev, .callback = add_probe_trace_event}, - .max_tevs = max_tevs}; + .mod = dbg->mod, .max_tevs = max_tevs}; int ret; /* Allocate result tevs array */ @@ -1194,7 +1299,7 @@ int debuginfo__find_trace_events(struct debuginfo *self, tf.tevs = *tevs; tf.ntevs = 0; - ret = debuginfo__find_probes(self, &tf.pf); + ret = debuginfo__find_probes(dbg, &tf.pf); if (ret < 0) { free(*tevs); *tevs = NULL; @@ -1220,7 +1325,8 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data) if (tag == DW_TAG_formal_parameter || tag == DW_TAG_variable) { ret = convert_variable_location(die_mem, af->pf.addr, - af->pf.fb_ops, NULL); + af->pf.fb_ops, &af->pf.sp_die, + NULL); if (ret == 0) { ret = die_get_varname(die_mem, buf, MAX_VAR_LEN); pr_debug2("Add new var: %s\n", buf); @@ -1252,7 +1358,7 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) vl = &af->vls[af->nvls++]; /* Trace point should be converted from subprogram DIE */ - ret = convert_to_trace_point(&pf->sp_die, pf->addr, + ret = convert_to_trace_point(&pf->sp_die, af->mod, pf->addr, pf->pev->point.retprobe, &vl->point); if (ret < 0) return ret; @@ -1284,13 +1390,14 @@ out: } /* Find available variables at given probe point */ -int debuginfo__find_available_vars_at(struct debuginfo *self, +int debuginfo__find_available_vars_at(struct debuginfo *dbg, struct perf_probe_event *pev, struct variable_list **vls, int max_vls, bool externs) { struct available_var_finder af = { .pf = {.pev = pev, .callback = add_available_vars}, + .mod = dbg->mod, .max_vls = max_vls, .externs = externs}; int ret; @@ -1302,7 +1409,7 @@ int debuginfo__find_available_vars_at(struct debuginfo *self, af.vls = *vls; af.nvls = 0; - ret = debuginfo__find_probes(self, &af.pf); + ret = debuginfo__find_probes(dbg, &af.pf); if (ret < 0) { /* Free vlist for error */ while (af.nvls--) { @@ -1320,19 +1427,19 @@ int debuginfo__find_available_vars_at(struct debuginfo *self, } /* Reverse search */ -int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr, +int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, struct perf_probe_point *ppt) { Dwarf_Die cudie, spdie, indie; - Dwarf_Addr _addr, baseaddr; - const char *fname = NULL, *func = NULL, *tmp; + Dwarf_Addr _addr = 0, baseaddr = 0; + const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp; int baseline = 0, lineno = 0, ret = 0; /* Adjust address with bias */ - addr += self->bias; + addr += dbg->bias; /* Find cu die */ - if (!dwarf_addrdie(self->dbg, (Dwarf_Addr)addr - self->bias, &cudie)) { + if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr - dbg->bias, &cudie)) { pr_warning("Failed to find debug information for address %lx\n", addr); ret = -EINVAL; @@ -1346,27 +1453,36 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr, /* Find a corresponding function (name, baseline and baseaddr) */ if (die_find_realfunc(&cudie, (Dwarf_Addr)addr, &spdie)) { /* Get function entry information */ - tmp = dwarf_diename(&spdie); - if (!tmp || + func = basefunc = dwarf_diename(&spdie); + if (!func || dwarf_entrypc(&spdie, &baseaddr) != 0 || - dwarf_decl_line(&spdie, &baseline) != 0) + dwarf_decl_line(&spdie, &baseline) != 0) { + lineno = 0; goto post; - func = tmp; + } - if (addr == (unsigned long)baseaddr) + fname = dwarf_decl_file(&spdie); + if (addr == (unsigned long)baseaddr) { /* Function entry - Relative line number is 0 */ lineno = baseline; - else if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr, - &indie)) { + goto post; + } + + /* Track down the inline functions step by step */ + while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr, + &indie)) { + /* There is an inline function */ if (dwarf_entrypc(&indie, &_addr) == 0 && - _addr == addr) + _addr == addr) { /* * addr is at an inline function entry. * In this case, lineno should be the call-site - * line number. + * line number. (overwrite lineinfo) */ lineno = die_get_call_lineno(&indie); - else { + fname = die_get_call_file(&indie); + break; + } else { /* * addr is in an inline function body. * Since lineno points one of the lines @@ -1374,19 +1490,27 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr, * be the entry line of the inline function. */ tmp = dwarf_diename(&indie); - if (tmp && - dwarf_decl_line(&spdie, &baseline) == 0) - func = tmp; + if (!tmp || + dwarf_decl_line(&indie, &baseline) != 0) + break; + func = tmp; + spdie = indie; } } + /* Verify the lineno and baseline are in a same file */ + tmp = dwarf_decl_file(&spdie); + if (!tmp || strcmp(tmp, fname) != 0) + lineno = 0; } post: /* Make a relative line number or an offset */ if (lineno) ppt->line = lineno - baseline; - else if (func) + else if (basefunc) { ppt->offset = addr - (unsigned long)baseaddr; + func = basefunc; + } /* Duplicate strings */ if (func) { @@ -1474,7 +1598,7 @@ static int line_range_inline_cb(Dwarf_Die *in_die, void *data) return 0; } -/* Search function from function name */ +/* Search function definition from function name */ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) { struct dwarf_callback_param *param = data; @@ -1485,7 +1609,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die))) return DWARF_CB_OK; - if (dwarf_tag(sp_die) == DW_TAG_subprogram && + if (die_is_func_def(sp_die) && die_compare_name(sp_die, lr->function)) { lf->fname = dwarf_decl_file(sp_die); dwarf_decl_line(sp_die, &lr->offset); @@ -1516,7 +1640,7 @@ static int find_line_range_by_func(struct line_finder *lf) return param.retval; } -int debuginfo__find_line_range(struct debuginfo *self, struct line_range *lr) +int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr) { struct line_finder lf = {.lr = lr, .found = 0}; int ret = 0; @@ -1533,7 +1657,7 @@ int debuginfo__find_line_range(struct debuginfo *self, struct line_range *lr) struct dwarf_callback_param line_range_param = { .data = (void *)&lf, .retval = 0}; - dwarf_getpubnames(self->dbg, pubname_search_cb, + dwarf_getpubnames(dbg->dbg, pubname_search_cb, &pubname_param, 0); if (pubname_param.found) { line_range_search_cb(&lf.sp_die, &line_range_param); @@ -1544,12 +1668,12 @@ int debuginfo__find_line_range(struct debuginfo *self, struct line_range *lr) /* Loop on CUs (Compilation Unit) */ while (!lf.found && ret >= 0) { - if (dwarf_nextcu(self->dbg, off, &noff, &cuhl, + if (dwarf_nextcu(dbg->dbg, off, &noff, &cuhl, NULL, NULL, NULL) != 0) break; /* Get the DIE(Debugging Information Entry) of this CU */ - diep = dwarf_offdie(self->dbg, off + cuhl, &lf.cu_die); + diep = dwarf_offdie(dbg->dbg, off + cuhl, &lf.cu_die); if (!diep) continue; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 17e94d0c36f..ffc33cdd25c 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -7,6 +7,7 @@ #define MAX_PROBE_BUFFER 1024 #define MAX_PROBES 128 +#define MAX_PROBE_ARGS 128 static inline int is_c_varname(const char *name) { @@ -14,7 +15,7 @@ static inline int is_c_varname(const char *name) return isalpha(name[0]) || name[0] == '_'; } -#ifdef DWARF_SUPPORT +#ifdef HAVE_DWARF_SUPPORT #include "dwarf-aux.h" @@ -23,31 +24,32 @@ static inline int is_c_varname(const char *name) /* debug information structure */ struct debuginfo { Dwarf *dbg; + Dwfl_Module *mod; Dwfl *dwfl; Dwarf_Addr bias; }; extern struct debuginfo *debuginfo__new(const char *path); extern struct debuginfo *debuginfo__new_online_kernel(unsigned long addr); -extern void debuginfo__delete(struct debuginfo *self); +extern void debuginfo__delete(struct debuginfo *dbg); /* Find probe_trace_events specified by perf_probe_event from debuginfo */ -extern int debuginfo__find_trace_events(struct debuginfo *self, +extern int debuginfo__find_trace_events(struct debuginfo *dbg, struct perf_probe_event *pev, struct probe_trace_event **tevs, int max_tevs); /* Find a perf_probe_point from debuginfo */ -extern int debuginfo__find_probe_point(struct debuginfo *self, +extern int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr, struct perf_probe_point *ppt); /* Find a line range */ -extern int debuginfo__find_line_range(struct debuginfo *self, +extern int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr); /* Find available variables */ -extern int debuginfo__find_available_vars_at(struct debuginfo *self, +extern int debuginfo__find_available_vars_at(struct debuginfo *dbg, struct perf_probe_event *pev, struct variable_list **vls, int max_points, bool externs); @@ -77,6 +79,7 @@ struct probe_finder { struct trace_event_finder { struct probe_finder pf; + Dwfl_Module *mod; /* For solving symbols */ struct probe_trace_event *tevs; /* Found trace events */ int ntevs; /* Number of trace events */ int max_tevs; /* Max number of trace events */ @@ -84,6 +87,7 @@ struct trace_event_finder { struct available_var_finder { struct probe_finder pf; + Dwfl_Module *mod; /* For solving symbols */ struct variable_list *vls; /* Found variable lists */ int nvls; /* Number of variable lists */ int max_vls; /* Max no. of variable lists */ @@ -102,6 +106,6 @@ struct line_finder { int found; }; -#endif /* DWARF_SUPPORT */ +#endif /* HAVE_DWARF_SUPPORT */ #endif /*_PROBE_FINDER_H */ diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h index 4cedea59f51..c3cb6584d52 100644 --- a/tools/perf/util/pstack.h +++ b/tools/perf/util/pstack.h @@ -5,10 +5,10 @@ struct pstack; struct pstack *pstack__new(unsigned short max_nr_entries); -void pstack__delete(struct pstack *self); -bool pstack__empty(const struct pstack *self); -void pstack__remove(struct pstack *self, void *key); -void pstack__push(struct pstack *self, void *key); -void *pstack__pop(struct pstack *self); +void pstack__delete(struct pstack *pstack); +bool pstack__empty(const struct pstack *pstack); +void pstack__remove(struct pstack *pstack, void *key); +void pstack__push(struct pstack *pstack, void *key); +void *pstack__pop(struct pstack *pstack); #endif /* _PERF_PSTACK_ */ diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index f75ae1b9900..239036fb2b2 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -17,5 +17,5 @@ util/xyarray.c util/cgroup.c util/rblist.c util/strlist.c -util/sysfs.c +util/fs.c ../../lib/rbtree.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 925e0c3e6d9..4bf8ace7f51 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -8,18 +8,31 @@ #include "cpumap.h" #include "thread_map.h" +/* + * Support debug printing even though util/debug.c is not linked. That means + * implementing 'verbose' and 'eprintf'. + */ +int verbose; + +int eprintf(int level, const char *fmt, ...) +{ + va_list args; + int ret = 0; + + if (verbose >= level) { + va_start(args, fmt); + ret = vfprintf(stderr, fmt, args); + va_end(args); + } + + return ret; +} + /* Define PyVarObject_HEAD_INIT for python 2.5 */ #ifndef PyVarObject_HEAD_INIT # define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size, #endif -struct throttle_event { - struct perf_event_header header; - u64 time; - u64 id; - u64 stream_id; -}; - PyMODINIT_FUNC initperf(void); #define member_def(type, member, ptype, help) \ @@ -802,6 +815,8 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, PyObject *pyevent = pyrf_event__new(event); struct pyrf_event *pevent = (struct pyrf_event *)pyevent; + perf_evlist__mmap_consume(evlist, cpu); + if (pyevent == NULL) return PyErr_NoMemory(); @@ -967,6 +982,7 @@ static struct { { "COUNT_SW_PAGE_FAULTS_MAJ", PERF_COUNT_SW_PAGE_FAULTS_MAJ }, { "COUNT_SW_ALIGNMENT_FAULTS", PERF_COUNT_SW_ALIGNMENT_FAULTS }, { "COUNT_SW_EMULATION_FAULTS", PERF_COUNT_SW_EMULATION_FAULTS }, + { "COUNT_SW_DUMMY", PERF_COUNT_SW_DUMMY }, { "SAMPLE_IP", PERF_SAMPLE_IP }, { "SAMPLE_TID", PERF_SAMPLE_TID }, @@ -1015,6 +1031,7 @@ PyMODINIT_FUNC initperf(void) pyrf_cpu_map__setup_types() < 0) return; + /* The page_size is placed in util object. */ page_size = sysconf(_SC_PAGE_SIZE); Py_INCREF(&pyrf_evlist__type); diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c index a16cdd2625a..0dfe27d9945 100644 --- a/tools/perf/util/rblist.c +++ b/tools/perf/util/rblist.c @@ -48,10 +48,12 @@ void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node) rblist->node_delete(rblist, rb_node); } -struct rb_node *rblist__find(struct rblist *rblist, const void *entry) +static struct rb_node *__rblist__findnew(struct rblist *rblist, + const void *entry, + bool create) { struct rb_node **p = &rblist->entries.rb_node; - struct rb_node *parent = NULL; + struct rb_node *parent = NULL, *new_node = NULL; while (*p != NULL) { int rc; @@ -67,7 +69,26 @@ struct rb_node *rblist__find(struct rblist *rblist, const void *entry) return parent; } - return NULL; + if (create) { + new_node = rblist->node_new(rblist, entry); + if (new_node) { + rb_link_node(new_node, parent, p); + rb_insert_color(new_node, &rblist->entries); + ++rblist->nr_entries; + } + } + + return new_node; +} + +struct rb_node *rblist__find(struct rblist *rblist, const void *entry) +{ + return __rblist__findnew(rblist, entry, false); +} + +struct rb_node *rblist__findnew(struct rblist *rblist, const void *entry) +{ + return __rblist__findnew(rblist, entry, true); } void rblist__init(struct rblist *rblist) diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h index 6d0cae5ae83..ff9913b994c 100644 --- a/tools/perf/util/rblist.h +++ b/tools/perf/util/rblist.h @@ -32,6 +32,7 @@ void rblist__delete(struct rblist *rblist); int rblist__add_node(struct rblist *rblist, const void *new_entry); void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node); struct rb_node *rblist__find(struct rblist *rblist, const void *entry); +struct rb_node *rblist__findnew(struct rblist *rblist, const void *entry); struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx); static inline bool rblist__empty(const struct rblist *rblist) diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c new file mode 100644 index 00000000000..c8845b107f6 --- /dev/null +++ b/tools/perf/util/record.c @@ -0,0 +1,179 @@ +#include "evlist.h" +#include "evsel.h" +#include "cpumap.h" +#include "parse-events.h" +#include "fs.h" +#include "util.h" + +typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel); + +static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str) +{ + struct perf_evlist *evlist; + struct perf_evsel *evsel; + int err = -EAGAIN, fd; + + evlist = perf_evlist__new(); + if (!evlist) + return -ENOMEM; + + if (parse_events(evlist, str)) + goto out_delete; + + evsel = perf_evlist__first(evlist); + + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); + if (fd < 0) + goto out_delete; + close(fd); + + fn(evsel); + + fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0); + if (fd < 0) { + if (errno == EINVAL) + err = -EINVAL; + goto out_delete; + } + close(fd); + err = 0; + +out_delete: + perf_evlist__delete(evlist); + return err; +} + +static bool perf_probe_api(setup_probe_fn_t fn) +{ + const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL}; + struct cpu_map *cpus; + int cpu, ret, i = 0; + + cpus = cpu_map__new(NULL); + if (!cpus) + return false; + cpu = cpus->map[0]; + cpu_map__delete(cpus); + + do { + ret = perf_do_probe_api(fn, cpu, try[i++]); + if (!ret) + return true; + } while (ret == -EAGAIN && try[i]); + + return false; +} + +static void perf_probe_sample_identifier(struct perf_evsel *evsel) +{ + evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER; +} + +bool perf_can_sample_identifier(void) +{ + return perf_probe_api(perf_probe_sample_identifier); +} + +void perf_evlist__config(struct perf_evlist *evlist, + struct perf_record_opts *opts) +{ + struct perf_evsel *evsel; + bool use_sample_identifier = false; + + /* + * Set the evsel leader links before we configure attributes, + * since some might depend on this info. + */ + if (opts->group) + perf_evlist__set_leader(evlist); + + if (evlist->cpus->map[0] < 0) + opts->no_inherit = true; + + list_for_each_entry(evsel, &evlist->entries, node) + perf_evsel__config(evsel, opts); + + if (evlist->nr_entries > 1) { + struct perf_evsel *first = perf_evlist__first(evlist); + + list_for_each_entry(evsel, &evlist->entries, node) { + if (evsel->attr.sample_type == first->attr.sample_type) + continue; + use_sample_identifier = perf_can_sample_identifier(); + break; + } + list_for_each_entry(evsel, &evlist->entries, node) + perf_evsel__set_sample_id(evsel, use_sample_identifier); + } + + perf_evlist__set_id_pos(evlist); +} + +static int get_max_rate(unsigned int *rate) +{ + char path[PATH_MAX]; + const char *procfs = procfs__mountpoint(); + + if (!procfs) + return -1; + + snprintf(path, PATH_MAX, + "%s/sys/kernel/perf_event_max_sample_rate", procfs); + + return filename__read_int(path, (int *) rate); +} + +static int perf_record_opts__config_freq(struct perf_record_opts *opts) +{ + bool user_freq = opts->user_freq != UINT_MAX; + unsigned int max_rate; + + if (opts->user_interval != ULLONG_MAX) + opts->default_interval = opts->user_interval; + if (user_freq) + opts->freq = opts->user_freq; + + /* + * User specified count overrides default frequency. + */ + if (opts->default_interval) + opts->freq = 0; + else if (opts->freq) { + opts->default_interval = opts->freq; + } else { + pr_err("frequency and count are zero, aborting\n"); + return -1; + } + + if (get_max_rate(&max_rate)) + return 0; + + /* + * 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; + } + + /* + * Default frequency is over current maximum. + */ + if (max_rate < opts->freq) { + pr_warning("Lowering default frequency rate to %u.\n" + "Please consider tweaking " + "/proc/sys/kernel/perf_event_max_sample_rate.\n", + max_rate); + opts->freq = max_rate; + } + + return 0; +} + +int perf_record_opts__config(struct perf_record_opts *opts) +{ + return perf_record_opts__config_freq(opts); +} diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index eacec859f29..d5e5969f6fe 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -261,7 +261,8 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine __maybe_unused, - struct addr_location *al) + struct thread *thread, + struct addr_location *al) { struct format_field *field; static char handler[256]; @@ -272,8 +273,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused, int cpu = sample->cpu; void *data = sample->raw_data; unsigned long long nsecs = sample->time; - struct thread *thread = al->thread; - char *comm = thread->comm; + const char *comm = thread__comm_str(thread); dSP; @@ -282,7 +282,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused, event = find_cache_event(evsel); if (!event) - die("ug! no event found for type %" PRIu64, evsel->attr.config); + die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); pid = raw_field_value(event, "common_pid", data); @@ -351,7 +351,8 @@ static void perl_process_event_generic(union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine __maybe_unused, - struct addr_location *al __maybe_unused) + struct thread *thread __maybe_unused, + struct addr_location *al __maybe_unused) { dSP; @@ -377,10 +378,11 @@ static void perl_process_event(union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, - struct addr_location *al) + struct thread *thread, + struct addr_location *al) { - perl_process_tracepoint(event, sample, evsel, machine, al); - perl_process_event_generic(event, sample, evsel, machine, al); + perl_process_tracepoint(event, sample, evsel, machine, thread, al); + perl_process_event_generic(event, sample, evsel, machine, thread, al); } static void run_start_sub(void) diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index e87aa5d9696..53c20e7fd90 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -56,6 +56,17 @@ static void handler_call_die(const char *handler_name) Py_FatalError("problem in Python trace event handler"); } +/* + * Insert val into into the dictionary and decrement the reference counter. + * This is necessary for dictionaries since PyDict_SetItemString() does not + * steal a reference, as opposed to PyTuple_SetItem(). + */ +static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val) +{ + PyDict_SetItemString(dict, key, val); + Py_DECREF(val); +} + static void define_value(enum print_arg_type field_type, const char *ev_name, const char *field_name, @@ -225,6 +236,7 @@ static void python_process_tracepoint(union perf_event *perf_event struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine __maybe_unused, + struct thread *thread, struct addr_location *al) { PyObject *handler, *retval, *context, *t, *obj, *dict = NULL; @@ -238,8 +250,7 @@ static void python_process_tracepoint(union perf_event *perf_event int cpu = sample->cpu; void *data = sample->raw_data; unsigned long long nsecs = sample->time; - struct thread *thread = al->thread; - char *comm = thread->comm; + const char *comm = thread__comm_str(thread); t = PyTuple_New(MAX_FIELDS); if (!t) @@ -279,11 +290,11 @@ static void python_process_tracepoint(union perf_event *perf_event PyTuple_SetItem(t, n++, PyInt_FromLong(pid)); PyTuple_SetItem(t, n++, PyString_FromString(comm)); } else { - PyDict_SetItemString(dict, "common_cpu", PyInt_FromLong(cpu)); - PyDict_SetItemString(dict, "common_s", PyInt_FromLong(s)); - PyDict_SetItemString(dict, "common_ns", PyInt_FromLong(ns)); - PyDict_SetItemString(dict, "common_pid", PyInt_FromLong(pid)); - PyDict_SetItemString(dict, "common_comm", PyString_FromString(comm)); + 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)); } for (field = event->format.fields; field; field = field->next) { if (field->flags & FIELD_IS_STRING) { @@ -313,7 +324,7 @@ static void python_process_tracepoint(union perf_event *perf_event if (handler) PyTuple_SetItem(t, n++, obj); else - PyDict_SetItemString(dict, field->name, obj); + pydict_set_item_string_decref(dict, field->name, obj); } if (!handler) @@ -345,12 +356,12 @@ static void python_process_general_event(union perf_event *perf_event struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine __maybe_unused, + struct thread *thread, struct addr_location *al) { PyObject *handler, *retval, *t, *dict; static char handler_name[64]; unsigned n = 0; - struct thread *thread = al->thread; /* * Use the MAX_FIELDS to make the function expandable, though @@ -370,21 +381,21 @@ static void python_process_general_event(union perf_event *perf_event if (!handler || !PyCallable_Check(handler)) goto exit; - PyDict_SetItemString(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); - PyDict_SetItemString(dict, "attr", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); + pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( (const char *)&evsel->attr, sizeof(evsel->attr))); - PyDict_SetItemString(dict, "sample", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize( (const char *)sample, sizeof(*sample))); - PyDict_SetItemString(dict, "raw_buf", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( (const char *)sample->raw_data, sample->raw_size)); - PyDict_SetItemString(dict, "comm", - PyString_FromString(thread->comm)); + pydict_set_item_string_decref(dict, "comm", + PyString_FromString(thread__comm_str(thread))); if (al->map) { - PyDict_SetItemString(dict, "dso", + pydict_set_item_string_decref(dict, "dso", PyString_FromString(al->map->dso->name)); } if (al->sym) { - PyDict_SetItemString(dict, "symbol", + pydict_set_item_string_decref(dict, "symbol", PyString_FromString(al->sym->name)); } @@ -404,17 +415,18 @@ static void python_process_event(union perf_event *perf_event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, + struct thread *thread, struct addr_location *al) { switch (evsel->attr.type) { case PERF_TYPE_TRACEPOINT: python_process_tracepoint(perf_event, sample, evsel, - machine, al); + machine, thread, al); break; /* Reserve for future process_hw/sw/raw APIs */ default: python_process_general_event(perf_event, sample, evsel, - machine, al); + machine, thread, al); } } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index cf1fe01b7e8..f36d24a0244 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1,4 +1,5 @@ #include <linux/kernel.h> +#include <traceevent/event-parse.h> #include <byteswap.h> #include <unistd.h> @@ -12,72 +13,37 @@ #include "sort.h" #include "util.h" #include "cpumap.h" -#include "event-parse.h" #include "perf_regs.h" #include "vdso.h" -static int perf_session__open(struct perf_session *self, bool force) +static int perf_session__open(struct perf_session *session) { - struct stat input_stat; + struct perf_data_file *file = session->file; - if (!strcmp(self->filename, "-")) { - self->fd_pipe = true; - self->fd = STDIN_FILENO; - - if (perf_session__read_header(self, self->fd) < 0) - pr_err("incompatible file format (rerun with -v to learn more)"); - - return 0; - } - - self->fd = open(self->filename, O_RDONLY); - if (self->fd < 0) { - int err = errno; - - pr_err("failed to open %s: %s", self->filename, strerror(err)); - if (err == ENOENT && !strcmp(self->filename, "perf.data")) - pr_err(" (try 'perf record' first)"); - pr_err("\n"); - return -errno; - } - - if (fstat(self->fd, &input_stat) < 0) - goto out_close; - - if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) { - pr_err("file %s not owned by current user or root\n", - self->filename); - goto out_close; - } - - if (!input_stat.st_size) { - pr_info("zero-sized file (%s), nothing to do!\n", - self->filename); - goto out_close; - } - - if (perf_session__read_header(self, self->fd) < 0) { + if (perf_session__read_header(session) < 0) { pr_err("incompatible file format (rerun with -v to learn more)"); - goto out_close; + return -1; } - if (!perf_evlist__valid_sample_type(self->evlist)) { + if (perf_data_file__is_pipe(file)) + return 0; + + if (!perf_evlist__valid_sample_type(session->evlist)) { pr_err("non matching sample_type"); - goto out_close; + return -1; } - if (!perf_evlist__valid_sample_id_all(self->evlist)) { + if (!perf_evlist__valid_sample_id_all(session->evlist)) { pr_err("non matching sample_id_all"); - goto out_close; + return -1; } - self->size = input_stat.st_size; - return 0; + if (!perf_evlist__valid_read_format(session->evlist)) { + pr_err("non matching read_format"); + return -1; + } -out_close: - close(self->fd); - self->fd = -1; - return -1; + return 0; } void perf_session__set_id_hdr_size(struct perf_session *session) @@ -87,71 +53,70 @@ void perf_session__set_id_hdr_size(struct perf_session *session) machines__set_id_hdr_size(&session->machines, id_hdr_size); } -int perf_session__create_kernel_maps(struct perf_session *self) +int perf_session__create_kernel_maps(struct perf_session *session) { - int ret = machine__create_kernel_maps(&self->machines.host); + int ret = machine__create_kernel_maps(&session->machines.host); if (ret >= 0) - ret = machines__create_guest_kernel_maps(&self->machines); + ret = machines__create_guest_kernel_maps(&session->machines); return ret; } -static void perf_session__destroy_kernel_maps(struct perf_session *self) +static void perf_session__destroy_kernel_maps(struct perf_session *session) { - machines__destroy_kernel_maps(&self->machines); + machines__destroy_kernel_maps(&session->machines); } -struct perf_session *perf_session__new(const char *filename, int mode, - bool force, bool repipe, - struct perf_tool *tool) +struct perf_session *perf_session__new(struct perf_data_file *file, + bool repipe, struct perf_tool *tool) { - struct perf_session *self; - struct stat st; - size_t len; - - if (!filename || !strlen(filename)) { - if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode)) - filename = "-"; - else - filename = "perf.data"; - } + struct perf_session *session = zalloc(sizeof(*session)); - len = strlen(filename); - self = zalloc(sizeof(*self) + len); - - if (self == NULL) + if (!session) goto out; - memcpy(self->filename, filename, len); - self->repipe = repipe; - INIT_LIST_HEAD(&self->ordered_samples.samples); - INIT_LIST_HEAD(&self->ordered_samples.sample_cache); - INIT_LIST_HEAD(&self->ordered_samples.to_free); - machines__init(&self->machines); + session->repipe = repipe; + INIT_LIST_HEAD(&session->ordered_samples.samples); + INIT_LIST_HEAD(&session->ordered_samples.sample_cache); + INIT_LIST_HEAD(&session->ordered_samples.to_free); + machines__init(&session->machines); - if (mode == O_RDONLY) { - if (perf_session__open(self, force) < 0) + if (file) { + if (perf_data_file__open(file)) goto out_delete; - perf_session__set_id_hdr_size(self); - } else if (mode == O_WRONLY) { + + session->file = file; + + if (perf_data_file__is_read(file)) { + if (perf_session__open(session) < 0) + goto out_close; + + perf_session__set_id_hdr_size(session); + } + } + + if (!file || perf_data_file__is_write(file)) { /* * In O_RDONLY mode this will be performed when reading the * kernel MMAP event, in perf_event__process_mmap(). */ - if (perf_session__create_kernel_maps(self) < 0) + if (perf_session__create_kernel_maps(session) < 0) goto out_delete; } if (tool && tool->ordering_requires_timestamps && - tool->ordered_samples && !perf_evlist__sample_id_all(self->evlist)) { + tool->ordered_samples && !perf_evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); tool->ordered_samples = false; } -out: - return self; -out_delete: - perf_session__delete(self); + return session; + + out_close: + perf_data_file__close(file); + out_delete: + perf_session__delete(session); + out: return NULL; } @@ -181,19 +146,22 @@ static void perf_session_env__delete(struct perf_session_env *env) free(env->pmu_mappings); } -void perf_session__delete(struct perf_session *self) +void perf_session__delete(struct perf_session *session) { - perf_session__destroy_kernel_maps(self); - perf_session__delete_dead_threads(self); - perf_session__delete_threads(self); - perf_session_env__delete(&self->header.env); - machines__exit(&self->machines); - close(self->fd); - free(self); + perf_session__destroy_kernel_maps(session); + perf_session__delete_dead_threads(session); + perf_session__delete_threads(session); + perf_session_env__delete(&session->header.env); + machines__exit(&session->machines); + if (session->file) + perf_data_file__close(session->file); + free(session); vdso__exit(); } -static int process_event_synth_tracing_data_stub(union perf_event *event +static int process_event_synth_tracing_data_stub(struct perf_tool *tool + __maybe_unused, + union perf_event *event __maybe_unused, struct perf_session *session __maybe_unused) @@ -202,7 +170,8 @@ static int process_event_synth_tracing_data_stub(union perf_event *event return 0; } -static int process_event_synth_attr_stub(union perf_event *event __maybe_unused, +static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, struct perf_evlist **pevlist __maybe_unused) { @@ -238,23 +207,18 @@ static int process_finished_round_stub(struct perf_tool *tool __maybe_unused, return 0; } -static int process_event_type_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused) -{ - dump_printf(": unhandled!\n"); - return 0; -} - static int process_finished_round(struct perf_tool *tool, union perf_event *event, struct perf_session *session); -static void perf_tool__fill_defaults(struct perf_tool *tool) +void perf_tool__fill_defaults(struct perf_tool *tool) { if (tool->sample == NULL) tool->sample = process_event_sample_stub; if (tool->mmap == NULL) tool->mmap = process_event_stub; + if (tool->mmap2 == NULL) + tool->mmap2 = process_event_stub; if (tool->comm == NULL) tool->comm = process_event_stub; if (tool->fork == NULL) @@ -271,8 +235,6 @@ static void perf_tool__fill_defaults(struct perf_tool *tool) tool->unthrottle = process_event_stub; if (tool->attr == NULL) tool->attr = process_event_synth_attr_stub; - if (tool->event_type == NULL) - tool->event_type = process_event_type_stub; if (tool->tracing_data == NULL) tool->tracing_data = process_event_synth_tracing_data_stub; if (tool->build_id == NULL) @@ -352,6 +314,25 @@ static void perf_event__mmap_swap(union perf_event *event, } } +static void perf_event__mmap2_swap(union perf_event *event, + bool sample_id_all) +{ + event->mmap2.pid = bswap_32(event->mmap2.pid); + event->mmap2.tid = bswap_32(event->mmap2.tid); + event->mmap2.start = bswap_64(event->mmap2.start); + event->mmap2.len = bswap_64(event->mmap2.len); + event->mmap2.pgoff = bswap_64(event->mmap2.pgoff); + event->mmap2.maj = bswap_32(event->mmap2.maj); + event->mmap2.min = bswap_32(event->mmap2.min); + event->mmap2.ino = bswap_64(event->mmap2.ino); + + if (sample_id_all) { + void *data = &event->mmap2.filename; + + data += PERF_ALIGN(strlen(data) + 1, sizeof(u64)); + swap_sample_id_all(event, data); + } +} static void perf_event__task_swap(union perf_event *event, bool sample_id_all) { event->fork.pid = bswap_32(event->fork.pid); @@ -377,6 +358,17 @@ static void perf_event__read_swap(union perf_event *event, bool sample_id_all) swap_sample_id_all(event, &event->read + 1); } +static void perf_event__throttle_swap(union perf_event *event, + bool sample_id_all) +{ + event->throttle.time = bswap_64(event->throttle.time); + event->throttle.id = bswap_64(event->throttle.id); + event->throttle.stream_id = bswap_64(event->throttle.stream_id); + + if (sample_id_all) + swap_sample_id_all(event, &event->throttle + 1); +} + static u8 revbyte(u8 b) { int rev = (b >> 4) | ((b & 0xf) << 4); @@ -422,6 +414,9 @@ void perf_event__attr_swap(struct perf_event_attr *attr) attr->bp_type = bswap_32(attr->bp_type); attr->bp_addr = bswap_64(attr->bp_addr); attr->bp_len = bswap_64(attr->bp_len); + attr->branch_sample_type = bswap_64(attr->branch_sample_type); + attr->sample_regs_user = bswap_64(attr->sample_regs_user); + attr->sample_stack_user = bswap_32(attr->sample_stack_user); swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64)); } @@ -456,11 +451,14 @@ typedef void (*perf_event__swap_op)(union perf_event *event, static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_MMAP] = perf_event__mmap_swap, + [PERF_RECORD_MMAP2] = perf_event__mmap2_swap, [PERF_RECORD_COMM] = perf_event__comm_swap, [PERF_RECORD_FORK] = perf_event__task_swap, [PERF_RECORD_EXIT] = perf_event__task_swap, [PERF_RECORD_LOST] = perf_event__all64_swap, [PERF_RECORD_READ] = perf_event__read_swap, + [PERF_RECORD_THROTTLE] = perf_event__throttle_swap, + [PERF_RECORD_UNTHROTTLE] = perf_event__throttle_swap, [PERF_RECORD_SAMPLE] = perf_event__all64_swap, [PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap, [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, @@ -496,7 +494,7 @@ static int perf_session_deliver_event(struct perf_session *session, u64 file_offset); static int flush_sample_queue(struct perf_session *s, - struct perf_tool *tool) + struct perf_tool *tool) { struct ordered_samples *os = &s->ordered_samples; struct list_head *head = &os->samples; @@ -504,13 +502,20 @@ static int flush_sample_queue(struct perf_session *s, struct perf_sample sample; u64 limit = os->next_flush; u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL; - unsigned idx = 0, progress_next = os->nr_samples / 16; + bool show_progress = limit == ULLONG_MAX; + struct ui_progress prog; int ret; if (!tool->ordered_samples || !limit) return 0; + if (show_progress) + ui_progress__init(&prog, os->nr_samples, "Processing time ordered events..."); + list_for_each_entry_safe(iter, tmp, head, list) { + if (session_done()) + return 0; + if (iter->timestamp > limit) break; @@ -527,11 +532,9 @@ static int flush_sample_queue(struct perf_session *s, os->last_flush = iter->timestamp; list_del(&iter->list); list_add(&iter->list, &os->sample_cache); - if (++idx >= progress_next) { - progress_next += os->nr_samples / 16; - ui_progress__update(idx, os->nr_samples, - "Processing time ordered events..."); - } + + if (show_progress) + ui_progress__update(&prog, 1); } if (list_empty(head)) { @@ -644,7 +647,7 @@ static void __queue_event(struct sample_queue *new, struct perf_session *s) #define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct sample_queue)) -static int perf_session_queue_event(struct perf_session *s, union perf_event *event, +int perf_session_queue_event(struct perf_session *s, union perf_event *event, struct perf_sample *sample, u64 file_offset) { struct ordered_samples *os = &s->ordered_samples; @@ -740,7 +743,7 @@ static void perf_session__print_tstamp(struct perf_session *session, union perf_event *event, struct perf_sample *sample) { - u64 sample_type = perf_evlist__sample_type(session->evlist); + u64 sample_type = __perf_evlist__combined_sample_type(session->evlist); if (event->header.type != PERF_RECORD_SAMPLE && !perf_evlist__sample_id_all(session->evlist)) { @@ -755,6 +758,36 @@ static void perf_session__print_tstamp(struct perf_session *session, printf("%" PRIu64 " ", sample->time); } +static void sample_read__printf(struct perf_sample *sample, u64 read_format) +{ + printf("... sample_read:\n"); + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + printf("...... time enabled %016" PRIx64 "\n", + sample->read.time_enabled); + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + printf("...... time running %016" PRIx64 "\n", + sample->read.time_running); + + if (read_format & PERF_FORMAT_GROUP) { + u64 i; + + printf(".... group nr %" PRIu64 "\n", sample->read.group.nr); + + for (i = 0; i < sample->read.group.nr; i++) { + struct sample_read_value *value; + + value = &sample->read.group.values[i]; + printf("..... id %016" PRIx64 + ", value %016" PRIx64 "\n", + value->id, value->value); + } + } else + printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n", + sample->read.one.id, sample->read.one.value); +} + static void dump_event(struct perf_session *session, union perf_event *event, u64 file_offset, struct perf_sample *sample) { @@ -804,11 +837,18 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_DATA_SRC) printf(" . data_src: 0x%"PRIx64"\n", sample->data_src); + + if (sample_type & PERF_SAMPLE_TRANSACTION) + printf("... transaction: %" PRIx64 "\n", sample->transaction); + + if (sample_type & PERF_SAMPLE_READ) + sample_read__printf(sample, evsel->attr.read_format); } static struct machine * perf_session__find_machine_for_cpumode(struct perf_session *session, - union perf_event *event) + union perf_event *event, + struct perf_sample *sample) { const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; @@ -817,10 +857,11 @@ static struct machine * (cpumode == PERF_RECORD_MISC_GUEST_USER))) { u32 pid; - if (event->header.type == PERF_RECORD_MMAP) + if (event->header.type == PERF_RECORD_MMAP + || event->header.type == PERF_RECORD_MMAP2) pid = event->mmap.pid; else - pid = event->ip.pid; + pid = sample->pid; return perf_session__findnew_machine(session, pid); } @@ -828,6 +869,75 @@ static struct machine * return &session->machines.host; } +static int deliver_sample_value(struct perf_session *session, + struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct sample_read_value *v, + struct machine *machine) +{ + struct perf_sample_id *sid; + + sid = perf_evlist__id2sid(session->evlist, v->id); + if (sid) { + sample->id = v->id; + sample->period = v->value - sid->period; + sid->period = v->value; + } + + if (!sid || sid->evsel == NULL) { + ++session->stats.nr_unknown_id; + return 0; + } + + return tool->sample(tool, event, sample, sid->evsel, machine); +} + +static int deliver_sample_group(struct perf_session *session, + struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + int ret = -EINVAL; + u64 i; + + for (i = 0; i < sample->read.group.nr; i++) { + ret = deliver_sample_value(session, tool, event, sample, + &sample->read.group.values[i], + machine); + if (ret) + break; + } + + return ret; +} + +static int +perf_session__deliver_sample(struct perf_session *session, + struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + /* We know evsel != NULL. */ + u64 sample_type = evsel->attr.sample_type; + u64 read_format = evsel->attr.read_format; + + /* Standard sample delievery. */ + if (!(sample_type & PERF_SAMPLE_READ)) + return tool->sample(tool, event, sample, evsel, machine); + + /* For PERF_SAMPLE_READ we have either single or group mode. */ + if (read_format & PERF_FORMAT_GROUP) + return deliver_sample_group(session, tool, event, sample, + machine); + else + return deliver_sample_value(session, tool, event, sample, + &sample->read.one, machine); +} + static int perf_session_deliver_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, @@ -857,7 +967,8 @@ static int perf_session_deliver_event(struct perf_session *session, hists__inc_nr_events(&evsel->hists, event->header.type); } - machine = perf_session__find_machine_for_cpumode(session, event); + machine = perf_session__find_machine_for_cpumode(session, event, + sample); switch (event->header.type) { case PERF_RECORD_SAMPLE: @@ -870,9 +981,12 @@ static int perf_session_deliver_event(struct perf_session *session, ++session->stats.nr_unprocessable_samples; return 0; } - return tool->sample(tool, event, sample, evsel, machine); + return perf_session__deliver_sample(session, tool, event, + sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); + case PERF_RECORD_MMAP2: + return tool->mmap2(tool, event, sample, machine); case PERF_RECORD_COMM: return tool->comm(tool, event, sample, machine); case PERF_RECORD_FORK: @@ -895,25 +1009,10 @@ static int perf_session_deliver_event(struct perf_session *session, } } -static int perf_session__preprocess_sample(struct perf_session *session, - union perf_event *event, struct perf_sample *sample) -{ - if (event->header.type != PERF_RECORD_SAMPLE || - !(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_CALLCHAIN)) - return 0; - - if (!ip_callchain__valid(sample->callchain, event)) { - pr_debug("call-chain problem with event, skipping it.\n"); - ++session->stats.nr_invalid_chains; - session->stats.total_invalid_chains += sample->period; - return -EINVAL; - } - return 0; -} - static int perf_session__process_user_event(struct perf_session *session, union perf_event *event, struct perf_tool *tool, u64 file_offset) { + int fd = perf_data_file__fd(session->file); int err; dump_event(session, event, file_offset, NULL); @@ -921,16 +1020,14 @@ static int perf_session__process_user_event(struct perf_session *session, union /* These events are processed right away */ switch (event->header.type) { case PERF_RECORD_HEADER_ATTR: - err = tool->attr(event, &session->evlist); + err = tool->attr(tool, event, &session->evlist); if (err == 0) perf_session__set_id_hdr_size(session); return err; - case PERF_RECORD_HEADER_EVENT_TYPE: - return tool->event_type(tool, event); case PERF_RECORD_HEADER_TRACING_DATA: /* setup for reading amidst mmap */ - lseek(session->fd, file_offset, SEEK_SET); - return tool->tracing_data(event, session); + lseek(fd, file_offset, SEEK_SET); + return tool->tracing_data(tool, event, session); case PERF_RECORD_HEADER_BUILD_ID: return tool->build_id(tool, event, session); case PERF_RECORD_FINISHED_ROUND: @@ -975,10 +1072,6 @@ static int perf_session__process_event(struct perf_session *session, if (ret) return ret; - /* Preprocess sample records - precheck callchains */ - if (perf_session__preprocess_sample(session, event, &sample)) - return 0; - if (tool->ordered_samples) { ret = perf_session_queue_event(session, event, &sample, file_offset); @@ -990,23 +1083,23 @@ static int perf_session__process_event(struct perf_session *session, file_offset); } -void perf_event_header__bswap(struct perf_event_header *self) +void perf_event_header__bswap(struct perf_event_header *hdr) { - self->type = bswap_32(self->type); - self->misc = bswap_16(self->misc); - self->size = bswap_16(self->size); + hdr->type = bswap_32(hdr->type); + hdr->misc = bswap_16(hdr->misc); + hdr->size = bswap_16(hdr->size); } struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) { - return machine__findnew_thread(&session->machines.host, pid); + return machine__findnew_thread(&session->machines.host, 0, pid); } -static struct thread *perf_session__register_idle_thread(struct perf_session *self) +static struct thread *perf_session__register_idle_thread(struct perf_session *session) { - struct thread *thread = perf_session__findnew(self, 0); + struct thread *thread = perf_session__findnew(session, 0); - if (thread == NULL || thread__set_comm(thread, "swapper")) { + if (thread == NULL || thread__set_comm(thread, "swapper", 0)) { pr_err("problem inserting idle task.\n"); thread = NULL; } @@ -1054,12 +1147,12 @@ static void perf_session__warn_about_errors(const struct perf_session *session, } } -#define session_done() (*(volatile int *)(&session_done)) volatile int session_done; -static int __perf_session__process_pipe_events(struct perf_session *self, +static int __perf_session__process_pipe_events(struct perf_session *session, struct perf_tool *tool) { + int fd = perf_data_file__fd(session->file); union perf_event *event; uint32_t size, cur_size = 0; void *buf = NULL; @@ -1078,7 +1171,7 @@ static int __perf_session__process_pipe_events(struct perf_session *self, return -errno; more: event = buf; - err = readn(self->fd, event, sizeof(struct perf_event_header)); + err = readn(fd, event, sizeof(struct perf_event_header)); if (err <= 0) { if (err == 0) goto done; @@ -1087,12 +1180,14 @@ more: goto out_err; } - if (self->header.needs_swap) + if (session->header.needs_swap) perf_event_header__bswap(&event->header); size = event->header.size; - if (size == 0) - size = 8; + if (size < sizeof(struct perf_event_header)) { + pr_err("bad event header size\n"); + goto out_err; + } if (size > cur_size) { void *new = realloc(buf, size); @@ -1108,7 +1203,7 @@ more: p += sizeof(struct perf_event_header); if (size - sizeof(struct perf_event_header)) { - err = readn(self->fd, p, size - sizeof(struct perf_event_header)); + err = readn(fd, p, size - sizeof(struct perf_event_header)); if (err <= 0) { if (err == 0) { pr_err("unexpected end of event stream\n"); @@ -1120,7 +1215,7 @@ more: } } - if ((skip = perf_session__process_event(self, event, tool, head)) < 0) { + if ((skip = perf_session__process_event(session, event, tool, head)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", head, event->header.size, event->header.type); err = -EINVAL; @@ -1135,11 +1230,13 @@ more: if (!session_done()) goto more; done: - err = 0; + /* do the final flush for ordered samples */ + session->ordered_samples.next_flush = ULLONG_MAX; + err = flush_sample_queue(session, tool); out_err: free(buf); - perf_session__warn_about_errors(self, tool); - perf_session_free_sample_buffers(self); + perf_session__warn_about_errors(session, tool); + perf_session_free_sample_buffers(session); return err; } @@ -1161,8 +1258,12 @@ fetch_mmaped_event(struct perf_session *session, if (session->header.needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size > mmap_size) + if (head + event->header.size > mmap_size) { + /* We're not fetching the event so swap back again */ + if (session->header.needs_swap) + perf_event_header__bswap(&event->header); return NULL; + } return event; } @@ -1183,12 +1284,14 @@ int __perf_session__process_events(struct perf_session *session, u64 data_offset, u64 data_size, u64 file_size, struct perf_tool *tool) { - u64 head, page_offset, file_offset, file_pos, progress_next; + int fd = perf_data_file__fd(session->file); + u64 head, page_offset, file_offset, file_pos; int err, mmap_prot, mmap_flags, map_idx = 0; size_t mmap_size; char *buf, *mmaps[NUM_MMAPS]; union perf_event *event; uint32_t size; + struct ui_progress prog; perf_tool__fill_defaults(tool); @@ -1196,10 +1299,10 @@ int __perf_session__process_events(struct perf_session *session, file_offset = page_offset; head = data_offset - page_offset; - if (data_offset + data_size < file_size) + if (data_size && (data_offset + data_size < file_size)) file_size = data_offset + data_size; - progress_next = file_size / 16; + ui_progress__init(&prog, file_size, "Processing events..."); mmap_size = MMAP_SIZE; if (mmap_size > file_size) @@ -1215,7 +1318,7 @@ int __perf_session__process_events(struct perf_session *session, mmap_flags = MAP_PRIVATE; } remap: - buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, session->fd, + buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, fd, file_offset); if (buf == MAP_FAILED) { pr_err("failed to mmap file\n"); @@ -1242,7 +1345,7 @@ more: size = event->header.size; - if (size == 0 || + if (size < sizeof(struct perf_event_header) || perf_session__process_event(session, event, tool, file_pos) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", file_offset + head, event->header.size, @@ -1254,16 +1357,15 @@ more: head += size; file_pos += size; - if (file_pos >= progress_next) { - progress_next += file_size / 16; - ui_progress__update(file_pos, file_size, - "Processing events..."); - } + ui_progress__update(&prog, size); + + if (session_done()) + goto out; if (file_pos < file_size) goto more; - err = 0; +out: /* do the final flush for ordered samples */ session->ordered_samples.next_flush = ULLONG_MAX; err = flush_sample_queue(session, tool); @@ -1274,33 +1376,37 @@ out_err: return err; } -int perf_session__process_events(struct perf_session *self, +int perf_session__process_events(struct perf_session *session, struct perf_tool *tool) { + u64 size = perf_data_file__size(session->file); int err; - if (perf_session__register_idle_thread(self) == NULL) + if (perf_session__register_idle_thread(session) == NULL) return -ENOMEM; - if (!self->fd_pipe) - err = __perf_session__process_events(self, - self->header.data_offset, - self->header.data_size, - self->size, tool); + if (!perf_data_file__is_pipe(session->file)) + err = __perf_session__process_events(session, + session->header.data_offset, + session->header.data_size, + size, tool); else - err = __perf_session__process_pipe_events(self, tool); + err = __perf_session__process_pipe_events(session, tool); return err; } bool perf_session__has_traces(struct perf_session *session, const char *msg) { - if (!(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_RAW)) { - pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg); - return false; + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &session->evlist->entries, node) { + if (evsel->attr.type == PERF_TYPE_TRACEPOINT) + return true; } - return true; + pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg); + return false; } int maps__set_kallsyms_ref_reloc_sym(struct map **maps, @@ -1334,15 +1440,15 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps, return 0; } -size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp) +size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp) { - return machines__fprintf_dsos(&self->machines, fp); + return machines__fprintf_dsos(&session->machines, fp); } -size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp, +size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp, bool (skip)(struct dso *dso, int parm), int parm) { - return machines__fprintf_dsos_buildid(&self->machines, fp, skip, parm); + return machines__fprintf_dsos_buildid(&session->machines, fp, skip, parm); } size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) @@ -1383,13 +1489,18 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *sample, struct machine *machine, - int print_sym, int print_dso, int print_symoffset) + unsigned int print_opts, unsigned int stack_depth) { struct addr_location al; struct callchain_cursor_node *node; - - if (perf_event__preprocess_sample(event, machine, &al, sample, - NULL) < 0) { + int print_ip = print_opts & PRINT_IP_OPT_IP; + int print_sym = print_opts & PRINT_IP_OPT_SYM; + int print_dso = print_opts & PRINT_IP_OPT_DSO; + int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET; + int print_oneline = print_opts & PRINT_IP_OPT_ONELINE; + char s = print_oneline ? ' ' : '\t'; + + if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) { error("problem processing %d event, skipping it.\n", event->header.type); return; @@ -1397,37 +1508,51 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, if (symbol_conf.use_callchain && sample->callchain) { - if (machine__resolve_callchain(machine, evsel, al.thread, - sample, NULL) != 0) { + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); return; } callchain_cursor_commit(&callchain_cursor); - while (1) { + while (stack_depth) { node = callchain_cursor_current(&callchain_cursor); if (!node) break; - printf("\t%16" PRIx64, node->ip); + if (print_ip) + printf("%c%16" PRIx64, s, node->ip); + if (print_sym) { printf(" "); - symbol__fprintf_symname(node->sym, stdout); + if (print_symoffset) { + al.addr = node->ip; + al.map = node->map; + symbol__fprintf_symname_offs(node->sym, &al, stdout); + } else + symbol__fprintf_symname(node->sym, stdout); } + if (print_dso) { printf(" ("); map__fprintf_dsoname(node->map, stdout); printf(")"); } - printf("\n"); + + if (!print_oneline) + printf("\n"); callchain_cursor_advance(&callchain_cursor); + + stack_depth--; } } else { - printf("%16" PRIx64, sample->ip); + if (print_ip) + printf("%16" PRIx64, sample->ip); + if (print_sym) { printf(" "); if (print_symoffset) @@ -1489,13 +1614,14 @@ int perf_session__cpu_bitmap(struct perf_session *session, void perf_session__fprintf_info(struct perf_session *session, FILE *fp, bool full) { + int fd = perf_data_file__fd(session->file); struct stat st; int ret; if (session == NULL || fp == NULL) return; - ret = fstat(session->fd, &st); + ret = fstat(fd, &st); if (ret == -1) return; @@ -1510,52 +1636,26 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, const struct perf_evsel_str_handler *assocs, size_t nr_assocs) { - struct perf_evlist *evlist = session->evlist; - struct event_format *format; struct perf_evsel *evsel; - char *tracepoint, *name; size_t i; int err; for (i = 0; i < nr_assocs; i++) { - err = -ENOMEM; - tracepoint = strdup(assocs[i].name); - if (tracepoint == NULL) - goto out; - - err = -ENOENT; - name = strchr(tracepoint, ':'); - if (name == NULL) - goto out_free; - - *name++ = '\0'; - format = pevent_find_event_by_name(session->pevent, - tracepoint, name); - if (format == NULL) { - /* - * Adding a handler for an event not in the session, - * just ignore it. - */ - goto next; - } - - evsel = perf_evlist__find_tracepoint_by_id(evlist, format->id); + /* + * Adding a handler for an event not in the session, + * just ignore it. + */ + evsel = perf_evlist__find_tracepoint_by_name(session->evlist, assocs[i].name); if (evsel == NULL) - goto next; + continue; err = -EEXIST; - if (evsel->handler.func != NULL) - goto out_free; - evsel->handler.func = assocs[i].handler; -next: - free(tracepoint); + if (evsel->handler != NULL) + goto out; + evsel->handler = assocs[i].handler; } err = 0; out: return err; - -out_free: - free(tracepoint); - goto out; } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index f3b235ec7bf..50f640958f0 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -7,6 +7,7 @@ #include "machine.h" #include "symbol.h" #include "thread.h" +#include "data.h" #include <linux/rbtree.h> #include <linux/perf_event.h> @@ -29,65 +30,72 @@ struct ordered_samples { struct perf_session { struct perf_header header; - unsigned long size; struct machines machines; struct perf_evlist *evlist; struct pevent *pevent; struct events_stats stats; - int fd; - bool fd_pipe; bool repipe; - char *cwd; struct ordered_samples ordered_samples; - char filename[1]; + struct perf_data_file *file; }; +#define PRINT_IP_OPT_IP (1<<0) +#define PRINT_IP_OPT_SYM (1<<1) +#define PRINT_IP_OPT_DSO (1<<2) +#define PRINT_IP_OPT_SYMOFFSET (1<<3) +#define PRINT_IP_OPT_ONELINE (1<<4) + struct perf_tool; -struct perf_session *perf_session__new(const char *filename, int mode, - bool force, bool repipe, - struct perf_tool *tool); +struct perf_session *perf_session__new(struct perf_data_file *file, + bool repipe, struct perf_tool *tool); void perf_session__delete(struct perf_session *session); -void perf_event_header__bswap(struct perf_event_header *self); +void perf_event_header__bswap(struct perf_event_header *hdr); -int __perf_session__process_events(struct perf_session *self, +int __perf_session__process_events(struct perf_session *session, u64 data_offset, u64 data_size, u64 size, struct perf_tool *tool); -int perf_session__process_events(struct perf_session *self, +int perf_session__process_events(struct perf_session *session, struct perf_tool *tool); -int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel *evsel, +int perf_session_queue_event(struct perf_session *s, union perf_event *event, + struct perf_sample *sample, u64 file_offset); + +void perf_tool__fill_defaults(struct perf_tool *tool); + +int perf_session__resolve_callchain(struct perf_session *session, + struct perf_evsel *evsel, struct thread *thread, struct ip_callchain *chain, struct symbol **parent); -bool perf_session__has_traces(struct perf_session *self, const char *msg); +bool perf_session__has_traces(struct perf_session *session, const char *msg); void mem_bswap_64(void *src, int byte_size); void mem_bswap_32(void *src, int byte_size); void perf_event__attr_swap(struct perf_event_attr *attr); -int perf_session__create_kernel_maps(struct perf_session *self); +int perf_session__create_kernel_maps(struct perf_session *session); void perf_session__set_id_hdr_size(struct perf_session *session); static inline -struct machine *perf_session__find_machine(struct perf_session *self, pid_t pid) +struct machine *perf_session__find_machine(struct perf_session *session, pid_t pid) { - return machines__find(&self->machines, pid); + return machines__find(&session->machines, pid); } static inline -struct machine *perf_session__findnew_machine(struct perf_session *self, pid_t pid) +struct machine *perf_session__findnew_machine(struct perf_session *session, pid_t pid) { - return machines__findnew(&self->machines, pid); + return machines__findnew(&session->machines, pid); } -struct thread *perf_session__findnew(struct perf_session *self, pid_t pid); -size_t perf_session__fprintf(struct perf_session *self, FILE *fp); +struct thread *perf_session__findnew(struct perf_session *session, pid_t pid); +size_t perf_session__fprintf(struct perf_session *session, FILE *fp); -size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp); +size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp); size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp, bool (fn)(struct dso *dso, int parm), int parm); @@ -99,7 +107,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, struct perf_sample *sample, struct machine *machine, - int print_sym, int print_dso, int print_symoffset); + unsigned int print_opts, unsigned int stack_depth); int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap); @@ -114,4 +122,8 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, #define perf_session__set_tracepoints_handlers(session, array) \ __perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array)) + +extern volatile int session_done; + +#define session_done() (*(volatile int *)(&session_done)) #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 313a5a73011..3c1b75c8b9a 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1,5 +1,6 @@ #include "sort.h" #include "hist.h" +#include "comm.h" #include "symbol.h" regex_t parent_regex; @@ -7,6 +8,8 @@ const char default_parent_pattern[] = "^sys_|^do_page_fault"; const char *parent_pattern = default_parent_pattern; const char default_sort_order[] = "comm,dso,symbol"; const char *sort_order = default_sort_order; +regex_t ignore_callees_regex; +int have_ignore_callees = 0; int sort__need_collapse = 0; int sort__has_parent = 0; int sort__has_sym = 0; @@ -40,7 +43,7 @@ static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...) return n; } -static int64_t cmp_null(void *l, void *r) +static int64_t cmp_null(const void *l, const void *r) { if (!l && !r) return 0; @@ -55,14 +58,15 @@ static int64_t cmp_null(void *l, void *r) static int64_t sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) { - return right->thread->pid - left->thread->pid; + return right->thread->tid - left->thread->tid; } -static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { + const char *comm = thread__comm_str(he->thread); return repsep_snprintf(bf, size, "%*s:%5d", width - 6, - self->thread->comm ?: "", self->thread->pid); + comm ?: "", he->thread->tid); } struct sort_entry sort_thread = { @@ -77,25 +81,21 @@ struct sort_entry sort_thread = { static int64_t sort__comm_cmp(struct hist_entry *left, struct hist_entry *right) { - return right->thread->pid - left->thread->pid; + /* Compare the addr that should be unique among comm */ + return comm__str(right->comm) - comm__str(left->comm); } static int64_t sort__comm_collapse(struct hist_entry *left, struct hist_entry *right) { - char *comm_l = left->thread->comm; - char *comm_r = right->thread->comm; - - if (!comm_l || !comm_r) - return cmp_null(comm_l, comm_r); - - return strcmp(comm_l, comm_r); + /* Compare the addr that should be unique among comm */ + return comm__str(right->comm) - comm__str(left->comm); } -static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*s", width, self->thread->comm); + return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm)); } struct sort_entry sort_comm = { @@ -146,10 +146,10 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf, return repsep_snprintf(bf, size, "%-*s", width, "[unknown]"); } -static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__dso_snprintf(self->ms.map, bf, size, width); + return _hist_entry__dso_snprintf(he->ms.map, bf, size, width); } struct sort_entry sort_dso = { @@ -180,9 +180,19 @@ static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r) static int64_t sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) { + int64_t ret; + if (!left->ms.sym && !right->ms.sym) return right->level - left->level; + /* + * comparing symbol address alone is not enough since it's a + * relative address within a dso. + */ + ret = sort__dso_cmp(left, right); + if (ret != 0) + return ret; + return _sort__sym_cmp(left->ms.sym, right->ms.sym); } @@ -222,11 +232,11 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, return ret; } -static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip, - self->level, bf, size, width); + return _hist_entry__sym_snprintf(he->ms.map, he->ms.sym, he->ip, + he->level, bf, size, width); } struct sort_entry sort_sym = { @@ -241,50 +251,32 @@ struct sort_entry sort_sym = { static int64_t sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) { - return (int64_t)(right->ip - left->ip); + if (!left->srcline) { + if (!left->ms.map) + left->srcline = SRCLINE_UNKNOWN; + else { + struct map *map = left->ms.map; + left->srcline = get_srcline(map->dso, + map__rip_2objdump(map, left->ip)); + } + } + if (!right->srcline) { + if (!right->ms.map) + right->srcline = SRCLINE_UNKNOWN; + else { + struct map *map = right->ms.map; + right->srcline = get_srcline(map->dso, + map__rip_2objdump(map, right->ip)); + } + } + return strcmp(left->srcline, right->srcline); } -static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width __maybe_unused) { - FILE *fp = NULL; - char cmd[PATH_MAX + 2], *path = self->srcline, *nl; - size_t line_len; - - if (path != NULL) - goto out_path; - - if (!self->ms.map) - goto out_ip; - - if (!strncmp(self->ms.map->dso->long_name, "/tmp/perf-", 10)) - goto out_ip; - - snprintf(cmd, sizeof(cmd), "addr2line -e %s %016" PRIx64, - self->ms.map->dso->long_name, self->ip); - fp = popen(cmd, "r"); - if (!fp) - goto out_ip; - - if (getline(&path, &line_len, fp) < 0 || !line_len) - goto out_ip; - self->srcline = strdup(path); - if (self->srcline == NULL) - goto out_ip; - - nl = strchr(self->srcline, '\n'); - if (nl != NULL) - *nl = '\0'; - path = self->srcline; -out_path: - if (fp) - pclose(fp); - return repsep_snprintf(bf, size, "%s", path); -out_ip: - if (fp) - pclose(fp); - return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip); + return repsep_snprintf(bf, size, "%s", he->srcline); } struct sort_entry sort_srcline = { @@ -308,11 +300,11 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right) return strcmp(sym_l->name, sym_r->name); } -static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { return repsep_snprintf(bf, size, "%-*s", width, - self->parent ? self->parent->name : "[other]"); + he->parent ? he->parent->name : "[other]"); } struct sort_entry sort_parent = { @@ -330,10 +322,10 @@ sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right) return right->cpu - left->cpu; } -static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf, - size_t size, unsigned int width) +static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*d", width, self->cpu); + return repsep_snprintf(bf, size, "%*d", width, he->cpu); } struct sort_entry sort_cpu = { @@ -352,10 +344,10 @@ sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right) right->branch_info->from.map); } -static int hist_entry__dso_from_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__dso_snprintf(self->branch_info->from.map, + return _hist_entry__dso_snprintf(he->branch_info->from.map, bf, size, width); } @@ -366,10 +358,10 @@ sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) right->branch_info->to.map); } -static int hist_entry__dso_to_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return _hist_entry__dso_snprintf(self->branch_info->to.map, + return _hist_entry__dso_snprintf(he->branch_info->to.map, bf, size, width); } @@ -397,21 +389,21 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) return _sort__sym_cmp(to_l->sym, to_r->sym); } -static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - struct addr_map_symbol *from = &self->branch_info->from; + struct addr_map_symbol *from = &he->branch_info->from; return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, - self->level, bf, size, width); + he->level, bf, size, width); } -static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - struct addr_map_symbol *to = &self->branch_info->to; + struct addr_map_symbol *to = &he->branch_info->to; return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, - self->level, bf, size, width); + he->level, bf, size, width); } @@ -454,13 +446,13 @@ sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right) return mp || p; } -static int hist_entry__mispredict_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width){ static const char *out = "N/A"; - if (self->branch_info->flags.predicted) + if (he->branch_info->flags.predicted) out = "N"; - else if (self->branch_info->flags.mispred) + else if (he->branch_info->flags.mispred) out = "Y"; return repsep_snprintf(bf, size, "%-*s", width, out); @@ -480,19 +472,19 @@ sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right) return (int64_t)(r - l); } -static int hist_entry__daddr_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__daddr_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { uint64_t addr = 0; struct map *map = NULL; struct symbol *sym = NULL; - if (self->mem_info) { - addr = self->mem_info->daddr.addr; - map = self->mem_info->daddr.map; - sym = self->mem_info->daddr.sym; + if (he->mem_info) { + addr = he->mem_info->daddr.addr; + map = he->mem_info->daddr.map; + sym = he->mem_info->daddr.sym; } - return _hist_entry__sym_snprintf(map, sym, addr, self->level, bf, size, + return _hist_entry__sym_snprintf(map, sym, addr, he->level, bf, size, width); } @@ -510,13 +502,13 @@ sort__dso_daddr_cmp(struct hist_entry *left, struct hist_entry *right) return _sort__dso_cmp(map_l, map_r); } -static int hist_entry__dso_daddr_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__dso_daddr_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { struct map *map = NULL; - if (self->mem_info) - map = self->mem_info->daddr.map; + if (he->mem_info) + map = he->mem_info->daddr.map; return _hist_entry__dso_snprintf(map, bf, size, width); } @@ -540,14 +532,14 @@ sort__locked_cmp(struct hist_entry *left, struct hist_entry *right) return (int64_t)(data_src_r.mem_lock - data_src_l.mem_lock); } -static int hist_entry__locked_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__locked_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { const char *out; u64 mask = PERF_MEM_LOCK_NA; - if (self->mem_info) - mask = self->mem_info->data_src.mem_lock; + if (he->mem_info) + mask = he->mem_info->data_src.mem_lock; if (mask & PERF_MEM_LOCK_NA) out = "N/A"; @@ -589,7 +581,7 @@ static const char * const tlb_access[] = { }; #define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *)) -static int hist_entry__tlb_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { char out[64]; @@ -600,8 +592,8 @@ static int hist_entry__tlb_snprintf(struct hist_entry *self, char *bf, out[0] = '\0'; - if (self->mem_info) - m = self->mem_info->data_src.mem_dtlb; + if (he->mem_info) + m = he->mem_info->data_src.mem_dtlb; hit = m & PERF_MEM_TLB_HIT; miss = m & PERF_MEM_TLB_MISS; @@ -666,7 +658,7 @@ static const char * const mem_lvl[] = { }; #define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *)) -static int hist_entry__lvl_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { char out[64]; @@ -675,8 +667,8 @@ static int hist_entry__lvl_snprintf(struct hist_entry *self, char *bf, u64 m = PERF_MEM_LVL_NA; u64 hit, miss; - if (self->mem_info) - m = self->mem_info->data_src.mem_lvl; + if (he->mem_info) + m = he->mem_info->data_src.mem_lvl; out[0] = '\0'; @@ -734,7 +726,7 @@ static const char * const snoop_access[] = { }; #define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *)) -static int hist_entry__snoop_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { char out[64]; @@ -744,8 +736,8 @@ static int hist_entry__snoop_snprintf(struct hist_entry *self, char *bf, out[0] = '\0'; - if (self->mem_info) - m = self->mem_info->data_src.mem_snoop; + if (he->mem_info) + m = he->mem_info->data_src.mem_snoop; for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) { if (!(m & 0x1)) @@ -782,10 +774,10 @@ sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right) return he_weight(left) - he_weight(right); } -static int hist_entry__local_weight_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__local_weight_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*llu", width, he_weight(self)); + return repsep_snprintf(bf, size, "%-*llu", width, he_weight(he)); } struct sort_entry sort_local_weight = { @@ -801,10 +793,10 @@ sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right) return left->stat.weight - right->stat.weight; } -static int hist_entry__global_weight_snprintf(struct hist_entry *self, char *bf, +static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*llu", width, self->stat.weight); + return repsep_snprintf(bf, size, "%-*llu", width, he->stat.weight); } struct sort_entry sort_global_weight = { @@ -856,6 +848,127 @@ struct sort_entry sort_mem_snoop = { .se_width_idx = HISTC_MEM_SNOOP, }; +static int64_t +sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return left->branch_info->flags.abort != + right->branch_info->flags.abort; +} + +static int hist_entry__abort_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + static const char *out = "."; + + if (he->branch_info->flags.abort) + out = "A"; + return repsep_snprintf(bf, size, "%-*s", width, out); +} + +struct sort_entry sort_abort = { + .se_header = "Transaction abort", + .se_cmp = sort__abort_cmp, + .se_snprintf = hist_entry__abort_snprintf, + .se_width_idx = HISTC_ABORT, +}; + +static int64_t +sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return left->branch_info->flags.in_tx != + right->branch_info->flags.in_tx; +} + +static int hist_entry__in_tx_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + static const char *out = "."; + + if (he->branch_info->flags.in_tx) + out = "T"; + + return repsep_snprintf(bf, size, "%-*s", width, out); +} + +struct sort_entry sort_in_tx = { + .se_header = "Branch in transaction", + .se_cmp = sort__in_tx_cmp, + .se_snprintf = hist_entry__in_tx_snprintf, + .se_width_idx = HISTC_IN_TX, +}; + +static int64_t +sort__transaction_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return left->transaction - right->transaction; +} + +static inline char *add_str(char *p, const char *str) +{ + strcpy(p, str); + return p + strlen(str); +} + +static struct txbit { + unsigned flag; + const char *name; + int skip_for_len; +} txbits[] = { + { PERF_TXN_ELISION, "EL ", 0 }, + { PERF_TXN_TRANSACTION, "TX ", 1 }, + { PERF_TXN_SYNC, "SYNC ", 1 }, + { PERF_TXN_ASYNC, "ASYNC ", 0 }, + { PERF_TXN_RETRY, "RETRY ", 0 }, + { PERF_TXN_CONFLICT, "CON ", 0 }, + { PERF_TXN_CAPACITY_WRITE, "CAP-WRITE ", 1 }, + { PERF_TXN_CAPACITY_READ, "CAP-READ ", 0 }, + { 0, NULL, 0 } +}; + +int hist_entry__transaction_len(void) +{ + int i; + int len = 0; + + for (i = 0; txbits[i].name; i++) { + if (!txbits[i].skip_for_len) + len += strlen(txbits[i].name); + } + len += 4; /* :XX<space> */ + return len; +} + +static int hist_entry__transaction_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + u64 t = he->transaction; + char buf[128]; + char *p = buf; + int i; + + buf[0] = 0; + for (i = 0; txbits[i].name; i++) + if (txbits[i].flag & t) + p = add_str(p, txbits[i].name); + if (t && !(t & (PERF_TXN_SYNC|PERF_TXN_ASYNC))) + p = add_str(p, "NEITHER "); + if (t & PERF_TXN_ABORT_MASK) { + sprintf(p, ":%" PRIx64, + (t & PERF_TXN_ABORT_MASK) >> + PERF_TXN_ABORT_SHIFT); + p += strlen(p); + } + + return repsep_snprintf(bf, size, "%-*s", width, buf); +} + +struct sort_entry sort_transaction = { + .se_header = "Transaction ", + .se_cmp = sort__transaction_cmp, + .se_snprintf = hist_entry__transaction_snprintf, + .se_width_idx = HISTC_TRANSACTION, +}; + struct sort_dimension { const char *name; struct sort_entry *entry; @@ -872,6 +985,9 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_PARENT, "parent", sort_parent), DIM(SORT_CPU, "cpu", sort_cpu), DIM(SORT_SRCLINE, "srcline", sort_srcline), + DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight), + DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), + DIM(SORT_TRANSACTION, "transaction", sort_transaction), }; #undef DIM @@ -884,6 +1000,8 @@ static struct sort_dimension bstack_sort_dimensions[] = { DIM(SORT_SYM_FROM, "symbol_from", sort_sym_from), DIM(SORT_SYM_TO, "symbol_to", sort_sym_to), DIM(SORT_MISPREDICT, "mispredict", sort_mispredict), + DIM(SORT_IN_TX, "in_tx", sort_in_tx), + DIM(SORT_ABORT, "abort", sort_abort), }; #undef DIM @@ -891,8 +1009,6 @@ static struct sort_dimension bstack_sort_dimensions[] = { #define DIM(d, n, func) [d - __SORT_MEMORY_MODE] = { .name = n, .entry = &(func) } static struct sort_dimension memory_sort_dimensions[] = { - DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight), - DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym), DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso), DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked), @@ -1007,7 +1123,7 @@ int setup_sorting(void) return ret; } -static void sort_entry__setup_elide(struct sort_entry *self, +static void sort_entry__setup_elide(struct sort_entry *se, struct strlist *list, const char *list_name, FILE *fp) { @@ -1015,7 +1131,7 @@ static void sort_entry__setup_elide(struct sort_entry *self, if (fp != NULL) fprintf(fp, "# %s: %s\n", list_name, strlist__entry(list, 0)->s); - self->elide = true; + se->elide = true; } } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 45ac84c1e03..43e5ff42a60 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -22,13 +22,14 @@ #include "parse-events.h" #include "thread.h" -#include "sort.h" extern regex_t parent_regex; extern const char *sort_order; extern const char default_parent_pattern[]; extern const char *parent_pattern; extern const char default_sort_order[]; +extern regex_t ignore_callees_regex; +extern int have_ignore_callees; extern int sort__need_collapse; extern int sort__has_parent; extern int sort__has_sym; @@ -82,11 +83,16 @@ struct hist_entry { struct he_stat stat; struct map_symbol ms; struct thread *thread; + struct comm *comm; u64 ip; + u64 transaction; s32 cpu; struct hist_entry_diff diff; + /* We are added by hists__add_dummy_entry. */ + bool dummy; + /* XXX These two should move to some tree widget lib */ u16 row_offset; u16 nr_rows; @@ -138,6 +144,9 @@ enum sort_type { SORT_PARENT, SORT_CPU, SORT_SRCLINE, + SORT_LOCAL_WEIGHT, + SORT_GLOBAL_WEIGHT, + SORT_TRANSACTION, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, @@ -146,12 +155,12 @@ enum sort_type { SORT_SYM_FROM, SORT_SYM_TO, SORT_MISPREDICT, + SORT_ABORT, + SORT_IN_TX, /* memory mode specific sort keys */ __SORT_MEMORY_MODE, - SORT_LOCAL_WEIGHT = __SORT_MEMORY_MODE, - SORT_GLOBAL_WEIGHT, - SORT_MEM_DADDR_SYMBOL, + SORT_MEM_DADDR_SYMBOL = __SORT_MEMORY_MODE, SORT_MEM_DADDR_DSO, SORT_MEM_LOCKED, SORT_MEM_TLB, @@ -170,7 +179,7 @@ struct sort_entry { int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *); int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *); - int (*se_snprintf)(struct hist_entry *self, char *bf, size_t size, + int (*se_snprintf)(struct hist_entry *he, char *bf, size_t size, unsigned int width); u8 se_width_idx; bool elide; @@ -183,4 +192,6 @@ int setup_sorting(void); extern int sort_dimension__add(const char *); void sort__setup_elide(FILE *fp); +int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset); + #endif /* __PERF_SORT_H */ diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c new file mode 100644 index 00000000000..d11aefbc4b8 --- /dev/null +++ b/tools/perf/util/srcline.c @@ -0,0 +1,265 @@ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include <linux/kernel.h> + +#include "util/dso.h" +#include "util/util.h" +#include "util/debug.h" + +#ifdef HAVE_LIBBFD_SUPPORT + +/* + * Implement addr2line using libbfd. + */ +#define PACKAGE "perf" +#include <bfd.h> + +struct a2l_data { + const char *input; + unsigned long addr; + + bool found; + const char *filename; + const char *funcname; + unsigned line; + + bfd *abfd; + asymbol **syms; +}; + +static int bfd_error(const char *string) +{ + const char *errmsg; + + errmsg = bfd_errmsg(bfd_get_error()); + fflush(stdout); + + if (string) + pr_debug("%s: %s\n", string, errmsg); + else + pr_debug("%s\n", errmsg); + + return -1; +} + +static int slurp_symtab(bfd *abfd, struct a2l_data *a2l) +{ + long storage; + long symcount; + asymbol **syms; + bfd_boolean dynamic = FALSE; + + if ((bfd_get_file_flags(abfd) & HAS_SYMS) == 0) + return bfd_error(bfd_get_filename(abfd)); + + storage = bfd_get_symtab_upper_bound(abfd); + if (storage == 0L) { + storage = bfd_get_dynamic_symtab_upper_bound(abfd); + dynamic = TRUE; + } + if (storage < 0L) + return bfd_error(bfd_get_filename(abfd)); + + syms = malloc(storage); + if (dynamic) + symcount = bfd_canonicalize_dynamic_symtab(abfd, syms); + else + symcount = bfd_canonicalize_symtab(abfd, syms); + + if (symcount < 0) { + free(syms); + return bfd_error(bfd_get_filename(abfd)); + } + + a2l->syms = syms; + return 0; +} + +static void find_address_in_section(bfd *abfd, asection *section, void *data) +{ + bfd_vma pc, vma; + bfd_size_type size; + struct a2l_data *a2l = data; + + if (a2l->found) + return; + + if ((bfd_get_section_flags(abfd, section) & SEC_ALLOC) == 0) + return; + + pc = a2l->addr; + vma = bfd_get_section_vma(abfd, section); + size = bfd_get_section_size(section); + + if (pc < vma || pc >= vma + size) + return; + + a2l->found = bfd_find_nearest_line(abfd, section, a2l->syms, pc - vma, + &a2l->filename, &a2l->funcname, + &a2l->line); +} + +static struct a2l_data *addr2line_init(const char *path) +{ + bfd *abfd; + struct a2l_data *a2l = NULL; + + abfd = bfd_openr(path, NULL); + if (abfd == NULL) + return NULL; + + if (!bfd_check_format(abfd, bfd_object)) + goto out; + + a2l = zalloc(sizeof(*a2l)); + if (a2l == NULL) + goto out; + + a2l->abfd = abfd; + a2l->input = strdup(path); + if (a2l->input == NULL) + goto out; + + if (slurp_symtab(abfd, a2l)) + goto out; + + return a2l; + +out: + if (a2l) { + free((void *)a2l->input); + free(a2l); + } + bfd_close(abfd); + return NULL; +} + +static void addr2line_cleanup(struct a2l_data *a2l) +{ + if (a2l->abfd) + bfd_close(a2l->abfd); + free((void *)a2l->input); + free(a2l->syms); + free(a2l); +} + +static int addr2line(const char *dso_name, unsigned long addr, + char **file, unsigned int *line) +{ + int ret = 0; + struct a2l_data *a2l; + + a2l = addr2line_init(dso_name); + if (a2l == NULL) { + pr_warning("addr2line_init failed for %s\n", dso_name); + return 0; + } + + a2l->addr = addr; + bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l); + + if (a2l->found && a2l->filename) { + *file = strdup(a2l->filename); + *line = a2l->line; + + if (*file) + ret = 1; + } + + addr2line_cleanup(a2l); + return ret; +} + +#else /* HAVE_LIBBFD_SUPPORT */ + +static int addr2line(const char *dso_name, unsigned long addr, + char **file, unsigned int *line_nr) +{ + FILE *fp; + char cmd[PATH_MAX]; + char *filename = NULL; + size_t len; + char *sep; + int ret = 0; + + scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64, + dso_name, addr); + + fp = popen(cmd, "r"); + if (fp == NULL) { + pr_warning("popen failed for %s\n", dso_name); + return 0; + } + + if (getline(&filename, &len, fp) < 0 || !len) { + pr_warning("addr2line has no output for %s\n", dso_name); + goto out; + } + + sep = strchr(filename, '\n'); + if (sep) + *sep = '\0'; + + if (!strcmp(filename, "??:0")) { + pr_debug("no debugging info in %s\n", dso_name); + free(filename); + goto out; + } + + sep = strchr(filename, ':'); + if (sep) { + *sep++ = '\0'; + *file = filename; + *line_nr = strtoul(sep, NULL, 0); + ret = 1; + } +out: + pclose(fp); + return ret; +} +#endif /* HAVE_LIBBFD_SUPPORT */ + +char *get_srcline(struct dso *dso, unsigned long addr) +{ + char *file = NULL; + unsigned line = 0; + char *srcline; + char *dso_name = dso->long_name; + size_t size; + + if (!dso->has_srcline) + return SRCLINE_UNKNOWN; + + if (dso_name[0] == '[') + goto out; + + if (!strncmp(dso_name, "/tmp/perf-", 10)) + goto out; + + if (!addr2line(dso_name, addr, &file, &line)) + goto out; + + /* just calculate actual length */ + size = snprintf(NULL, 0, "%s:%u", file, line) + 1; + + srcline = malloc(size); + if (srcline) + snprintf(srcline, size, "%s:%u", file, line); + else + srcline = SRCLINE_UNKNOWN; + + free(file); + return srcline; + +out: + dso->has_srcline = 0; + return SRCLINE_UNKNOWN; +} + +void free_srcline(char *srcline) +{ + if (srcline && strcmp(srcline, SRCLINE_UNKNOWN) != 0) + free(srcline); +} diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 7c59c28afcc..6506b3dfb60 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -10,6 +10,12 @@ void update_stats(struct stats *stats, u64 val) delta = val - stats->mean; stats->mean += delta / stats->n; stats->M2 += delta*(val - stats->mean); + + if (val > stats->max) + stats->max = val; + + if (val < stats->min) + stats->min = val; } double avg_stats(struct stats *stats) diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 588367c3c76..ae8ccd7227c 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -6,6 +6,7 @@ struct stats { double n, mean, M2; + u64 max, min; }; void update_stats(struct stats *stats, u64 val); @@ -13,4 +14,12 @@ double avg_stats(struct stats *stats); double stddev_stats(struct stats *stats); double rel_stddev_stats(double stddev, double avg); +static inline void init_stats(struct stats *stats) +{ + stats->n = 0.0; + stats->mean = 0.0; + stats->M2 = 0.0; + stats->min = (u64) -1; + stats->max = 0; +} #endif diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c index 834c8ebfe38..3edd0538161 100644 --- a/tools/perf/util/strfilter.c +++ b/tools/perf/util/strfilter.c @@ -10,22 +10,22 @@ static const char *OP_not = "!"; /* Logical NOT */ #define is_operator(c) ((c) == '|' || (c) == '&' || (c) == '!') #define is_separator(c) (is_operator(c) || (c) == '(' || (c) == ')') -static void strfilter_node__delete(struct strfilter_node *self) +static void strfilter_node__delete(struct strfilter_node *node) { - if (self) { - if (self->p && !is_operator(*self->p)) - free((char *)self->p); - strfilter_node__delete(self->l); - strfilter_node__delete(self->r); - free(self); + if (node) { + if (node->p && !is_operator(*node->p)) + free((char *)node->p); + strfilter_node__delete(node->l); + strfilter_node__delete(node->r); + free(node); } } -void strfilter__delete(struct strfilter *self) +void strfilter__delete(struct strfilter *filter) { - if (self) { - strfilter_node__delete(self->root); - free(self); + if (filter) { + strfilter_node__delete(filter->root); + free(filter); } } @@ -62,15 +62,15 @@ static struct strfilter_node *strfilter_node__alloc(const char *op, struct strfilter_node *l, struct strfilter_node *r) { - struct strfilter_node *ret = zalloc(sizeof(struct strfilter_node)); + struct strfilter_node *node = zalloc(sizeof(*node)); - if (ret) { - ret->p = op; - ret->l = l; - ret->r = r; + if (node) { + node->p = op; + node->l = l; + node->r = r; } - return ret; + return node; } static struct strfilter_node *strfilter_node__new(const char *s, @@ -154,46 +154,46 @@ error: */ struct strfilter *strfilter__new(const char *rules, const char **err) { - struct strfilter *ret = zalloc(sizeof(struct strfilter)); + struct strfilter *filter = zalloc(sizeof(*filter)); const char *ep = NULL; - if (ret) - ret->root = strfilter_node__new(rules, &ep); + if (filter) + filter->root = strfilter_node__new(rules, &ep); - if (!ret || !ret->root || *ep != '\0') { + if (!filter || !filter->root || *ep != '\0') { if (err) *err = ep; - strfilter__delete(ret); - ret = NULL; + strfilter__delete(filter); + filter = NULL; } - return ret; + return filter; } -static bool strfilter_node__compare(struct strfilter_node *self, +static bool strfilter_node__compare(struct strfilter_node *node, const char *str) { - if (!self || !self->p) + if (!node || !node->p) return false; - switch (*self->p) { + switch (*node->p) { case '|': /* OR */ - return strfilter_node__compare(self->l, str) || - strfilter_node__compare(self->r, str); + return strfilter_node__compare(node->l, str) || + strfilter_node__compare(node->r, str); case '&': /* AND */ - return strfilter_node__compare(self->l, str) && - strfilter_node__compare(self->r, str); + return strfilter_node__compare(node->l, str) && + strfilter_node__compare(node->r, str); case '!': /* NOT */ - return !strfilter_node__compare(self->r, str); + return !strfilter_node__compare(node->r, str); default: - return strglobmatch(str, self->p); + return strglobmatch(str, node->p); } } /* Return true if STR matches the filter rules */ -bool strfilter__compare(struct strfilter *self, const char *str) +bool strfilter__compare(struct strfilter *filter, const char *str) { - if (!self) + if (!filter) return false; - return strfilter_node__compare(self->root, str); + return strfilter_node__compare(filter->root, str); } diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h index 00f58a7506d..fe611f3c9e3 100644 --- a/tools/perf/util/strfilter.h +++ b/tools/perf/util/strfilter.h @@ -30,19 +30,19 @@ struct strfilter *strfilter__new(const char *rules, const char **err); /** * strfilter__compare - compare given string and a string filter - * @self: String filter + * @filter: String filter * @str: target string * - * Compare @str and @self. Return true if the str match the rule + * Compare @str and @filter. Return true if the str match the rule */ -bool strfilter__compare(struct strfilter *self, const char *str); +bool strfilter__compare(struct strfilter *filter, const char *str); /** * strfilter__delete - delete a string filter - * @self: String filter to delete + * @filter: String filter to delete * - * Delete @self. + * Delete @filter. */ -void strfilter__delete(struct strfilter *self); +void strfilter__delete(struct strfilter *filter); #endif diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index 29c7b2cb252..f0b0c008c50 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -387,3 +387,27 @@ void *memdup(const void *src, size_t len) return p; } + +/** + * str_append - reallocate string and append another + * @s: pointer to string pointer + * @len: pointer to len (initialized) + * @a: string to append. + */ +int str_append(char **s, int *len, const char *a) +{ + int olen = *s ? strlen(*s) : 0; + int nlen = olen + strlen(a) + 1; + if (*len < nlen) { + *len = *len * 2; + if (*len < nlen) + *len = nlen; + *s = realloc(*s, *len); + if (!*s) + return -ENOMEM; + if (olen == 0) + **s = 0; + } + strcat(*s, a); + return 0; +} diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 4b12bf85032..eed0b96302a 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -8,6 +8,22 @@ #include "symbol.h" #include "debug.h" +#ifndef HAVE_ELF_GETPHDRNUM_SUPPORT +static int elf_getphdrnum(Elf *elf, size_t *dst) +{ + GElf_Ehdr gehdr; + GElf_Ehdr *ehdr; + + ehdr = gelf_getehdr(elf, &gehdr); + if (!ehdr) + return -1; + + *dst = ehdr->e_phnum; + + return 0; +} +#endif + #ifndef NT_GNU_BUILD_ID #define NT_GNU_BUILD_ID 3 #endif @@ -471,27 +487,27 @@ int filename__read_debuglink(const char *filename, char *debuglink, ek = elf_kind(elf); if (ek != ELF_K_ELF) - goto out_close; + goto out_elf_end; if (gelf_getehdr(elf, &ehdr) == NULL) { pr_err("%s: cannot get elf header.\n", __func__); - goto out_close; + goto out_elf_end; } sec = elf_section_by_name(elf, &ehdr, &shdr, ".gnu_debuglink", NULL); if (sec == NULL) - goto out_close; + goto out_elf_end; data = elf_getdata(sec, NULL); if (data == NULL) - goto out_close; + goto out_elf_end; /* the start of this section is a zero-terminated string */ strncpy(debuglink, data->d_buf, size); +out_elf_end: elf_end(elf); - out_close: close(fd); out: @@ -599,11 +615,13 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, if (dso->kernel == DSO_TYPE_USER) { GElf_Shdr shdr; ss->adjust_symbols = (ehdr.e_type == ET_EXEC || + ehdr.e_type == ET_REL || elf_section_by_name(elf, &ehdr, &shdr, ".gnu.prelink_undo", NULL) != NULL); } else { - ss->adjust_symbols = 0; + ss->adjust_symbols = ehdr.e_type == ET_EXEC || + ehdr.e_type == ET_REL; } ss->name = strdup(name); @@ -624,6 +642,37 @@ out_close: return err; } +/** + * ref_reloc_sym_not_found - has kernel relocation symbol been found. + * @kmap: kernel maps and relocation reference symbol + * + * This function returns %true if we are dealing with the kernel maps and the + * relocation reference symbol has not yet been found. Otherwise %false is + * returned. + */ +static bool ref_reloc_sym_not_found(struct kmap *kmap) +{ + return kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name && + !kmap->ref_reloc_sym->unrelocated_addr; +} + +/** + * ref_reloc - kernel relocation offset. + * @kmap: kernel maps and relocation reference symbol + * + * This function returns the offset of kernel addresses as determined by using + * the relocation reference symbol i.e. if the kernel has not been relocated + * then the return value is zero. + */ +static u64 ref_reloc(struct kmap *kmap) +{ + if (kmap && kmap->ref_reloc_sym && + kmap->ref_reloc_sym->unrelocated_addr) + return kmap->ref_reloc_sym->addr - + kmap->ref_reloc_sym->unrelocated_addr; + return 0; +} + int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, symbol_filter_t filter, int kmodule) @@ -642,8 +691,17 @@ int dso__load_sym(struct dso *dso, struct map *map, Elf_Scn *sec, *sec_strndx; Elf *elf; int nr = 0; + bool remap_kernel = false, adjust_kernel_syms = false; dso->symtab_type = syms_ss->type; + dso->rel = syms_ss->ehdr.e_type == ET_REL; + + /* + * Modules may already have symbols from kallsyms, but those symbols + * have the wrong values for the dso maps, so remove them. + */ + if (kmodule && syms_ss->symtab) + symbols__delete(&dso->symbols[map->type]); if (!syms_ss->symtab) { syms_ss->symtab = syms_ss->dynsym; @@ -681,7 +739,31 @@ int dso__load_sym(struct dso *dso, struct map *map, nr_syms = shdr.sh_size / shdr.sh_entsize; memset(&sym, 0, sizeof(sym)); - dso->adjust_symbols = runtime_ss->adjust_symbols; + + /* + * The kernel relocation symbol is needed in advance in order to adjust + * kernel maps correctly. + */ + if (ref_reloc_sym_not_found(kmap)) { + elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) { + const char *elf_name = elf_sym__name(&sym, symstrs); + + if (strcmp(elf_name, kmap->ref_reloc_sym->name)) + continue; + kmap->ref_reloc_sym->unrelocated_addr = sym.st_value; + break; + } + } + + 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. + */ + if (map->type == MAP__FUNCTION && (dso->kernel || kmodule)) { + remap_kernel = true; + adjust_kernel_syms = dso->adjust_symbols; + } elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) { struct symbol *f; const char *elf_name = elf_sym__name(&sym, symstrs); @@ -690,10 +772,6 @@ int dso__load_sym(struct dso *dso, struct map *map, const char *section_name; bool used_opd = false; - if (kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name && - strcmp(elf_name, kmap->ref_reloc_sym->name) == 0) - kmap->ref_reloc_sym->unrelocated_addr = sym.st_value; - if (!is_label && !elf_sym__is_a(&sym, map->type)) continue; @@ -745,20 +823,55 @@ int dso__load_sym(struct dso *dso, struct map *map, (sym.st_value & 1)) --sym.st_value; - if (dso->kernel != DSO_TYPE_USER || kmodule) { + 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 */ + map_groups__remove(kmap->kmaps, map); + map_groups__insert(kmap->kmaps, 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); @@ -781,8 +894,16 @@ int dso__load_sym(struct dso *dso, struct map *map, dso__delete(curr_dso); goto out_elf_end; } - curr_map->map_ip = identity__map_ip; - curr_map->unmap_ip = identity__map_ip; + 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(kmap->kmaps, curr_map); dsos__add(&dso->node, curr_dso); @@ -846,6 +967,652 @@ out_elf_end: return err; } +static int elf_read_maps(Elf *elf, bool exe, mapfn_t mapfn, void *data) +{ + GElf_Phdr phdr; + size_t i, phdrnum; + int err; + u64 sz; + + if (elf_getphdrnum(elf, &phdrnum)) + return -1; + + for (i = 0; i < phdrnum; i++) { + if (gelf_getphdr(elf, i, &phdr) == NULL) + return -1; + if (phdr.p_type != PT_LOAD) + continue; + if (exe) { + if (!(phdr.p_flags & PF_X)) + continue; + } else { + if (!(phdr.p_flags & PF_R)) + continue; + } + sz = min(phdr.p_memsz, phdr.p_filesz); + if (!sz) + continue; + err = mapfn(phdr.p_vaddr, sz, phdr.p_offset, data); + if (err) + return err; + } + return 0; +} + +int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data, + bool *is_64_bit) +{ + int err; + Elf *elf; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + return -1; + + if (is_64_bit) + *is_64_bit = (gelf_getclass(elf) == ELFCLASS64); + + err = elf_read_maps(elf, exe, mapfn, data); + + elf_end(elf); + return err; +} + +static int copy_bytes(int from, off_t from_offs, int to, off_t to_offs, u64 len) +{ + ssize_t r; + size_t n; + int err = -1; + char *buf = malloc(page_size); + + if (buf == NULL) + return -1; + + if (lseek(to, to_offs, SEEK_SET) != to_offs) + goto out; + + if (lseek(from, from_offs, SEEK_SET) != from_offs) + goto out; + + while (len) { + n = page_size; + if (len < n) + n = len; + /* Use read because mmap won't work on proc files */ + r = read(from, buf, n); + if (r < 0) + goto out; + if (!r) + break; + n = r; + r = write(to, buf, n); + if (r < 0) + goto out; + if ((size_t)r != n) + goto out; + len -= n; + } + + err = 0; +out: + free(buf); + return err; +} + +struct kcore { + int fd; + int elfclass; + Elf *elf; + GElf_Ehdr ehdr; +}; + +static int kcore__open(struct kcore *kcore, const char *filename) +{ + GElf_Ehdr *ehdr; + + kcore->fd = open(filename, O_RDONLY); + if (kcore->fd == -1) + return -1; + + kcore->elf = elf_begin(kcore->fd, ELF_C_READ, NULL); + if (!kcore->elf) + goto out_close; + + kcore->elfclass = gelf_getclass(kcore->elf); + if (kcore->elfclass == ELFCLASSNONE) + goto out_end; + + ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr); + if (!ehdr) + goto out_end; + + return 0; + +out_end: + elf_end(kcore->elf); +out_close: + close(kcore->fd); + return -1; +} + +static int kcore__init(struct kcore *kcore, char *filename, int elfclass, + bool temp) +{ + GElf_Ehdr *ehdr; + + kcore->elfclass = elfclass; + + if (temp) + kcore->fd = mkstemp(filename); + else + kcore->fd = open(filename, O_WRONLY | O_CREAT | O_EXCL, 0400); + if (kcore->fd == -1) + return -1; + + kcore->elf = elf_begin(kcore->fd, ELF_C_WRITE, NULL); + if (!kcore->elf) + goto out_close; + + if (!gelf_newehdr(kcore->elf, elfclass)) + goto out_end; + + ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr); + if (!ehdr) + goto out_end; + + return 0; + +out_end: + elf_end(kcore->elf); +out_close: + close(kcore->fd); + unlink(filename); + return -1; +} + +static void kcore__close(struct kcore *kcore) +{ + elf_end(kcore->elf); + close(kcore->fd); +} + +static int kcore__copy_hdr(struct kcore *from, struct kcore *to, size_t count) +{ + GElf_Ehdr *ehdr = &to->ehdr; + GElf_Ehdr *kehdr = &from->ehdr; + + memcpy(ehdr->e_ident, kehdr->e_ident, EI_NIDENT); + ehdr->e_type = kehdr->e_type; + ehdr->e_machine = kehdr->e_machine; + ehdr->e_version = kehdr->e_version; + ehdr->e_entry = 0; + ehdr->e_shoff = 0; + ehdr->e_flags = kehdr->e_flags; + ehdr->e_phnum = count; + ehdr->e_shentsize = 0; + ehdr->e_shnum = 0; + ehdr->e_shstrndx = 0; + + if (from->elfclass == ELFCLASS32) { + ehdr->e_phoff = sizeof(Elf32_Ehdr); + ehdr->e_ehsize = sizeof(Elf32_Ehdr); + ehdr->e_phentsize = sizeof(Elf32_Phdr); + } else { + ehdr->e_phoff = sizeof(Elf64_Ehdr); + ehdr->e_ehsize = sizeof(Elf64_Ehdr); + ehdr->e_phentsize = sizeof(Elf64_Phdr); + } + + if (!gelf_update_ehdr(to->elf, ehdr)) + return -1; + + if (!gelf_newphdr(to->elf, count)) + return -1; + + return 0; +} + +static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset, + u64 addr, u64 len) +{ + GElf_Phdr gphdr; + GElf_Phdr *phdr; + + phdr = gelf_getphdr(kcore->elf, idx, &gphdr); + if (!phdr) + return -1; + + phdr->p_type = PT_LOAD; + phdr->p_flags = PF_R | PF_W | PF_X; + phdr->p_offset = offset; + phdr->p_vaddr = addr; + phdr->p_paddr = 0; + phdr->p_filesz = len; + phdr->p_memsz = len; + phdr->p_align = page_size; + + if (!gelf_update_phdr(kcore->elf, idx, phdr)) + return -1; + + return 0; +} + +static off_t kcore__write(struct kcore *kcore) +{ + return elf_update(kcore->elf, ELF_C_WRITE); +} + +struct phdr_data { + off_t offset; + u64 addr; + u64 len; +}; + +struct kcore_copy_info { + u64 stext; + u64 etext; + u64 first_symbol; + u64 last_symbol; + u64 first_module; + u64 last_module_symbol; + struct phdr_data kernel_map; + struct phdr_data modules_map; +}; + +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)) + return 0; + + if (strchr(name, '[')) { + if (start > kci->last_module_symbol) + kci->last_module_symbol = start; + return 0; + } + + if (!kci->first_symbol || start < kci->first_symbol) + kci->first_symbol = start; + + if (!kci->last_symbol || start > kci->last_symbol) + kci->last_symbol = start; + + if (!strcmp(name, "_stext")) { + kci->stext = start; + return 0; + } + + if (!strcmp(name, "_etext")) { + kci->etext = start; + return 0; + } + + return 0; +} + +static int kcore_copy__parse_kallsyms(struct kcore_copy_info *kci, + const char *dir) +{ + char kallsyms_filename[PATH_MAX]; + + scnprintf(kallsyms_filename, PATH_MAX, "%s/kallsyms", dir); + + if (symbol__restricted_filename(kallsyms_filename, "/proc/kallsyms")) + return -1; + + if (kallsyms__parse(kallsyms_filename, kci, + kcore_copy__process_kallsyms) < 0) + return -1; + + return 0; +} + +static int kcore_copy__process_modules(void *arg, + const char *name __maybe_unused, + u64 start) +{ + struct kcore_copy_info *kci = arg; + + if (!kci->first_module || start < kci->first_module) + kci->first_module = start; + + return 0; +} + +static int kcore_copy__parse_modules(struct kcore_copy_info *kci, + const char *dir) +{ + char modules_filename[PATH_MAX]; + + scnprintf(modules_filename, PATH_MAX, "%s/modules", dir); + + if (symbol__restricted_filename(modules_filename, "/proc/modules")) + return -1; + + if (modules__parse(modules_filename, kci, + kcore_copy__process_modules) < 0) + return -1; + + return 0; +} + +static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff, + u64 s, u64 e) +{ + if (p->addr || s < start || s >= end) + return; + + p->addr = s; + p->offset = (s - start) + pgoff; + p->len = e < end ? e - s : end - s; +} + +static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data) +{ + struct kcore_copy_info *kci = data; + u64 end = start + len; + + kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext, + kci->etext); + + kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module, + kci->last_module_symbol); + + return 0; +} + +static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf) +{ + if (elf_read_maps(elf, true, kcore_copy__read_map, kci) < 0) + return -1; + + return 0; +} + +static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir, + Elf *elf) +{ + if (kcore_copy__parse_kallsyms(kci, dir)) + return -1; + + if (kcore_copy__parse_modules(kci, dir)) + return -1; + + if (kci->stext) + kci->stext = round_down(kci->stext, page_size); + else + kci->stext = round_down(kci->first_symbol, page_size); + + if (kci->etext) { + kci->etext = round_up(kci->etext, page_size); + } else if (kci->last_symbol) { + kci->etext = round_up(kci->last_symbol, page_size); + kci->etext += page_size; + } + + kci->first_module = round_down(kci->first_module, page_size); + + if (kci->last_module_symbol) { + kci->last_module_symbol = round_up(kci->last_module_symbol, + page_size); + kci->last_module_symbol += page_size; + } + + if (!kci->stext || !kci->etext) + return -1; + + if (kci->first_module && !kci->last_module_symbol) + return -1; + + return kcore_copy__read_maps(kci, elf); +} + +static int kcore_copy__copy_file(const char *from_dir, const char *to_dir, + const char *name) +{ + char from_filename[PATH_MAX]; + char to_filename[PATH_MAX]; + + scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name); + scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name); + + return copyfile_mode(from_filename, to_filename, 0400); +} + +static int kcore_copy__unlink(const char *dir, const char *name) +{ + char filename[PATH_MAX]; + + scnprintf(filename, PATH_MAX, "%s/%s", dir, name); + + return unlink(filename); +} + +static int kcore_copy__compare_fds(int from, int to) +{ + char *buf_from; + char *buf_to; + ssize_t ret; + size_t len; + int err = -1; + + buf_from = malloc(page_size); + buf_to = malloc(page_size); + if (!buf_from || !buf_to) + goto out; + + while (1) { + /* Use read because mmap won't work on proc files */ + ret = read(from, buf_from, page_size); + if (ret < 0) + goto out; + + if (!ret) + break; + + len = ret; + + if (readn(to, buf_to, len) != (int)len) + goto out; + + if (memcmp(buf_from, buf_to, len)) + goto out; + } + + err = 0; +out: + free(buf_to); + free(buf_from); + return err; +} + +static int kcore_copy__compare_files(const char *from_filename, + const char *to_filename) +{ + int from, to, err = -1; + + from = open(from_filename, O_RDONLY); + if (from < 0) + return -1; + + to = open(to_filename, O_RDONLY); + if (to < 0) + goto out_close_from; + + err = kcore_copy__compare_fds(from, to); + + close(to); +out_close_from: + close(from); + return err; +} + +static int kcore_copy__compare_file(const char *from_dir, const char *to_dir, + const char *name) +{ + char from_filename[PATH_MAX]; + char to_filename[PATH_MAX]; + + scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name); + scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name); + + return kcore_copy__compare_files(from_filename, to_filename); +} + +/** + * kcore_copy - copy kallsyms, modules and kcore from one directory to another. + * @from_dir: from directory + * @to_dir: to directory + * + * This function copies kallsyms, modules and kcore files from one directory to + * another. kallsyms and modules are copied entirely. Only code segments are + * copied from kcore. It is assumed that two segments suffice: one for the + * kernel proper and one for all the modules. The code segments are determined + * from kallsyms and modules files. The kernel map starts at _stext or the + * lowest function symbol, and ends at _etext or the highest function symbol. + * The module map starts at the lowest module address and ends at the highest + * module symbol. Start addresses are rounded down to the nearest page. End + * addresses are rounded up to the nearest page. An extra page is added to the + * highest kernel symbol and highest module symbol to, hopefully, encompass that + * symbol too. Because it contains only code sections, the resulting kcore is + * unusual. One significant peculiarity is that the mapping (start -> pgoff) + * is not the same for the kernel map and the modules map. That happens because + * the data is copied adjacently whereas the original kcore has gaps. Finally, + * kallsyms and modules files are compared with their copies to check that + * modules have not been loaded or unloaded while the copies were taking place. + * + * Return: %0 on success, %-1 on failure. + */ +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; + struct kcore_copy_info kci = { .stext = 0, }; + char kcore_filename[PATH_MAX]; + char extract_filename[PATH_MAX]; + + if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms")) + return -1; + + if (kcore_copy__copy_file(from_dir, to_dir, "modules")) + goto out_unlink_kallsyms; + + scnprintf(kcore_filename, PATH_MAX, "%s/kcore", from_dir); + scnprintf(extract_filename, PATH_MAX, "%s/kcore", to_dir); + + if (kcore__open(&kcore, kcore_filename)) + goto out_unlink_modules; + + if (kcore_copy__calc_maps(&kci, from_dir, kcore.elf)) + goto out_kcore_close; + + 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)) + goto out_extract_close; + + if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr, + kci.kernel_map.len)) + goto out_extract_close; + + 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)) + goto out_extract_close; + } + + sz = kcore__write(&extract); + 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; + + if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset, + extract.fd, modules_offset, + kci.modules_map.len)) + goto out_extract_close; + + if (kcore_copy__compare_file(from_dir, to_dir, "modules")) + goto out_extract_close; + + if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms")) + goto out_extract_close; + + err = 0; + +out_extract_close: + kcore__close(&extract); + if (err) + unlink(extract_filename); +out_kcore_close: + kcore__close(&kcore); +out_unlink_modules: + if (err) + kcore_copy__unlink(to_dir, "modules"); +out_unlink_kallsyms: + if (err) + kcore_copy__unlink(to_dir, "kallsyms"); + + return err; +} + +int kcore_extract__create(struct kcore_extract *kce) +{ + struct kcore kcore; + struct kcore extract; + size_t count = 1; + int idx = 0, err = -1; + off_t offset = page_size, sz; + + if (kcore__open(&kcore, kce->kcore_filename)) + return -1; + + strcpy(kce->extract_filename, PERF_KCORE_EXTRACT); + if (kcore__init(&extract, kce->extract_filename, kcore.elfclass, true)) + goto out_kcore_close; + + if (kcore__copy_hdr(&kcore, &extract, count)) + goto out_extract_close; + + if (kcore__add_phdr(&extract, idx, offset, kce->addr, kce->len)) + goto out_extract_close; + + sz = kcore__write(&extract); + if (sz < 0 || sz > offset) + goto out_extract_close; + + if (copy_bytes(kcore.fd, kce->offs, extract.fd, offset, kce->len)) + goto out_extract_close; + + err = 0; + +out_extract_close: + kcore__close(&extract); + if (err) + unlink(kce->extract_filename); +out_kcore_close: + kcore__close(&kcore); + + return err; +} + +void kcore_extract__delete(struct kcore_extract *kce) +{ + unlink(kce->extract_filename); +} + void symbol__elf_init(void) { elf_version(EV_CURRENT); diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index a7390cde63b..2d2dd0532b5 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -301,6 +301,28 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused, return 0; } +int file__read_maps(int fd __maybe_unused, bool exe __maybe_unused, + mapfn_t mapfn __maybe_unused, void *data __maybe_unused, + bool *is_64_bit __maybe_unused) +{ + return -1; +} + +int kcore_extract__create(struct kcore_extract *kce __maybe_unused) +{ + return -1; +} + +void kcore_extract__delete(struct kcore_extract *kce __maybe_unused) +{ +} + +int kcore_copy(const char *from_dir __maybe_unused, + const char *to_dir __maybe_unused) +{ + return -1; +} + void symbol__elf_init(void) { } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index d5528e1cc03..c0c36965fff 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -51,6 +51,7 @@ static enum dso_binary_type binary_type_symtab[] = { DSO_BINARY_TYPE__SYSTEM_PATH_DSO, DSO_BINARY_TYPE__GUEST_KMODULE, DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE, + DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, DSO_BINARY_TYPE__NOT_FOUND, }; @@ -87,6 +88,7 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb) { s64 a; s64 b; + size_t na, nb; /* Prefer a symbol with non zero length */ a = syma->end - syma->start; @@ -120,11 +122,21 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb) else if (a > b) return SYMBOL_B; - /* If all else fails, choose the symbol with the longest name */ - if (strlen(syma->name) >= strlen(symb->name)) + /* Choose the symbol with the longest name */ + na = strlen(syma->name); + nb = strlen(symb->name); + if (na > nb) return SYMBOL_A; - else + else if (na < nb) + return SYMBOL_B; + + /* Avoid "SyS" kernel syscall aliases */ + if (na >= 3 && !strncmp(syma->name, "SyS", 3)) return SYMBOL_B; + if (na >= 10 && !strncmp(syma->name, "compat_SyS", 10)) + return SYMBOL_B; + + return SYMBOL_A; } void symbols__fixup_duplicate(struct rb_root *symbols) @@ -148,10 +160,12 @@ again: if (choose_best_symbol(curr, next) == SYMBOL_A) { rb_erase(&next->rb_node, symbols); + symbol__delete(next); goto again; } else { nd = rb_next(&curr->rb_node); rb_erase(&curr->rb_node, symbols); + symbol__delete(curr); } } } @@ -248,7 +262,10 @@ size_t symbol__fprintf_symname_offs(const struct symbol *sym, if (sym && sym->name) { length = fprintf(fp, "%s", sym->name); if (al) { - offset = al->addr - sym->start; + if (al->addr < sym->end) + offset = al->addr - sym->start; + else + offset = al->addr - al->map->start - sym->start; length += fprintf(fp, "+0x%lx", offset); } return length; @@ -316,6 +333,16 @@ static struct symbol *symbols__find(struct rb_root *symbols, u64 ip) return NULL; } +static struct symbol *symbols__first(struct rb_root *symbols) +{ + struct rb_node *n = rb_first(symbols); + + if (n) + return rb_entry(n, struct symbol, rb_node); + + return NULL; +} + struct symbol_name_rb_node { struct rb_node rb_node; struct symbol sym; @@ -386,6 +413,11 @@ struct symbol *dso__find_symbol(struct dso *dso, return symbols__find(&dso->symbols[type], addr); } +struct symbol *dso__first_symbol(struct dso *dso, enum map_type type) +{ + return symbols__first(&dso->symbols[type]); +} + struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name) { @@ -470,6 +502,64 @@ out_failure: return -1; } +int modules__parse(const char *filename, void *arg, + int (*process_module)(void *arg, const char *name, + u64 start)) +{ + char *line = NULL; + size_t n; + FILE *file; + int err = 0; + + file = fopen(filename, "r"); + if (file == NULL) + return -1; + + while (1) { + char name[PATH_MAX]; + u64 start; + char *sep; + ssize_t line_len; + + line_len = getline(&line, &n, file); + if (line_len < 0) { + if (feof(file)) + break; + err = -1; + goto out; + } + + if (!line) { + err = -1; + goto out; + } + + line[--line_len] = '\0'; /* \n */ + + sep = strrchr(line, 'x'); + if (sep == NULL) + continue; + + hex2u64(sep + 1, &start); + + sep = strchr(line, ' '); + if (sep == NULL) + continue; + + *sep = '\0'; + + scnprintf(name, sizeof(name), "[%s]", line); + + err = process_module(arg, name, start); + if (err) + break; + } +out: + free(line); + fclose(file); + return err; +} + struct process_kallsyms_args { struct map *map; struct dso *dso; @@ -522,6 +612,53 @@ static int dso__load_all_kallsyms(struct dso *dso, const char *filename, return kallsyms__parse(filename, &args, map__process_kallsym_symbol); } +static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map, + symbol_filter_t filter) +{ + struct map_groups *kmaps = map__kmap(map)->kmaps; + struct map *curr_map; + struct symbol *pos; + int count = 0, moved = 0; + struct rb_root *root = &dso->symbols[map->type]; + struct rb_node *next = rb_first(root); + + while (next) { + char *module; + + pos = rb_entry(next, struct symbol, rb_node); + next = rb_next(&pos->rb_node); + + module = strchr(pos->name, '\t'); + if (module) + *module = '\0'; + + curr_map = map_groups__find(kmaps, map->type, pos->start); + + if (!curr_map || (filter && filter(curr_map, pos))) { + rb_erase(&pos->rb_node, root); + symbol__delete(pos); + } else { + pos->start -= curr_map->start - curr_map->pgoff; + if (pos->end) + pos->end -= curr_map->start - curr_map->pgoff; + if (curr_map != map) { + rb_erase(&pos->rb_node, root); + symbols__insert( + &curr_map->dso->symbols[curr_map->type], + pos); + ++moved; + } else { + ++count; + } + } + } + + /* Symbols have been adjusted */ + dso->adjust_symbols = 1; + + return count + moved; +} + /* * Split the symbols into maps, making sure there are no overlaps, i.e. the * kernel range is broken in several maps, named [kernel].N, as we don't have @@ -663,6 +800,356 @@ bool symbol__restricted_filename(const char *filename, return restricted; } +struct module_info { + struct rb_node rb_node; + char *name; + u64 start; +}; + +static void add_module(struct module_info *mi, struct rb_root *modules) +{ + struct rb_node **p = &modules->rb_node; + struct rb_node *parent = NULL; + struct module_info *m; + + while (*p != NULL) { + parent = *p; + m = rb_entry(parent, struct module_info, rb_node); + if (strcmp(mi->name, m->name) < 0) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&mi->rb_node, parent, p); + rb_insert_color(&mi->rb_node, modules); +} + +static void delete_modules(struct rb_root *modules) +{ + struct module_info *mi; + struct rb_node *next = rb_first(modules); + + while (next) { + mi = rb_entry(next, struct module_info, rb_node); + next = rb_next(&mi->rb_node); + rb_erase(&mi->rb_node, modules); + free(mi->name); + free(mi); + } +} + +static struct module_info *find_module(const char *name, + struct rb_root *modules) +{ + struct rb_node *n = modules->rb_node; + + while (n) { + struct module_info *m; + int cmp; + + m = rb_entry(n, struct module_info, rb_node); + cmp = strcmp(name, m->name); + if (cmp < 0) + n = n->rb_left; + else if (cmp > 0) + n = n->rb_right; + else + return m; + } + + return NULL; +} + +static int __read_proc_modules(void *arg, const char *name, u64 start) +{ + struct rb_root *modules = arg; + struct module_info *mi; + + mi = zalloc(sizeof(struct module_info)); + if (!mi) + return -ENOMEM; + + mi->name = strdup(name); + mi->start = start; + + if (!mi->name) { + free(mi); + return -ENOMEM; + } + + add_module(mi, modules); + + return 0; +} + +static int read_proc_modules(const char *filename, struct rb_root *modules) +{ + if (symbol__restricted_filename(filename, "/proc/modules")) + return -1; + + if (modules__parse(filename, modules, __read_proc_modules)) { + delete_modules(modules); + return -1; + } + + return 0; +} + +int compare_proc_modules(const char *from, const char *to) +{ + struct rb_root from_modules = RB_ROOT; + struct rb_root to_modules = RB_ROOT; + struct rb_node *from_node, *to_node; + struct module_info *from_m, *to_m; + int ret = -1; + + if (read_proc_modules(from, &from_modules)) + return -1; + + if (read_proc_modules(to, &to_modules)) + goto out_delete_from; + + from_node = rb_first(&from_modules); + to_node = rb_first(&to_modules); + while (from_node) { + if (!to_node) + break; + + from_m = rb_entry(from_node, struct module_info, rb_node); + to_m = rb_entry(to_node, struct module_info, rb_node); + + if (from_m->start != to_m->start || + strcmp(from_m->name, to_m->name)) + break; + + from_node = rb_next(from_node); + to_node = rb_next(to_node); + } + + if (!from_node && !to_node) + ret = 0; + + delete_modules(&to_modules); +out_delete_from: + delete_modules(&from_modules); + + return ret; +} + +static int do_validate_kcore_modules(const char *filename, struct map *map, + struct map_groups *kmaps) +{ + struct rb_root modules = RB_ROOT; + struct map *old_map; + int err; + + err = read_proc_modules(filename, &modules); + if (err) + return err; + + old_map = map_groups__first(kmaps, map->type); + 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 */ + old_map = next; + continue; + } + + /* Module must be in memory at the same address */ + mi = find_module(old_map->dso->short_name, &modules); + if (!mi || mi->start != old_map->start) { + err = -EINVAL; + goto out; + } + + old_map = next; + } +out: + delete_modules(&modules); + return err; +} + +/* + * If kallsyms is referenced by name then we look for filename in the same + * directory. + */ +static bool filename_from_kallsyms_filename(char *filename, + const char *base_name, + const char *kallsyms_filename) +{ + char *name; + + strcpy(filename, kallsyms_filename); + name = strrchr(filename, '/'); + if (!name) + return false; + + name += 1; + + if (!strcmp(name, "kallsyms")) { + strcpy(name, base_name); + return true; + } + + return false; +} + +static int validate_kcore_modules(const char *kallsyms_filename, + struct map *map) +{ + struct map_groups *kmaps = map__kmap(map)->kmaps; + char modules_filename[PATH_MAX]; + + if (!filename_from_kallsyms_filename(modules_filename, "modules", + kallsyms_filename)) + return -EINVAL; + + if (do_validate_kcore_modules(modules_filename, map, kmaps)) + return -EINVAL; + + return 0; +} + +struct kcore_mapfn_data { + struct dso *dso; + enum map_type type; + struct list_head maps; +}; + +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); + if (map == NULL) + return -ENOMEM; + + map->end = map->start + len; + map->pgoff = pgoff; + + list_add(&map->node, &md->maps); + + return 0; +} + +static int dso__load_kcore(struct dso *dso, struct map *map, + const char *kallsyms_filename) +{ + struct map_groups *kmaps = map__kmap(map)->kmaps; + struct machine *machine = kmaps->machine; + struct kcore_mapfn_data md; + struct map *old_map, *new_map, *replacement_map = NULL; + bool is_64_bit; + int err, fd; + char kcore_filename[PATH_MAX]; + struct symbol *sym; + + /* This function requires that the map is the kernel map */ + if (map != machine->vmlinux_maps[map->type]) + return -EINVAL; + + if (!filename_from_kallsyms_filename(kcore_filename, "kcore", + kallsyms_filename)) + return -EINVAL; + + /* All modules must be present at their original addresses */ + if (validate_kcore_modules(kallsyms_filename, map)) + return -EINVAL; + + md.dso = dso; + md.type = map->type; + INIT_LIST_HEAD(&md.maps); + + fd = open(kcore_filename, O_RDONLY); + if (fd < 0) + return -EINVAL; + + /* Read new maps into temporary lists */ + err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md, + &is_64_bit); + if (err) + goto out_err; + + if (list_empty(&md.maps)) { + err = -EINVAL; + goto out_err; + } + + /* Remove old maps */ + old_map = map_groups__first(kmaps, map->type); + while (old_map) { + struct map *next = map_groups__next(old_map); + + if (old_map != map) + map_groups__remove(kmaps, old_map); + old_map = next; + } + + /* 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; + } + } + + if (!replacement_map) + replacement_map = list_entry(md.maps.next, struct map, node); + + /* Add new maps */ + while (!list_empty(&md.maps)) { + new_map = list_entry(md.maps.next, struct map, node); + list_del(&new_map->node); + if (new_map == replacement_map) { + map->start = new_map->start; + map->end = new_map->end; + map->pgoff = new_map->pgoff; + map->map_ip = new_map->map_ip; + map->unmap_ip = new_map->unmap_ip; + map__delete(new_map); + /* Ensure maps are correctly ordered */ + map_groups__remove(kmaps, map); + map_groups__insert(kmaps, map); + } else { + map_groups__insert(kmaps, new_map); + } + } + + /* + * Set the data type and long name so that kcore can be read via + * dso__data_read_addr(). + */ + if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + dso->data_type = DSO_BINARY_TYPE__GUEST_KCORE; + else + dso->data_type = DSO_BINARY_TYPE__KCORE; + dso__set_long_name(dso, strdup(kcore_filename)); + + close(fd); + + if (map->type == MAP__FUNCTION) + pr_debug("Using %s for kernel object code\n", kcore_filename); + else + pr_debug("Using %s for kernel data\n", kcore_filename); + + return 0; + +out_err: + while (!list_empty(&md.maps)) { + map = list_entry(md.maps.next, struct map, node); + list_del(&map->node); + map__delete(map); + } + close(fd); + return -EINVAL; +} + int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map, symbol_filter_t filter) { @@ -680,7 +1167,10 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, else dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS; - return dso__split_kallsyms(dso, map, filter); + if (!dso__load_kcore(dso, map, filename)) + return dso__split_kallsyms_for_kcore(dso, map, filter); + else + return dso__split_kallsyms(dso, map, filter); } static int dso__load_perf_map(struct dso *dso, struct map *map, @@ -843,10 +1333,15 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (!runtime_ss && syms_ss) runtime_ss = syms_ss; - if (syms_ss) - ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, 0); - else + if (syms_ss) { + int km; + + km = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE || + dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE; + ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, km); + } else { ret = -1; + } if (ret > 0) { int nr_plt; @@ -888,8 +1383,11 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, char symfs_vmlinux[PATH_MAX]; enum dso_binary_type symtab_type; - snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s", - symbol_conf.symfs, vmlinux); + if (vmlinux[0] == '/') + snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux); + else + snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s", + symbol_conf.symfs, vmlinux); if (dso->kernel == DSO_TYPE_GUEST_KERNEL) symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX; @@ -903,6 +1401,10 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, symsrc__destroy(&ss); if (err > 0) { + if (dso->kernel == DSO_TYPE_GUEST_KERNEL) + dso->data_type = DSO_BINARY_TYPE__GUEST_VMLINUX; + else + dso->data_type = DSO_BINARY_TYPE__VMLINUX; dso__set_long_name(dso, (char *)vmlinux); dso__set_loaded(dso, map->type); pr_debug("Using %s for symbols\n", symfs_vmlinux); @@ -942,6 +1444,105 @@ out: return err; } +static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz) +{ + char kallsyms_filename[PATH_MAX]; + struct dirent *dent; + int ret = -1; + DIR *d; + + d = opendir(dir); + if (!d) + return -1; + + while (1) { + dent = readdir(d); + if (!dent) + break; + if (dent->d_type != DT_DIR) + continue; + scnprintf(kallsyms_filename, sizeof(kallsyms_filename), + "%s/%s/kallsyms", dir, dent->d_name); + if (!validate_kcore_modules(kallsyms_filename, map)) { + strlcpy(dir, kallsyms_filename, dir_sz); + ret = 0; + break; + } + } + + closedir(d); + + return ret; +} + +static char *dso__find_kallsyms(struct dso *dso, struct map *map) +{ + u8 host_build_id[BUILD_ID_SIZE]; + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + bool is_host = false; + char path[PATH_MAX]; + + if (!dso->has_build_id) { + /* + * Last resort, if we don't have a build-id and couldn't find + * any vmlinux file, try the running kernel kallsyms table. + */ + goto proc_kallsyms; + } + + if (sysfs__read_build_id("/sys/kernel/notes", host_build_id, + sizeof(host_build_id)) == 0) + is_host = dso__build_id_equal(dso, host_build_id); + + build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); + + /* Use /proc/kallsyms if possible */ + if (is_host) { + DIR *d; + int fd; + + /* If no cached kcore go with /proc/kallsyms */ + scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", + buildid_dir, sbuild_id); + d = opendir(path); + if (!d) + goto proc_kallsyms; + closedir(d); + + /* + * Do not check the build-id cache, until we know we cannot use + * /proc/kcore. + */ + fd = open("/proc/kcore", O_RDONLY); + if (fd != -1) { + close(fd); + /* If module maps match go with /proc/kallsyms */ + if (!validate_kcore_modules("/proc/kallsyms", map)) + goto proc_kallsyms; + } + + /* Find kallsyms in build-id cache with kcore */ + if (!find_matching_kcore(map, path, sizeof(path))) + return strdup(path); + + goto proc_kallsyms; + } + + scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s", + buildid_dir, sbuild_id); + + if (access(path, F_OK)) { + pr_err("No kallsyms or vmlinux with build-id %s was found\n", + sbuild_id); + return NULL; + } + + return strdup(path); + +proc_kallsyms: + return strdup("/proc/kallsyms"); +} + static int dso__load_kernel_sym(struct dso *dso, struct map *map, symbol_filter_t filter) { @@ -968,73 +1569,33 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map, goto do_kallsyms; } - if (symbol_conf.vmlinux_name != NULL) { + if (!symbol_conf.ignore_vmlinux && symbol_conf.vmlinux_name != NULL) { err = dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name, filter); if (err > 0) { dso__set_long_name(dso, strdup(symbol_conf.vmlinux_name)); dso->lname_alloc = 1; - goto out_fixup; + return err; } return err; } - if (vmlinux_path != NULL) { + if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) { err = dso__load_vmlinux_path(dso, map, filter); if (err > 0) - goto out_fixup; + return err; } /* do not try local files if a symfs was given */ if (symbol_conf.symfs[0] != 0) return -1; - /* - * Say the kernel DSO was created when processing the build-id header table, - * we have a build-id, so check if it is the same as the running kernel, - * using it if it is. - */ - if (dso->has_build_id) { - u8 kallsyms_build_id[BUILD_ID_SIZE]; - char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - - if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id, - sizeof(kallsyms_build_id)) == 0) { - if (dso__build_id_equal(dso, kallsyms_build_id)) { - kallsyms_filename = "/proc/kallsyms"; - goto do_kallsyms; - } - } - /* - * Now look if we have it on the build-id cache in - * $HOME/.debug/[kernel.kallsyms]. - */ - build_id__sprintf(dso->build_id, sizeof(dso->build_id), - sbuild_id); - - if (asprintf(&kallsyms_allocated_filename, - "%s/.debug/[kernel.kallsyms]/%s", - getenv("HOME"), sbuild_id) == -1) { - pr_err("Not enough memory for kallsyms file lookup\n"); - return -1; - } + kallsyms_allocated_filename = dso__find_kallsyms(dso, map); + if (!kallsyms_allocated_filename) + return -1; - kallsyms_filename = kallsyms_allocated_filename; - - if (access(kallsyms_filename, F_OK)) { - pr_err("No kallsyms or vmlinux with build-id %s " - "was found\n", sbuild_id); - free(kallsyms_allocated_filename); - return -1; - } - } else { - /* - * Last resort, if we don't have a build-id and couldn't find - * any vmlinux file, try the running kernel kallsyms table. - */ - kallsyms_filename = "/proc/kallsyms"; - } + kallsyms_filename = kallsyms_allocated_filename; do_kallsyms: err = dso__load_kallsyms(dso, kallsyms_filename, map, filter); @@ -1042,9 +1603,8 @@ do_kallsyms: pr_debug("Using %s for symbols\n", kallsyms_filename); free(kallsyms_allocated_filename); - if (err > 0) { + if (err > 0 && !dso__is_kcore(dso)) { dso__set_long_name(dso, strdup("[kernel.kallsyms]")); -out_fixup: map__fixup_start(map); map__fixup_end(map); } @@ -1075,7 +1635,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, if (symbol_conf.default_guest_vmlinux_name != NULL) { err = dso__load_vmlinux(dso, map, symbol_conf.default_guest_vmlinux_name, filter); - goto out_try_fixup; + return err; } kallsyms_filename = symbol_conf.default_guest_kallsyms; @@ -1089,13 +1649,9 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, err = dso__load_kallsyms(dso, kallsyms_filename, map, filter); if (err > 0) pr_debug("Using %s for symbols\n", kallsyms_filename); - -out_try_fixup: - if (err > 0) { - if (kallsyms_filename != NULL) { - machine__mmap_name(machine, path, sizeof(path)); - dso__set_long_name(dso, strdup(path)); - } + if (err > 0 && !dso__is_kcore(dso)) { + machine__mmap_name(machine, path, sizeof(path)); + dso__set_long_name(dso, strdup(path)); map__fixup_start(map); map__fixup_end(map); } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 5f720dc076d..07de8fea2f4 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -13,7 +13,7 @@ #include <libgen.h> #include "build-id.h" -#ifdef LIBELF_SUPPORT +#ifdef HAVE_LIBELF_SUPPORT #include <libelf.h> #include <gelf.h> #endif @@ -21,7 +21,7 @@ #include "dso.h" -#ifdef HAVE_CPLUS_DEMANGLE +#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT extern char *cplus_demangle(const char *, int); static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i) @@ -46,7 +46,7 @@ static inline char *bfd_demangle(void __maybe_unused *v, * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP; * for newer versions we can use mmap to reduce memory usage: */ -#ifdef LIBELF_MMAP +#ifdef HAVE_LIBELF_MMAP_SUPPORT # define PERF_ELF_C_READ_MMAP ELF_C_READ_MMAP #else # define PERF_ELF_C_READ_MMAP ELF_C_READ @@ -85,6 +85,7 @@ struct symbol_conf { unsigned short priv_size; unsigned short nr_events; bool try_vmlinux_path, + ignore_vmlinux, show_kernel_path, use_modules, sort_by_name, @@ -178,7 +179,7 @@ struct symsrc { int fd; enum dso_binary_type type; -#ifdef LIBELF_SUPPORT +#ifdef HAVE_LIBELF_SUPPORT Elf *elf; GElf_Ehdr ehdr; @@ -215,12 +216,16 @@ 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__first_symbol(struct dso *dso, enum map_type type); int filename__read_build_id(const char *filename, void *bf, size_t size); int sysfs__read_build_id(const char *filename, void *bf, size_t size); int kallsyms__parse(const char *filename, void *arg, int (*process_symbol)(void *arg, const char *name, char type, u64 start)); +int modules__parse(const char *filename, void *arg, + int (*process_module)(void *arg, const char *name, + u64 start)); int filename__read_debuglink(const char *filename, char *debuglink, size_t size); @@ -247,4 +252,25 @@ 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); +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, + bool *is_64_bit); + +#define PERF_KCORE_EXTRACT "/tmp/perf-kcore-XXXXXX" + +struct kcore_extract { + char *kcore_filename; + u64 addr; + u64 offs; + u64 len; + char extract_filename[sizeof(PERF_KCORE_EXTRACT)]; + int fd; +}; + +int kcore_extract__create(struct kcore_extract *kce); +void kcore_extract__delete(struct kcore_extract *kce); + +int kcore_copy(const char *from_dir, const char *to_dir); +int compare_proc_modules(const char *from, const char *to); + #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/sysfs.c b/tools/perf/util/sysfs.c deleted file mode 100644 index f71e9eafe15..00000000000 --- a/tools/perf/util/sysfs.c +++ /dev/null @@ -1,60 +0,0 @@ - -#include "util.h" -#include "sysfs.h" - -static const char * const sysfs_known_mountpoints[] = { - "/sys", - 0, -}; - -static int sysfs_found; -char sysfs_mountpoint[PATH_MAX + 1]; - -static int sysfs_valid_mountpoint(const char *sysfs) -{ - struct statfs st_fs; - - if (statfs(sysfs, &st_fs) < 0) - return -ENOENT; - else if (st_fs.f_type != (long) SYSFS_MAGIC) - return -ENOENT; - - return 0; -} - -const char *sysfs_find_mountpoint(void) -{ - const char * const *ptr; - char type[100]; - FILE *fp; - - if (sysfs_found) - return (const char *) sysfs_mountpoint; - - ptr = sysfs_known_mountpoints; - while (*ptr) { - if (sysfs_valid_mountpoint(*ptr) == 0) { - sysfs_found = 1; - strcpy(sysfs_mountpoint, *ptr); - return sysfs_mountpoint; - } - ptr++; - } - - /* give up and parse /proc/mounts */ - fp = fopen("/proc/mounts", "r"); - if (fp == NULL) - return NULL; - - while (!sysfs_found && - fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n", - sysfs_mountpoint, type) == 2) { - - if (strcmp(type, "sysfs") == 0) - sysfs_found = 1; - } - - fclose(fp); - - return sysfs_found ? sysfs_mountpoint : NULL; -} diff --git a/tools/perf/util/sysfs.h b/tools/perf/util/sysfs.h deleted file mode 100644 index a813b720393..00000000000 --- a/tools/perf/util/sysfs.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __SYSFS_H__ -#define __SYSFS_H__ - -const char *sysfs_find_mountpoint(void); - -#endif /* __DEBUGFS_H__ */ diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 40399cbcca7..cd8e2f59271 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -6,85 +6,137 @@ #include "thread.h" #include "util.h" #include "debug.h" +#include "comm.h" -struct thread *thread__new(pid_t pid) +struct thread *thread__new(pid_t pid, pid_t tid) { - struct thread *self = zalloc(sizeof(*self)); - - if (self != NULL) { - map_groups__init(&self->mg); - self->pid = pid; - self->ppid = -1; - self->comm = malloc(32); - if (self->comm) - snprintf(self->comm, 32, ":%d", self->pid); + char *comm_str; + struct comm *comm; + struct thread *thread = zalloc(sizeof(*thread)); + + if (thread != NULL) { + map_groups__init(&thread->mg); + thread->pid_ = pid; + thread->tid = tid; + thread->ppid = -1; + INIT_LIST_HEAD(&thread->comm_list); + + comm_str = malloc(32); + if (!comm_str) + goto err_thread; + + snprintf(comm_str, 32, ":%d", tid); + comm = comm__new(comm_str, 0); + free(comm_str); + if (!comm) + goto err_thread; + + list_add(&comm->list, &thread->comm_list); + } + + return thread; + +err_thread: + free(thread); + return NULL; +} + +void thread__delete(struct thread *thread) +{ + struct comm *comm, *tmp; + + map_groups__exit(&thread->mg); + list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) { + list_del(&comm->list); + comm__free(comm); } - return self; + free(thread); } -void thread__delete(struct thread *self) +struct comm *thread__comm(const struct thread *thread) { - map_groups__exit(&self->mg); - free(self->comm); - free(self); + if (list_empty(&thread->comm_list)) + return NULL; + + return list_first_entry(&thread->comm_list, struct comm, list); } -int thread__set_comm(struct thread *self, const char *comm) +/* CHECKME: time should always be 0 if event aren't ordered */ +int thread__set_comm(struct thread *thread, const char *str, u64 timestamp) { - int err; - - if (self->comm) - free(self->comm); - self->comm = strdup(comm); - err = self->comm == NULL ? -ENOMEM : 0; - if (!err) { - self->comm_set = true; + struct comm *new, *curr = thread__comm(thread); + + /* Override latest entry if it had no specific time coverage */ + if (!curr->start) { + comm__override(curr, str, timestamp); + return 0; } - return err; + + new = comm__new(str, timestamp); + if (!new) + return -ENOMEM; + + list_add(&new->list, &thread->comm_list); + thread->comm_set = true; + + return 0; +} + +const char *thread__comm_str(const struct thread *thread) +{ + const struct comm *comm = thread__comm(thread); + + if (!comm) + return NULL; + + return comm__str(comm); } -int thread__comm_len(struct thread *self) +/* CHECKME: it should probably better return the max comm len from its comm list */ +int thread__comm_len(struct thread *thread) { - if (!self->comm_len) { - if (!self->comm) + if (!thread->comm_len) { + const char *comm = thread__comm_str(thread); + if (!comm) return 0; - self->comm_len = strlen(self->comm); + thread->comm_len = strlen(comm); } - return self->comm_len; + return thread->comm_len; } size_t thread__fprintf(struct thread *thread, FILE *fp) { - return fprintf(fp, "Thread %d %s\n", thread->pid, thread->comm) + + return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) + map_groups__fprintf(&thread->mg, verbose, fp); } -void thread__insert_map(struct thread *self, struct map *map) +void thread__insert_map(struct thread *thread, struct map *map) { - map_groups__fixup_overlappings(&self->mg, map, verbose, stderr); - map_groups__insert(&self->mg, map); + map_groups__fixup_overlappings(&thread->mg, map, verbose, stderr); + map_groups__insert(&thread->mg, map); } -int thread__fork(struct thread *self, struct thread *parent) +int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) { - int i; + int i, err; if (parent->comm_set) { - if (self->comm) - free(self->comm); - self->comm = strdup(parent->comm); - if (!self->comm) + const char *comm = thread__comm_str(parent); + if (!comm) return -ENOMEM; - self->comm_set = true; + err = thread__set_comm(thread, comm, timestamp); + if (!err) + return err; + thread->comm_set = true; } for (i = 0; i < MAP__NR_TYPES; ++i) - if (map_groups__clone(&self->mg, &parent->mg, i) < 0) + if (map_groups__clone(&thread->mg, &parent->mg, i) < 0) return -ENOMEM; - self->ppid = parent->pid; + thread->ppid = parent->tid; return 0; } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index eeb7ac62b9e..897c1b2a750 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -2,6 +2,7 @@ #define __PERF_THREAD_H #include <linux/rbtree.h> +#include <linux/list.h> #include <unistd.h> #include <sys/types.h> #include "symbol.h" @@ -12,31 +13,40 @@ struct thread { struct list_head node; }; struct map_groups mg; - pid_t pid; + pid_t pid_; /* Not all tools update this */ + pid_t tid; pid_t ppid; char shortname[3]; bool comm_set; - char *comm; + bool dead; /* if set thread has exited */ + struct list_head comm_list; int comm_len; void *priv; }; struct machine; +struct comm; -struct thread *thread__new(pid_t pid); -void thread__delete(struct thread *self); +struct thread *thread__new(pid_t pid, pid_t tid); +void thread__delete(struct thread *thread); +static inline void thread__exited(struct thread *thread) +{ + thread->dead = true; +} -int thread__set_comm(struct thread *self, const char *comm); -int thread__comm_len(struct thread *self); -void thread__insert_map(struct thread *self, struct map *map); -int thread__fork(struct thread *self, struct thread *parent); +int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp); +int thread__comm_len(struct thread *thread); +struct comm *thread__comm(const struct thread *thread); +const char *thread__comm_str(const struct thread *thread); +void thread__insert_map(struct thread *thread, struct map *map); +int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp); size_t thread__fprintf(struct thread *thread, FILE *fp); -static inline struct map *thread__find_map(struct thread *self, +static inline struct map *thread__find_map(struct thread *thread, enum map_type type, u64 addr) { - return self ? map_groups__find(&self->mg, type, addr) : NULL; + return thread ? map_groups__find(&thread->mg, type, addr) : NULL; } void thread__find_addr_map(struct thread *thread, struct machine *machine, @@ -45,6 +55,15 @@ void thread__find_addr_map(struct thread *thread, struct machine *machine, void thread__find_addr_location(struct thread *thread, struct machine *machine, u8 cpumode, enum map_type type, u64 addr, - struct addr_location *al, - symbol_filter_t filter); + struct addr_location *al); + +static inline void *thread__priv(struct thread *thread) +{ + return thread->priv; +} + +static inline void thread__set_priv(struct thread *thread, void *p) +{ + thread->priv = p; +} #endif /* __PERF_THREAD_H */ diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index b0e1aadba8d..4385816d3d4 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -18,12 +18,9 @@ typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event, typedef int (*event_op)(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); -typedef int (*event_attr_op)(union perf_event *event, +typedef int (*event_attr_op)(struct perf_tool *tool, + union perf_event *event, struct perf_evlist **pevlist); -typedef int (*event_simple_op)(struct perf_tool *tool, union perf_event *event); - -typedef int (*event_synth_op)(union perf_event *event, - struct perf_session *session); typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event, struct perf_session *session); @@ -32,6 +29,7 @@ struct perf_tool { event_sample sample, read; event_op mmap, + mmap2, comm, fork, exit, @@ -39,8 +37,7 @@ struct perf_tool { throttle, unthrottle; event_attr_op attr; - event_synth_op tracing_data; - event_simple_op event_type; + event_op2 tracing_data; event_op2 finished_round, build_id; bool ordered_samples; diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index df46be93d90..88cfeaff600 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -24,6 +24,7 @@ struct perf_top { u64 exact_samples; u64 guest_us_samples, guest_kernel_samples; int print_entries, count_filter, delay_secs; + int max_stack; bool hide_kernel_symbols, hide_user_symbols, zero; bool use_tui, use_stdio; bool kptr_restrict_warned; @@ -39,6 +40,8 @@ struct perf_top { float min_percent; }; +#define CONSOLE_CLEAR "[H[2J" + size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size); void perf_top__reset_sample_counters(struct perf_top *top); #endif /* __PERF_TOP_H */ diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index 3917eb9a847..f3c9e551bd3 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -46,65 +46,6 @@ static int output_fd; -static const char *find_debugfs(void) -{ - const char *path = perf_debugfs_mount(NULL); - - if (!path) - pr_debug("Your kernel does not support the debugfs filesystem"); - - return path; -} - -/* - * Finds the path to the debugfs/tracing - * Allocates the string and stores it. - */ -static const char *find_tracing_dir(void) -{ - static char *tracing; - static int tracing_found; - const char *debugfs; - - if (tracing_found) - return tracing; - - debugfs = find_debugfs(); - if (!debugfs) - return NULL; - - tracing = malloc(strlen(debugfs) + 9); - if (!tracing) - return NULL; - - sprintf(tracing, "%s/tracing", debugfs); - - tracing_found = 1; - return tracing; -} - -static char *get_tracing_file(const char *name) -{ - const char *tracing; - char *file; - - tracing = find_tracing_dir(); - if (!tracing) - return NULL; - - file = malloc(strlen(tracing) + strlen(name) + 2); - if (!file) - return NULL; - - sprintf(file, "%s/%s", tracing, name); - return file; -} - -static void put_tracing_file(char *file) -{ - free(file); -} - int bigendian(void) { unsigned char str[] = { 0x1, 0x2, 0x3, 0x4, 0x0, 0x0, 0x0, 0x0}; @@ -160,7 +101,7 @@ out: return err; } -static int read_header_files(void) +static int record_header_files(void) { char *path; struct stat st; @@ -299,7 +240,7 @@ out: return err; } -static int read_ftrace_files(struct tracepoint_path *tps) +static int record_ftrace_files(struct tracepoint_path *tps) { char *path; int ret; @@ -328,7 +269,7 @@ static bool system_in_tp_list(char *sys, struct tracepoint_path *tps) return false; } -static int read_event_files(struct tracepoint_path *tps) +static int record_event_files(struct tracepoint_path *tps) { struct dirent *dent; struct stat st; @@ -403,7 +344,7 @@ out: return err; } -static int read_proc_kallsyms(void) +static int record_proc_kallsyms(void) { unsigned int size; const char *path = "/proc/kallsyms"; @@ -421,7 +362,7 @@ static int read_proc_kallsyms(void) return record_file(path, 4); } -static int read_ftrace_printk(void) +static int record_ftrace_printk(void) { unsigned int size; char *path; @@ -473,12 +414,27 @@ get_tracepoints_path(struct list_head *pattrs) if (pos->attr.type != PERF_TYPE_TRACEPOINT) continue; ++nr_tracepoints; + + if (pos->name) { + ppath->next = tracepoint_name_to_path(pos->name); + if (ppath->next) + goto next; + + if (strchr(pos->name, ':') == NULL) + goto try_id; + + goto error; + } + +try_id: ppath->next = tracepoint_id_to_path(pos->attr.config); if (!ppath->next) { +error: pr_debug("No memory to alloc tracepoints list\n"); put_tracepoints_path(&path); return NULL; } +next: ppath = ppath->next; } @@ -520,8 +476,6 @@ static int tracing_data_header(void) else buf[0] = 0; - read_trace_init(buf[0], buf[0]); - if (write(output_fd, buf, 1) != 1) return -1; @@ -583,19 +537,19 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs, err = tracing_data_header(); if (err) goto out; - err = read_header_files(); + err = record_header_files(); if (err) goto out; - err = read_ftrace_files(tps); + err = record_ftrace_files(tps); if (err) goto out; - err = read_event_files(tps); + err = record_event_files(tps); if (err) goto out; - err = read_proc_kallsyms(); + err = record_proc_kallsyms(); if (err) goto out; - err = read_ftrace_printk(); + err = record_ftrace_printk(); out: /* diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 4454835a9eb..6681f71f2f9 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -28,12 +28,6 @@ #include "util.h" #include "trace-event.h" -int header_page_size_size; -int header_page_ts_size; -int header_page_data_offset; - -bool latency_format; - struct pevent *read_trace_init(int file_bigendian, int host_bigendian) { struct pevent *pevent = pevent_alloc(); @@ -126,42 +120,6 @@ raw_field_value(struct event_format *event, const char *name, void *data) return val; } -void *raw_field_ptr(struct event_format *event, const char *name, void *data) -{ - struct format_field *field; - - field = pevent_find_any_field(event, name); - if (!field) - return NULL; - - if (field->flags & FIELD_IS_DYNAMIC) { - int offset; - - offset = *(int *)(data + field->offset); - offset &= 0xffff; - - return data + offset; - } - - return data + field->offset; -} - -int trace_parse_common_type(struct pevent *pevent, void *data) -{ - struct pevent_record record; - - record.data = data; - return pevent_data_type(pevent, &record); -} - -int trace_parse_common_pid(struct pevent *pevent, void *data) -{ - struct pevent_record record; - - record.data = data; - return pevent_data_pid(pevent, &record); -} - unsigned long long read_size(struct event_format *event, void *ptr, int size) { return pevent_read_number(event->pevent, ptr, size); @@ -192,7 +150,7 @@ void parse_proc_kallsyms(struct pevent *pevent, char *next = NULL; char *addr_str; char *mod; - char *fmt; + char *fmt = NULL; line = strtok_r(file, "\n", &next); while (line) { diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index af215c0d237..f2112270c66 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -39,10 +39,6 @@ static int input_fd; -int file_bigendian; -int host_bigendian; -static int long_size; - static ssize_t trace_data_size; static bool repipe; @@ -216,7 +212,7 @@ static int read_ftrace_printk(struct pevent *pevent) static int read_header_files(struct pevent *pevent) { unsigned long long size; - char *header_event; + char *header_page; char buf[BUFSIZ]; int ret = 0; @@ -229,13 +225,26 @@ static int read_header_files(struct pevent *pevent) } size = read8(pevent); - skip(size); - /* - * The size field in the page is of type long, - * use that instead, since it represents the kernel. - */ - long_size = header_page_size_size; + header_page = malloc(size); + if (header_page == NULL) + return -1; + + if (do_read(header_page, size) < 0) { + pr_debug("did not read header page"); + free(header_page); + return -1; + } + + if (!pevent_parse_header_page(pevent, header_page, size, + pevent_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); + } + free(header_page); if (do_read(buf, 13) < 0) return -1; @@ -246,14 +255,8 @@ static int read_header_files(struct pevent *pevent) } size = read8(pevent); - header_event = malloc(size); - if (header_event == NULL) - return -1; - - if (do_read(header_event, size) < 0) - ret = -1; + skip(size); - free(header_event); return ret; } @@ -349,6 +352,10 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe) int show_funcs = 0; int show_printk = 0; ssize_t size = -1; + int file_bigendian; + int host_bigendian; + int file_long_size; + int file_page_size; struct pevent *pevent; int err; @@ -391,12 +398,15 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe) if (do_read(buf, 1) < 0) goto out; - long_size = buf[0]; + file_long_size = buf[0]; - page_size = read4(pevent); - if (!page_size) + file_page_size = read4(pevent); + if (!file_page_size) goto out; + pevent_set_long_size(pevent, file_long_size); + pevent_set_page_size(pevent, file_page_size); + err = read_header_files(pevent); if (err) goto out; diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 8715a1006d0..95199e4eea9 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -39,7 +39,8 @@ static void process_event_unsupported(union perf_event *event __maybe_unused, struct perf_sample *sample __maybe_unused, struct perf_evsel *evsel __maybe_unused, struct machine *machine __maybe_unused, - struct addr_location *al __maybe_unused) + struct thread *thread __maybe_unused, + struct addr_location *al __maybe_unused) { } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 1978c398ad8..04df6311410 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -1,31 +1,15 @@ #ifndef _PERF_UTIL_TRACE_EVENT_H #define _PERF_UTIL_TRACE_EVENT_H +#include <traceevent/event-parse.h> #include "parse-events.h" -#include "event-parse.h" #include "session.h" struct machine; struct perf_sample; union perf_event; struct perf_tool; - -extern int header_page_size_size; -extern int header_page_ts_size; -extern int header_page_data_offset; - -extern bool latency_format; -extern struct pevent *perf_pevent; - -enum { - RINGBUF_TYPE_PADDING = 29, - RINGBUF_TYPE_TIME_EXTEND = 30, - RINGBUF_TYPE_TIME_STAMP = 31, -}; - -#ifndef TS_SHIFT -#define TS_SHIFT 27 -#endif +struct thread; int bigendian(void); @@ -37,26 +21,19 @@ int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size); int parse_event_file(struct pevent *pevent, char *buf, unsigned long size, char *sys); -struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu); - unsigned long long raw_field_value(struct event_format *event, const char *name, void *data); -void *raw_field_ptr(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); ssize_t trace_report(int fd, struct pevent **pevent, bool repipe); -int trace_parse_common_type(struct pevent *pevent, void *data); -int trace_parse_common_pid(struct pevent *pevent, void *data); - struct event_format *trace_find_next_event(struct pevent *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); -struct pevent_record *trace_read_data(struct pevent *pevent, int cpu); int read_tracing_data(int fd, struct list_head *pattrs); struct tracing_data { @@ -83,7 +60,8 @@ struct scripting_ops { struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, - struct addr_location *al); + struct thread *thread, + struct addr_location *al); int (*generate_script) (struct pevent *pevent, const char *outfile); }; diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c index 958723ba3d2..2f891f7e70b 100644 --- a/tools/perf/util/unwind.c +++ b/tools/perf/util/unwind.c @@ -473,7 +473,7 @@ static int entry(u64 ip, struct thread *thread, struct machine *machine, thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER, - MAP__FUNCTION, ip, &al, NULL); + MAP__FUNCTION, ip, &al); e.ip = ip; e.map = al.map; diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index cb6bc503a79..ec0c71a2ca2 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -13,7 +13,7 @@ struct unwind_entry { typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); -#ifdef LIBUNWIND_SUPPORT +#ifdef HAVE_LIBUNWIND_SUPPORT int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct machine *machine, struct thread *thread, @@ -31,5 +31,5 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, { return 0; } -#endif /* LIBUNWIND_SUPPORT */ +#endif /* HAVE_LIBUNWIND_SUPPORT */ #endif /* __UNWIND_H */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 59d868add27..28a0a89c1f7 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -1,7 +1,7 @@ #include "../perf.h" #include "util.h" #include <sys/mman.h> -#ifdef BACKTRACE_SUPPORT +#ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> #endif #include <stdio.h> @@ -55,17 +55,20 @@ int mkdir_p(char *path, mode_t mode) return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0; } -static int slow_copyfile(const char *from, const char *to) +static int slow_copyfile(const char *from, const char *to, mode_t mode) { - int err = 0; + int err = -1; char *line = NULL; size_t n; FILE *from_fp = fopen(from, "r"), *to_fp; + mode_t old_umask; if (from_fp == NULL) goto out; + old_umask = umask(mode ^ 0777); to_fp = fopen(to, "w"); + umask(old_umask); if (to_fp == NULL) goto out_fclose_from; @@ -82,7 +85,7 @@ out: return err; } -int copyfile(const char *from, const char *to) +int copyfile_mode(const char *from, const char *to, mode_t mode) { int fromfd, tofd; struct stat st; @@ -93,13 +96,13 @@ int copyfile(const char *from, const char *to) goto out; if (st.st_size == 0) /* /proc? do it slowly... */ - return slow_copyfile(from, to); + return slow_copyfile(from, to, mode); fromfd = open(from, O_RDONLY); if (fromfd < 0) goto out; - tofd = creat(to, 0755); + tofd = creat(to, mode); if (tofd < 0) goto out_close_from; @@ -121,6 +124,11 @@ out: return err; } +int copyfile(const char *from, const char *to) +{ + return copyfile_mode(from, to, 0755); +} + unsigned long convert_unit(unsigned long value, char *unit) { *unit = ' '; @@ -204,7 +212,7 @@ int hex2u64(const char *ptr, u64 *long_val) } /* Obtain a backtrace and print it to stdout. */ -#ifdef BACKTRACE_SUPPORT +#ifdef HAVE_BACKTRACE_SUPPORT void dump_stack(void) { void *array[16]; @@ -269,3 +277,139 @@ void perf_debugfs_set_path(const char *mntpt) snprintf(debugfs_mountpoint, strlen(debugfs_mountpoint), "%s", mntpt); set_tracing_events_path(mntpt); } + +static const char *find_debugfs(void) +{ + const char *path = perf_debugfs_mount(NULL); + + if (!path) + fprintf(stderr, "Your kernel does not support the debugfs filesystem"); + + return path; +} + +/* + * Finds the path to the debugfs/tracing + * Allocates the string and stores it. + */ +const char *find_tracing_dir(void) +{ + static char *tracing; + static int tracing_found; + const char *debugfs; + + if (tracing_found) + return tracing; + + debugfs = find_debugfs(); + if (!debugfs) + return NULL; + + tracing = malloc(strlen(debugfs) + 9); + if (!tracing) + return NULL; + + sprintf(tracing, "%s/tracing", debugfs); + + tracing_found = 1; + return tracing; +} + +char *get_tracing_file(const char *name) +{ + const char *tracing; + char *file; + + tracing = find_tracing_dir(); + if (!tracing) + return NULL; + + file = malloc(strlen(tracing) + strlen(name) + 2); + if (!file) + return NULL; + + sprintf(file, "%s/%s", tracing, name); + return file; +} + +void put_tracing_file(char *file) +{ + free(file); +} + +int parse_nsec_time(const char *str, u64 *ptime) +{ + u64 time_sec, time_nsec; + char *end; + + time_sec = strtoul(str, &end, 10); + if (*end != '.' && *end != '\0') + return -1; + + if (*end == '.') { + int i; + char nsec_buf[10]; + + if (strlen(++end) > 9) + return -1; + + strncpy(nsec_buf, end, 9); + nsec_buf[9] = '\0'; + + /* make it nsec precision */ + for (i = strlen(nsec_buf); i < 9; i++) + nsec_buf[i] = '0'; + + time_nsec = strtoul(nsec_buf, &end, 10); + if (*end != '\0') + return -1; + } else + time_nsec = 0; + + *ptime = time_sec * NSEC_PER_SEC + time_nsec; + return 0; +} + +unsigned long parse_tag_value(const char *str, struct parse_tag *tags) +{ + struct parse_tag *i = tags; + + while (i->tag) { + char *s; + + s = strchr(str, i->tag); + if (s) { + unsigned long int value; + char *endptr; + + value = strtoul(str, &endptr, 10); + if (s != endptr) + break; + + if (value > ULONG_MAX / i->mult) + break; + value *= i->mult; + return value; + } + i++; + } + + return (unsigned long) -1; +} + +int filename__read_int(const char *filename, int *value) +{ + char line[64]; + int fd = open(filename, O_RDONLY), err = -1; + + if (fd < 0) + return -1; + + if (read(fd, line, sizeof(line)) > 0) { + *value = atoi(line); + err = 0; + } + + close(fd); + return err; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 2732fad0390..c8f362daba8 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -80,6 +80,9 @@ extern char buildid_dir[]; extern char tracing_events_path[]; extern void perf_debugfs_set_path(const char *mountpoint); const char *perf_debugfs_mount(const char *mountpoint); +const char *find_tracing_dir(void); +char *get_tracing_file(const char *name); +void put_tracing_file(char *file); /* On most systems <limits.h> would have given us this, but * not on some systems (e.g. GNU/Hurd). @@ -125,6 +128,8 @@ const char *perf_debugfs_mount(const char *mountpoint); #endif #endif +#define PERF_GTK_DSO "libperf-gtk.so" + /* General helper functions */ extern void usage(const char *err) NORETURN; extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2))); @@ -205,6 +210,8 @@ static inline int has_extension(const char *filename, const char *ext) #define NSEC_PER_MSEC 1000000L #endif +int parse_nsec_time(const char *str, u64 *ptime); + extern unsigned char sane_ctype[256]; #define GIT_SPACE 0x01 #define GIT_DIGIT 0x02 @@ -236,6 +243,7 @@ static inline int sane_case(int x, int high) int mkdir_p(char *path, mode_t mode); int copyfile(const char *from, const char *to); +int copyfile_mode(const char *from, const char *to, mode_t mode); s64 perf_atoll(const char *str); char **argv_split(const char *str, int *argcp); @@ -265,6 +273,13 @@ bool is_power_of_2(unsigned long n) return (n != 0 && ((n & (n - 1)) == 0)); } +static inline unsigned next_pow2(unsigned x) +{ + if (!x) + return 1; + return 1ULL << (32 - __builtin_clz(x - 1)); +} + size_t hex_width(u64 v); int hex2u64(const char *ptr, u64 *val); @@ -276,4 +291,20 @@ void dump_stack(void); extern unsigned int page_size; void get_term_dimensions(struct winsize *ws); + +struct parse_tag { + char tag; + int mult; +}; + +unsigned long parse_tag_value(const char *str, struct parse_tag *tags); + +#define SRCLINE_UNKNOWN ((char *) "??:0") + +struct dso; + +char *get_srcline(struct dso *dso, unsigned long addr); +void free_srcline(char *srcline); + +int filename__read_int(const char *filename, int *value); #endif /* GIT_COMPAT_UTIL_H */ |