diff options
Diffstat (limited to 'tools/perf')
352 files changed, 14171 insertions, 2925 deletions
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index 3db3db9278be..643cc4ba6872 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -31,3 +31,5 @@ config.mak.autogen .config-detected util/intel-pt-decoder/inat-tables.c arch/*/include/generated/ +pmu-events/pmu-events.c +pmu-events/jevents diff --git a/tools/perf/Build b/tools/perf/Build index b12d5d1666e3..bd8eeb60533c 100644 --- a/tools/perf/Build +++ b/tools/perf/Build @@ -3,10 +3,12 @@ perf-y += builtin-annotate.o perf-y += builtin-config.o perf-y += builtin-diff.o perf-y += builtin-evlist.o +perf-y += builtin-ftrace.o perf-y += builtin-help.o perf-y += builtin-sched.o perf-y += builtin-buildid-list.o perf-y += builtin-buildid-cache.o +perf-y += builtin-kallsyms.o perf-y += builtin-list.o perf-y += builtin-record.o perf-y += builtin-report.o @@ -39,8 +41,7 @@ CFLAGS_builtin-help.o += $(paths) CFLAGS_builtin-timechart.o += $(paths) CFLAGS_perf.o += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" \ -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" \ - -DPREFIX="BUILD_STR($(prefix_SQ))" \ - -include $(OUTPUT)PERF-VERSION-FILE + -DPREFIX="BUILD_STR($(prefix_SQ))" CFLAGS_builtin-trace.o += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))" CFLAGS_builtin-report.o += -DTIPDIR="BUILD_STR($(tipdir_SQ))" CFLAGS_builtin-report.o += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)" @@ -49,5 +50,6 @@ libperf-y += util/ libperf-y += arch/ libperf-y += ui/ libperf-y += scripts/ +libperf-y += trace/beauty/ gtk-y += ui/gtk/ diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt index b0b3007d3c9c..4b6cdbf8f935 100644 --- a/tools/perf/Documentation/intel-pt.txt +++ b/tools/perf/Documentation/intel-pt.txt @@ -108,6 +108,9 @@ approach is available to export the data to a postgresql database. Refer to script export-to-postgresql.py for more details, and to script call-graph-from-postgresql.py for an example of using the database. +There is also script intel-pt-events.py which provides an example of how to +unpack the raw data for power events and PTWRITE. + As mentioned above, it is easy to capture too much data. One way to limit the data captured is to use 'snapshot' mode which is explained further below. Refer to 'new snapshot option' and 'Intel PT modes of operation' further below. @@ -364,6 +367,42 @@ cyc_thresh Specifies how frequently CYC packets are produced - see cyc CYC packets are not requested by default. +pt Specifies pass-through which enables the 'branch' config term. + + The default config selects 'pt' if it is available, so a user will + never need to specify this term. + +branch Enable branch tracing. Branch tracing is enabled by default so to + disable branch tracing use 'branch=0'. + + The default config selects 'branch' if it is available. + +ptw Enable PTWRITE packets which are produced when a ptwrite instruction + is executed. + + Support for this feature is indicated by: + + /sys/bus/event_source/devices/intel_pt/caps/ptwrite + + which contains "1" if the feature is supported and + "0" otherwise. + +fup_on_ptw Enable a FUP packet to follow the PTWRITE packet. The FUP packet + provides the address of the ptwrite instruction. In the absence of + fup_on_ptw, the decoder will use the address of the previous branch + if branch tracing is enabled, otherwise the address will be zero. + Note that fup_on_ptw will work even when branch tracing is disabled. + +pwr_evt Enable power events. The power events provide information about + changes to the CPU C-state. + + Support for this feature is indicated by: + + /sys/bus/event_source/devices/intel_pt/caps/power_event_trace + + which contains "1" if the feature is supported and + "0" otherwise. + new snapshot option ------------------- @@ -674,13 +713,15 @@ Having no option is the same as which, in turn, is the same as - --itrace=ibxe + --itrace=ibxwpe The letters are: i synthesize "instructions" events b synthesize "branches" events x synthesize "transactions" events + w synthesize "ptwrite" events + p synthesize "power" events c synthesize branches events (calls only) r synthesize branches events (returns only) e synthesize tracing error events @@ -699,7 +740,40 @@ and "r" can be combined to get calls and returns. 'flags' field can be used in perf script to determine whether the event is a tranasaction start, commit or abort. -Error events are new. They show where the decoder lost the trace. Error events +Note that "instructions", "branches" and "transactions" events depend on code +flow packets which can be disabled by using the config term "branch=0". Refer +to the config terms section above. + +"ptwrite" events record the payload of the ptwrite instruction and whether +"fup_on_ptw" was used. "ptwrite" events depend on PTWRITE packets which are +recorded only if the "ptw" config term was used. Refer to the config terms +section above. perf script "synth" field displays "ptwrite" information like +this: "ip: 0 payload: 0x123456789abcdef0" where "ip" is 1 if "fup_on_ptw" was +used. + +"Power" events correspond to power event packets and CBR (core-to-bus ratio) +packets. While CBR packets are always recorded when tracing is enabled, power +event packets are recorded only if the "pwr_evt" config term was used. Refer to +the config terms section above. The power events record information about +C-state changes, whereas CBR is indicative of CPU frequency. perf script +"event,synth" fields display information like this: + cbr: cbr: 22 freq: 2189 MHz (200%) + mwait: hints: 0x60 extensions: 0x1 + pwre: hw: 0 cstate: 2 sub-cstate: 0 + exstop: ip: 1 + pwrx: deepest cstate: 2 last cstate: 2 wake reason: 0x4 +Where: + "cbr" includes the frequency and the percentage of maximum non-turbo + "mwait" shows mwait hints and extensions + "pwre" shows C-state transitions (to a C-state deeper than C0) and + whether initiated by hardware + "exstop" indicates execution stopped and whether the IP was recorded + exactly, + "pwrx" indicates return to C0 +For more details refer to the Intel 64 and IA-32 Architectures Software +Developer Manuals. + +Error events show where the decoder lost the trace. Error events are quite important. Users must know if what they are seeing is a complete picture or not. diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index e2a4c5e0dbe5..a3abe04c779d 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -3,13 +3,15 @@ c synthesize branches events (calls only) r synthesize branches events (returns only) x synthesize transactions events + w synthesize ptwrite events + p synthesize power events e synthesize error events d create a debug log g synthesize a call chain (use with i or x) l synthesize last branch entries (use with i or x) s skip initial number of events - The default is all events i.e. the same as --itrace=ibxe + The default is all events i.e. the same as --itrace=ibxwpe In addition, the period (default 100000) for instructions events can be specified in units of: @@ -26,8 +28,8 @@ Also the number of last branch entries (default 64, max. 1024) for instructions or transactions events can be specified. - It is also possible to skip events generated (instructions, branches, transactions) - at the beginning. This is useful to ignore initialization code. + It is also possible to skip events generated (instructions, branches, transactions, + ptwrite, power) at the beginning. This is useful to ignore initialization code. --itrace=i0nss1000000 diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index 8ffbd272952d..a89273d8e744 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -39,6 +39,10 @@ OPTIONS --verbose:: Be more verbose. (Show symbol address, etc) +-q:: +--quiet:: + Do not show any message. (Suppress -v) + -D:: --dump-raw-trace:: Dump raw trace in ASCII. diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index 3f06730c7f47..822414235170 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -76,7 +76,7 @@ REPORT OPTIONS -c:: --coalesce:: - Specify sorintg fields for single cacheline display. + Specify sorting fields for single cacheline display. Following fields are available: tid,pid,iaddr,dso (see COALESCE) @@ -106,7 +106,7 @@ REPORT OPTIONS -d:: --display:: - Siwtch to HITM type (rmt, lcl) to display and sort on. Total HITMs as default. + Switch to HITM type (rmt, lcl) to display and sort on. Total HITMs as default. C2C RECORD ---------- @@ -248,7 +248,7 @@ output fields set for caheline offsets output: Code address, Code symbol, Shared Object, Source line dso - coalesced by shared object -By default the coalescing is setup with 'pid,tid,iaddr'. +By default the coalescing is setup with 'pid,iaddr'. STDIO OUTPUT ------------ diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 9365b75fd04f..5b4fff3adc4b 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -498,6 +498,18 @@ record.*:: But if this option is 'no-cache', it will not update the build-id cache. 'skip' skips post-processing and does not update the cache. +diff.*:: + diff.order:: + This option sets the number of columns to sort the result. + The default is 0, which means sorting by baseline. + Setting it to 1 will sort the result by delta (or other + compute method selected). + + diff.compute:: + This options sets the method for computing the diff result. + Possible values are 'delta', 'delta-abs', 'ratio' and + 'wdiff'. Default is 'delta'. + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index 3e9490b9c533..a79c84ae61aa 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -73,6 +73,10 @@ OPTIONS Be verbose, for instance, show the raw counts in addition to the diff. +-q:: +--quiet:: + Do not show any message. (Suppress -v) + -f:: --force:: Don't do ownership validation. @@ -86,8 +90,9 @@ OPTIONS -c:: --compute:: - Differential computation selection - delta,ratio,wdiff (default is delta). - See COMPARISON METHODS section for more info. + Differential computation selection - delta, ratio, wdiff, delta-abs + (default is delta-abs). Default can be changed using diff.compute + config option. See COMPARISON METHODS section for more info. -p:: --period:: @@ -99,7 +104,11 @@ OPTIONS -o:: --order:: - Specify compute sorting column number. + Specify compute sorting column number. 0 means sorting by baseline + overhead and 1 (default) means sorting by computed value of column 1 + (data from the first file other base baseline). Values more than 1 + can be used only if enough data files are provided. + The default value can be set using the diff.order config option. --percentage:: Determine how to display the overhead percentage of filtered entries. @@ -181,6 +190,10 @@ with: relative to how entries are filtered. Use --percentage=absolute to prevent such fluctuation. +delta-abs +~~~~~~~~~ +Same as 'delta` method, but sort the result with the absolute values. + ratio ~~~~~ If specified the 'Ratio' column is displayed with value 'r' computed as: diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt new file mode 100644 index 000000000000..721a447f046e --- /dev/null +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -0,0 +1,87 @@ +perf-ftrace(1) +============= + +NAME +---- +perf-ftrace - simple wrapper for kernel's ftrace functionality + + +SYNOPSIS +-------- +[verse] +'perf ftrace' <command> + +DESCRIPTION +----------- +The 'perf ftrace' command is a simple wrapper of kernel's ftrace +functionality. It only supports single thread tracing currently and +just reads trace_pipe in text and then write it to stdout. + +The following options apply to perf ftrace. + +OPTIONS +------- + +-t:: +--tracer=:: + Tracer to use: function_graph or function. + +-v:: +--verbose=:: + Verbosity level. + +-p:: +--pid=:: + Trace on existing process id (comma separated list). + +-a:: +--all-cpus:: + Force system-wide collection. Scripts run without a <command> + normally use -a by default, while scripts run with a <command> + normally don't - this option allows the latter to be run in + system-wide mode. + +-C:: +--cpu=:: + Only trace for the list of CPUs provided. Multiple CPUs can + be provided as a comma separated list with no space like: 0,1. + Ranges of CPUs are specified with -: 0-2. + Default is to trace on all online CPUs. + +-T:: +--trace-funcs=:: + Only trace functions given by the argument. Multiple functions + can be given by using this option more than once. The function + argument also can be a glob pattern. It will be passed to + 'set_ftrace_filter' in tracefs. + +-N:: +--notrace-funcs=:: + Do not trace functions given by the argument. Like -T option, + this can be used more than once to specify multiple functions + (or glob patterns). It will be passed to 'set_ftrace_notrace' + in tracefs. + +-G:: +--graph-funcs=:: + Set graph filter on the given function (or a glob pattern). + This is useful for the function_graph tracer only and enables + tracing for functions executed from the given function. + This can be used more than once to specify multiple functions. + It will be passed to 'set_graph_function' in tracefs. + +-g:: +--nograph-funcs=:: + Set graph notrace filter on the given function (or a glob pattern). + Like -G option, this is useful for the function_graph tracer only + and disables tracing for function executed from the given function. + This can be used more than once to specify multiple functions. + It will be passed to 'set_graph_notrace' in tracefs. + +-D:: +--graph-depth=:: + Set max depth for function graph tracer to follow + +SEE ALSO +-------- +linkperf:perf-record[1], linkperf:perf-trace[1] diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt new file mode 100644 index 000000000000..954ea9e21236 --- /dev/null +++ b/tools/perf/Documentation/perf-kallsyms.txt @@ -0,0 +1,24 @@ +perf-kallsyms(1) +============== + +NAME +---- +perf-kallsyms - Searches running kernel for symbols + +SYNOPSIS +-------- +[verse] +'perf kallsyms <options> symbol_name[,symbol_name...]' + +DESCRIPTION +----------- +This command searches the running kernel kallsyms file for the given symbol(s) +and prints information about it, including the DSO, the kallsyms begin/end +addresses and the addresses in the ELF kallsyms symbol table (for symbols in +modules). + +OPTIONS +------- +-v:: +--verbose=:: + Increase verbosity level, showing details about symbol table loading, etc. diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 41857cce5e86..f709de54707b 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' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|event_glob] +'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|sdt|event_glob] DESCRIPTION ----------- @@ -24,6 +24,10 @@ Don't print descriptions. --long-desc:: Print longer event descriptions. +--details:: +Print how named events are resolved internally into perf events, and also +any extra expressions computed by perf stat. + [[EVENT_MODIFIERS]] EVENT MODIFIERS @@ -240,6 +244,8 @@ To limit the list use: . 'pmu' to print the kernel supplied PMU events. +. 'sdt' to list all Statically Defined Tracepoint 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-probe.txt b/tools/perf/Documentation/perf-probe.txt index e6c9902c6d82..165c2b1d4317 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -240,9 +240,13 @@ Add a probe on schedule() function 12th line with recording cpu local variable: or ./perf probe --add='schedule:12 cpu' - this will add one or more probes which has the name start with "schedule". +Add one or more probes which has the name start with "schedule". - Add probes on lines in schedule() function which calls update_rq_clock(). + ./perf probe schedule* + or + ./perf probe --add='schedule*' + +Add probes on lines in schedule() function which calls update_rq_clock(). ./perf probe 'schedule;update_rq_clock*' or diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 5054d9147f0f..b0e9e921d534 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -157,7 +157,7 @@ OPTIONS -a:: --all-cpus:: - System-wide collection from all CPUs. + System-wide collection from all CPUs (default if no target is specified). -p:: --pid=:: @@ -225,7 +225,7 @@ OPTIONS the libunwind or libdw library) should be used instead. Using the "lbr" method doesn't require any compiler options. It will produce call graphs from the hardware LBR registers. The - main limition is that it is only available on new Intel + main limitation is that it is only available on new Intel platforms, such as Haswell. It can only get user call chain. It doesn't work with branch stack sampling at the same time. @@ -347,6 +347,9 @@ Enable weightened sampling. An additional weight is recorded per sample and can 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. +--namespaces:: +Record events of type PERF_RECORD_NAMESPACES. + --transaction:: Record transaction flags for transaction related events. @@ -421,9 +424,19 @@ Configure all used events to run in user space. --timestamp-filename Append timestamp to output file name. ---switch-output:: +--switch-output[=mode]:: Generate multiple perf.data files, timestamp prefixed, switching to a new one -when receiving a SIGUSR2. +based on 'mode' value: + "signal" - when receiving a SIGUSR2 (default value) or + <size> - when reaching the size threshold, size is expected to + be a number with appended unit character - B/K/M/G + <time> - when reaching the time threshold, size is expected to + be a number with appended unit character - s/m/h/d + + Note: the precision of the size threshold hugely depends + on your configuration - the number and size of your ring + buffers (-m). It is generally more precise for higher sizes + (like >5M), for lower values expect different sizes. A possible use case is to, given an external event, slice the perf.data file that gets then processed, possibly via a perf script, to decide if that diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index f2914f03ae7b..9fa84617181e 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -25,6 +25,10 @@ OPTIONS --verbose:: Be more verbose. (show symbol address, etc) +-q:: +--quiet:: + Do not show any message. (Suppress -v) + -n:: --show-nr-samples:: Show the number of samples for each symbol @@ -68,7 +72,8 @@ OPTIONS --sort=:: Sort histogram entries by given key(s) - multiple keys can be specified in CSV format. Following sort keys are available: - pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, local_weight. + pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, + local_weight, cgroup_id. Each key has following meaning: @@ -76,6 +81,7 @@ OPTIONS - pid: command and tid of the task - dso: name of library or module executed at the time of sample - symbol: name of function executed at the time of sample + - symbol_size: size of function executed at the time of sample - parent: name of function matched to the parent regex filter. Unmatched entries are displayed as "[other]". - cpu: cpu number the task ran at the time of sample @@ -87,6 +93,7 @@ OPTIONS - 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. + - cgroup_id: ID derived from cgroup namespace device and inode numbers. - transaction: Transaction abort flags. - overhead: Overhead percentage of sample - overhead_sys: Overhead percentage of sample running in system mode @@ -168,11 +175,14 @@ OPTIONS By default, every sort keys not specified in -F will be appended automatically. + If the keys starts with a prefix '+', then it will append the specified + field(s) to the default field order. For example: perf report -F +period,sample. + -p:: --parent=<regex>:: A regex filter to identify parent. The parent is a caller of this function and searched through the callchain, thus it requires callchain - information recorded. The pattern is in the exteneded regex format and + information recorded. The pattern is in the extended regex format and defaults to "\^sys_|^do_page_fault", see '--sort parent'. -x:: @@ -197,8 +207,8 @@ OPTIONS -g:: --call-graph=<print_type,threshold[,print_limit],order,sort_key[,branch],value>:: Display call chains using type, min percent threshold, print limit, - call order, sort key, optional branch and value. Note that ordering of - parameters is not fixed so any parement can be given in an arbitraty order. + call order, sort key, optional branch and value. Note that ordering + is not fixed so any parameter can be given in an arbitrary order. One exception is the print_limit which should be preceded by threshold. print_type can be either: @@ -225,6 +235,7 @@ OPTIONS sort_key can be: - function: compare on functions (default) - address: compare on individual code addresses + - srcline: compare on source filename and line number branch can be: - branch: include last branch information in callgraph when available. @@ -420,6 +431,10 @@ include::itrace.txt[] --hierarchy:: Enable hierarchical output. +--inline:: + If a callgraph address belongs to an inlined function, the inline stack + will be printed. Each entry is function name or file/line. + include::callchain-overhead-calculation.txt[] SEE ALSO diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt index 76173969ab80..a092a2499e8f 100644 --- a/tools/perf/Documentation/perf-sched.txt +++ b/tools/perf/Documentation/perf-sched.txt @@ -132,6 +132,10 @@ OPTIONS for 'perf sched timehist' --migrations:: Show migration events. +-n:: +--next:: + Show next task. + -I:: --idle-hist:: Show idle-related events only. @@ -143,6 +147,8 @@ OPTIONS for 'perf sched timehist' stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. +--state:: + Show task state when it switched out. SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt index dfbb506d2c34..142606c0ec9c 100644 --- a/tools/perf/Documentation/perf-script-perl.txt +++ b/tools/perf/Documentation/perf-script-perl.txt @@ -39,7 +39,7 @@ EVENT HANDLERS When perf script is invoked using a trace script, a user-defined 'handler function' is called for each event in the trace. If there's no handler function defined for a given event type, the event is -ignored (or passed to a 'trace_handled' function, see below) and the +ignored (or passed to a 'trace_unhandled' function, see below) and the next event is processed. Most of the event's field values are passed as arguments to the diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index 54acba221558..51ec2d20068a 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -149,10 +149,8 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu, print "id=%d, args=%s\n" % \ (id, args), -def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs, - common_pid, common_comm): - print_header(event_name, common_cpu, common_secs, common_nsecs, - common_pid, common_comm) +def trace_unhandled(event_name, context, event_fields_dict): + print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())]) def print_header(event_name, cpu, secs, nsecs, pid, comm): print "%-20s %5u %05u.%09u %8u %-20s " % \ @@ -321,7 +319,7 @@ So those are the essential steps in writing and running a script. The process can be generalized to any tracepoint or set of tracepoints you're interested in - basically find the tracepoint(s) you're interested in by looking at the list of available events shown by -'perf list' and/or look in /sys/kernel/debug/tracing events for +'perf list' and/or look in /sys/kernel/debug/tracing/events/ for detailed event and field info, record the corresponding trace data using 'perf record', passing it the list of interesting events, generate a skeleton script using 'perf script -g python' and modify the @@ -334,7 +332,7 @@ right place, you can have your script listed alongside the other scripts listed by the 'perf script -l' command e.g.: ---- -root@tropicana:~# perf script -l +# perf script -l List of available trace scripts: wakeup-latency system-wide min/max/avg wakeup latency rw-by-file <comm> r/w activity for a program, by file @@ -383,8 +381,6 @@ source tree: ---- # ls -al kernel-source/tools/perf/scripts/python - -root@tropicana:/home/trz/src/tip# ls -al tools/perf/scripts/python total 32 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 . drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 .. @@ -399,7 +395,7 @@ otherwise your script won't show up at run-time), 'perf script -l' should show a new entry for your script: ---- -root@tropicana:~# perf script -l +# perf script -l List of available trace scripts: wakeup-latency system-wide min/max/avg wakeup latency rw-by-file <comm> r/w activity for a program, by file @@ -437,7 +433,7 @@ EVENT HANDLERS When perf script is invoked using a trace script, a user-defined 'handler function' is called for each event in the trace. If there's no handler function defined for a given event type, the event is -ignored (or passed to a 'trace_handled' function, see below) and the +ignored (or passed to a 'trace_unhandled' function, see below) and the next event is processed. Most of the event's field values are passed as arguments to the @@ -532,7 +528,7 @@ can implement a set of optional functions: gives scripts a chance to do setup tasks: ---- -def trace_begin: +def trace_begin(): pass ---- @@ -541,7 +537,7 @@ def trace_begin: as display results: ---- -def trace_end: +def trace_end(): pass ---- @@ -550,8 +546,7 @@ def trace_end: of common arguments are passed into it: ---- -def trace_unhandled(event_name, context, common_cpu, common_secs, - common_nsecs, common_pid, common_comm): +def trace_unhandled(event_name, context, event_fields_dict): pass ---- diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 5dc5c6a09ac4..5ee8796be96e 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -36,7 +36,7 @@ There are several variants of perf script: 'perf script report <script> [args]' to run and display the results of <script>. <script> is the name displayed in the output of 'perf - trace --list' i.e. the actual script name minus any language + script --list' i.e. the actual script name minus any language extension. The perf.data output from a previous run of 'perf script record <script>' is used and should be present for this command to succeed. [args] refers to the (mainly optional) args expected by @@ -76,7 +76,7 @@ OPTIONS Any command you can specify in a shell. -D:: ---dump-raw-script=:: +--dump-raw-trace=:: Display verbose dump of the trace data. -L:: @@ -116,8 +116,9 @@ OPTIONS --fields:: Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, - srcline, period, iregs, brstack, brstacksym, flags, bpf-output, - callindent, insn, insnlen. Field list can be prepended with the type, trace, sw or hw, + srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff, + callindent, insn, insnlen, synth. + Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace @@ -130,6 +131,14 @@ OPTIONS i.e., the specified fields apply to all event types if the type string is not given. + In addition to overriding fields, it is also possible to add or remove + fields from the defaults. For example + + -F -cpu,+insn + + removes the cpu field and adds the insn field. Adding/removing fields + cannot be mixed with normal overriding. + The arguments are processed in the order received. A later usage can reset a prior request. e.g.: @@ -185,19 +194,29 @@ OPTIONS instruction bytes and the instruction length of the current instruction. + The synth field is used by synthesized events which may be created when + Instruction Trace decoding. + Finally, a user may not set fields to none for all event types. i.e., -F "" is not allowed. The brstack output includes branch related information with raw addresses using the - /v/v/v/v/ syntax in the following order: + /v/v/v/v/cycles syntax in the following order: FROM: branch source instruction TO : branch target instruction M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported X/- : X=branch inside a transactional region, -=not in transaction region or not supported A/- : A=TSX abort entry, -=not aborted region or not supported + cycles The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible. + When brstackinsn is specified the full assembler sequences of branch sequences for each sample + is printed. This is the full execution path leading to the sample. This is only supported when the + sample was recorded with perf record -b or -j any. + + The brstackoff field will print an offset into a specific dso/binary. + -k:: --vmlinux=<file>:: vmlinux pathname @@ -248,6 +267,9 @@ OPTIONS --show-mmap-events Display mmap related events (e.g. MMAP, MMAP2). +--show-namespace-events + Display namespace events i.e. events of type PERF_RECORD_NAMESPACES. + --show-switch-events Display context switch events i.e. events of type PERF_RECORD_SWITCH or PERF_RECORD_SWITCH_CPU_WIDE. @@ -299,6 +321,14 @@ include::itrace.txt[] stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. +--max-blocks:: + Set the maximum number of program blocks to print with brstackasm for + each sample. + +--inline:: + If a callgraph address belongs to an inlined function, the inline stack + will be printed. Each entry has function name and file/line. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index d96ccd4844df..698076313606 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -63,7 +63,7 @@ report:: -a:: --all-cpus:: - system-wide collection from all CPUs + system-wide collection from all CPUs (default if no target is specified) -c:: --scale:: @@ -94,8 +94,7 @@ to activate system-wide monitoring. Default is to count on all CPUs. -A:: --no-aggr:: -Do not aggregate counts across all monitored CPUs in system-wide mode (-a). -This option is only valid in system-wide mode. +Do not aggregate counts across all monitored CPUs. -n:: --null:: @@ -237,6 +236,23 @@ To interpret the results it is usually needed to know on which CPUs the workload runs on. If needed the CPUs can be forced using taskset. +--no-merge:: +Do not merge results from same PMUs. + +--smi-cost:: +Measure SMI cost if msr/aperf/ and msr/smi/ events are supported. + +During the measurement, the /sys/device/cpu/freeze_on_smi will be set to +freeze core counters on SMI. +The aperf counter will not be effected by the setting. +The cost of SMI can be measured by (aperf - unhalted core cycles). + +In practice, the percentages of SMI cycles is very useful for performance +oriented analysis. --metric_only will be applied by default. +The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf + +Users who wants to get the actual value can apply --no-metric-only. + EXAMPLES -------- diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 781b019751a4..c1e3288a2dfb 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -35,7 +35,10 @@ OPTIONS -e:: --expr:: - List of syscalls to show, currently only syscall names. +--event:: + List of syscalls and other perf events (tracepoints, HW cache events, + etc) to show. + See 'perf list' for a complete list of events. Prefixing with ! shows all syscalls but the ones specified. You may need to escape it. @@ -120,7 +123,8 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. major or all pagefaults. Default value is maj. --syscalls:: - Trace system calls. This options is enabled by default. + Trace system calls. This options is enabled by default, disable with + --no-syscalls. --call-graph [mode,type,min[,limit],order[,key][,branch]]:: Setup and enable call-graph (stack chain/backtrace) recording. @@ -135,9 +139,6 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. --kernel-syscall-graph:: Show the kernel callchains on the syscall exit path. ---event:: - Trace other events, see 'perf list' for a complete list. - --max-stack:: Set the stack depth limit when parsing the callchain, anything beyond the specified depth will be ignored. Note that at this point diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index b664b18d3991..de8b39dda7b8 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -11,8 +11,8 @@ All fields are in native-endian of the machine that generated the perf.data. When perf is writing to a pipe it uses a special version of the file format that does not rely on seeking to adjust data offsets. This -format is not described here. The pipe version can be converted to -normal perf.data with perf inject. +format is described in "Pipe-mode data" section. The pipe data version can be +augmented with additional events using perf inject. The file starts with a perf_header: @@ -270,7 +270,7 @@ When the event stream contains multiple events each event is identified by an ID. This can be either through the PERF_SAMPLE_ID or the PERF_SAMPLE_IDENTIFIER header. The PERF_SAMPLE_IDENTIFIER header is at a fixed offset from the event header, which allows reliable -parsing of the header. Relying on ID may be ambigious. +parsing of the header. Relying on ID may be ambiguous. IDENTIFIER is only supported by newer Linux kernels. Perf record specific events: @@ -288,7 +288,7 @@ struct attr_event { uint64_t id[]; }; - PERF_RECORD_HEADER_EVENT_TYPE = 65, /* depreceated */ + PERF_RECORD_HEADER_EVENT_TYPE = 65, /* deprecated */ #define MAX_EVENT_NAME 64 @@ -411,6 +411,21 @@ An array bound by the perf_file_section size. ids points to a array of uint64_t defining the ids for event attr attr. +Pipe-mode data + +Pipe-mode avoid seeks in the file by removing the perf_file_section and flags +from the struct perf_header. The trimmed header is: + +struct perf_pipe_file_header { + u64 magic; + u64 size; +}; + +The information about attrs, data, and event_types is instead in the +synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA and +PERF_RECORD_HEADER_EVENT_TYPE that are generated by perf record in pipe-mode. + + References: include/uapi/linux/perf_event.h diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt index 8a6479c0eac9..db0ca3063eae 100644 --- a/tools/perf/Documentation/tips.txt +++ b/tools/perf/Documentation/tips.txt @@ -22,8 +22,8 @@ If you have debuginfo enabled, try: perf report -s sym,srcline For memory address profiling, try: perf mem record / perf mem report For tracepoint events, try: perf report -s trace_fields To record callchains for each sample: perf record -g -To record every process run by an user: perf record -u <user> -Skip collecing build-id when recording: perf record -B +To record every process run by a user: perf record -u <user> +Skip collecting build-id when recording: perf record -B To change sampling frequency to 100 Hz: perf record -F 100 See assembly instructions with percentage: perf annotate <symbol> If you prefer Intel style assembly, try: perf annotate -M intel diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index a511e5f31e36..a29da46d180f 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -12,6 +12,7 @@ tools/arch/sparc/include/asm/barrier_32.h tools/arch/sparc/include/asm/barrier_64.h tools/arch/tile/include/asm/barrier.h tools/arch/x86/include/asm/barrier.h +tools/arch/x86/include/asm/cmpxchg.h tools/arch/x86/include/asm/cpufeatures.h tools/arch/x86/include/asm/disabled-features.h tools/arch/x86/include/asm/required-features.h @@ -61,7 +62,9 @@ tools/include/asm-generic/bitops.h tools/include/linux/atomic.h tools/include/linux/bitops.h tools/include/linux/compiler.h +tools/include/linux/compiler-gcc.h tools/include/linux/coresight-pmu.h +tools/include/linux/bug.h tools/include/linux/filter.h tools/include/linux/hash.h tools/include/linux/kernel.h @@ -71,12 +74,15 @@ tools/include/uapi/asm-generic/mman-common.h tools/include/uapi/asm-generic/mman.h tools/include/uapi/linux/bpf.h tools/include/uapi/linux/bpf_common.h +tools/include/uapi/linux/fcntl.h tools/include/uapi/linux/hw_breakpoint.h tools/include/uapi/linux/mman.h tools/include/uapi/linux/perf_event.h +tools/include/uapi/linux/stat.h tools/include/linux/poison.h tools/include/linux/rbtree.h tools/include/linux/rbtree_augmented.h +tools/include/linux/refcount.h tools/include/linux/string.h tools/include/linux/stringify.h tools/include/linux/types.h diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 76c84f0eec52..bdf0e87f9b29 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -19,18 +19,18 @@ CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS) include $(srctree)/tools/scripts/Makefile.arch -$(call detected_var,ARCH) +$(call detected_var,SRCARCH) NO_PERF_REGS := 1 # Additional ARCH settings for ppc -ifeq ($(ARCH),powerpc) +ifeq ($(SRCARCH),powerpc) NO_PERF_REGS := 0 LIBUNWIND_LIBS := -lunwind -lunwind-ppc64 endif # Additional ARCH settings for x86 -ifeq ($(ARCH),x86) +ifeq ($(SRCARCH),x86) $(call detected,CONFIG_X86) ifeq (${IS_64_BIT}, 1) CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated @@ -43,12 +43,12 @@ ifeq ($(ARCH),x86) NO_PERF_REGS := 0 endif -ifeq ($(ARCH),arm) +ifeq ($(SRCARCH),arm) NO_PERF_REGS := 0 LIBUNWIND_LIBS = -lunwind -lunwind-arm endif -ifeq ($(ARCH),arm64) +ifeq ($(SRCARCH),arm64) NO_PERF_REGS := 0 LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 endif @@ -61,7 +61,7 @@ endif # Disable it on all other architectures in case libdw unwind # support is detected in system. Add supported architectures # to the check. -ifneq ($(ARCH),$(filter $(ARCH),x86 arm)) +ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm powerpc)) NO_LIBDW_DWARF_UNWIND := 1 endif @@ -115,9 +115,9 @@ endif FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS) FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf -FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi +FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi # include ARCH specific config --include $(src-perf)/arch/$(ARCH)/Makefile +-include $(src-perf)/arch/$(SRCARCH)/Makefile ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET CFLAGS += -DHAVE_ARCH_REGS_QUERY_REGISTER_OFFSET @@ -144,8 +144,12 @@ ifndef DEBUG endif ifeq ($(DEBUG),0) +ifeq ($(CC), clang) + CFLAGS += -O3 +else CFLAGS += -O6 endif +endif ifdef PARSER_DEBUG PARSER_DEBUG_BISON := -t @@ -166,10 +170,21 @@ PYTHON2_CONFIG := \ override PYTHON_CONFIG := \ $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG)) +grep-libs = $(filter -l%,$(1)) +strip-libs = $(filter-out -l%,$(1)) + PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) -PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) -PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) +ifdef PYTHON_CONFIG + PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) + PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) + PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil + PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) + ifeq ($(CC), clang) + PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS)) + endif + FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) +endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS) @@ -213,12 +228,12 @@ ifeq ($(DEBUG),0) endif INC_FLAGS += -I$(src-perf)/util/include -INC_FLAGS += -I$(src-perf)/arch/$(ARCH)/include +INC_FLAGS += -I$(src-perf)/arch/$(SRCARCH)/include INC_FLAGS += -I$(srctree)/tools/include/uapi INC_FLAGS += -I$(srctree)/tools/include/ -INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi -INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/ -INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/ +INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi +INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/ +INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/ # $(obj-perf) for generated common-cmds.h # $(obj-perf)/util for generated bison/flex headers @@ -259,6 +274,7 @@ ifdef NO_LIBELF NO_LIBUNWIND := 1 NO_LIBDW_DWARF_UNWIND := 1 NO_LIBBPF := 1 + NO_JVMTI := 1 else ifeq ($(feature-libelf), 0) ifeq ($(feature-glibc), 1) @@ -268,7 +284,7 @@ else LIBC_SUPPORT := 1 endif ifeq ($(LIBC_SUPPORT),1) - msg := $(warning No libelf found, disables 'probe' tool and BPF support in 'perf record', please install libelf-dev, libelf-devel or elfutils-libelf-devel); + msg := $(warning No libelf found. Disables 'probe' tool, jvmti and BPF support in 'perf record'. Please install libelf-dev, libelf-devel or elfutils-libelf-devel); NO_LIBELF := 1 NO_DWARF := 1 @@ -276,6 +292,7 @@ else NO_LIBUNWIND := 1 NO_LIBDW_DWARF_UNWIND := 1 NO_LIBBPF := 1 + NO_JVMTI := 1 else ifneq ($(filter s% -static%,$(LDFLAGS),),) msg := $(error No static glibc found, please install glibc-static); @@ -291,8 +308,10 @@ else endif endif ifneq ($(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 + ifndef NO_DWARF + msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); + NO_DWARF := 1 + endif else ifneq ($(feature-dwarf_getlocations), 1) msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157); @@ -307,6 +326,10 @@ ifdef NO_DWARF NO_LIBDW_DWARF_UNWIND := 1 endif +ifeq ($(feature-sched_getcpu), 1) + CFLAGS += -DHAVE_SCHED_GETCPU_SUPPORT +endif + ifndef NO_LIBELF CFLAGS += -DHAVE_LIBELF_SUPPORT EXTLIBS += -lelf @@ -332,7 +355,7 @@ ifndef NO_LIBELF 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); + msg := $(warning DWARF register mappings have not been defined for architecture $(SRCARCH), DWARF support disabled); NO_DWARF := 1 else CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS) @@ -357,7 +380,7 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_BPF_PROLOGUE $(call detected,CONFIG_BPF_PROLOGUE) else - msg := $(warning BPF prologue is not supported by architecture $(ARCH), missing regs_query_register_offset()); + msg := $(warning BPF prologue is not supported by architecture $(SRCARCH), missing regs_query_register_offset()); endif else msg := $(warning DWARF support is off, BPF prologue is disabled); @@ -383,7 +406,7 @@ ifdef PERF_HAVE_JITDUMP endif endif -ifeq ($(ARCH),powerpc) +ifeq ($(SRCARCH),powerpc) ifndef NO_DWARF CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX endif @@ -464,7 +487,7 @@ else endif ifndef NO_LOCAL_LIBUNWIND - ifeq ($(ARCH),$(filter $(ARCH),arm arm64)) + ifeq ($(SRCARCH),$(filter $(SRCARCH),arm arm64)) $(call feature_check,libunwind-debug-frame) ifneq ($(feature-libunwind-debug-frame), 1) msg := $(warning No debug_frame support found in libunwind); @@ -540,8 +563,6 @@ ifndef NO_GTK2 endif endif -grep-libs = $(filter -l%,$(1)) -strip-libs = $(filter-out -l%,$(1)) ifdef NO_LIBPERL CFLAGS += -DNO_LIBPERL @@ -589,18 +610,9 @@ else $(call disable-python,No 'python-config' tool was found: disables Python support - please install python-devel/python-dev) else - 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)) -lutil - PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) - FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) - ifneq ($(feature-libpython), 1) $(call disable-python,No 'Python.h' (for Python 2.x support) was found: disables Python support - please install python-devel/python-dev) else - ifneq ($(feature-libpython-version), 1) $(warning Python 3 is not yet supported; please set) $(warning PYTHON and/or PYTHON_CONFIG appropriately.) @@ -728,7 +740,7 @@ ifeq (${IS_64_BIT}, 1) NO_PERF_READ_VDSO32 := 1 endif endif - ifneq ($(ARCH), x86) + ifneq ($(SRCARCH), x86) NO_PERF_READ_VDSOX32 := 1 endif ifndef NO_PERF_READ_VDSOX32 @@ -757,7 +769,7 @@ ifdef LIBBABELTRACE endif ifndef NO_AUXTRACE - ifeq ($(ARCH),x86) + ifeq ($(SRCARCH),x86) ifeq ($(feature-get_cpuid), 0) msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc); NO_AUXTRACE := 1 @@ -860,7 +872,7 @@ sysconfdir = $(prefix)/etc ETC_PERFCONFIG = etc/perfconfig endif ifndef lib -ifeq ($(ARCH)$(IS_64_BIT), x861) +ifeq ($(SRCARCH)$(IS_64_BIT), x861) lib = lib64 else lib = lib diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 8bb16aa9d661..5008f51a08a2 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -226,7 +226,7 @@ endif ifeq ($(config),0) include $(srctree)/tools/scripts/Makefile.arch --include arch/$(ARCH)/Makefile +-include arch/$(SRCARCH)/Makefile endif # The FEATURE_DUMP_EXPORT holds location of the actual @@ -661,6 +661,7 @@ ifndef NO_PERF_READ_VDSOX32 endif ifndef NO_JVMTI $(call QUIET_INSTALL, $(LIBJVMTI)) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \ $(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)'; endif $(call QUIET_INSTALL, libexec) \ @@ -725,13 +726,13 @@ config-clean: $(call QUIET_CLEAN, config) $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null -clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean +clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) $(OUTPUT).config-detected $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents $(OUTPUT)$(LIBJVMTI).so $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \ - $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \ + $(OUTPUT)util/intel-pt-decoder/inat-tables.c \ $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \ $(OUTPUT)pmu-events/pmu-events.c $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean diff --git a/tools/perf/arch/Build b/tools/perf/arch/Build index 109eb75cf7de..d9b6af837c7d 100644 --- a/tools/perf/arch/Build +++ b/tools/perf/arch/Build @@ -1,2 +1,2 @@ libperf-y += common.o -libperf-y += $(ARCH)/ +libperf-y += $(SRCARCH)/ diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index dfea6b635525..7ce3d1a25133 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -17,6 +17,7 @@ #include <api/fs/fs.h> #include <linux/bitops.h> +#include <linux/compiler.h> #include <linux/coresight-pmu.h> #include <linux/kernel.h> #include <linux/log2.h> @@ -33,6 +34,7 @@ #include "../../util/cs-etm.h" #include <stdlib.h> +#include <sys/stat.h> #define ENABLE_SINK_MAX 128 #define CS_BUS_DEVICE_PATH "/bus/coresight/devices/" @@ -201,19 +203,18 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME, opts->auxtrace_snapshot_size); - if (cs_etm_evsel) { - /* - * To obtain the auxtrace buffer file descriptor, the auxtrace - * event must come first. - */ - perf_evlist__to_front(evlist, cs_etm_evsel); - /* - * In the case of per-cpu mmaps, we need the CPU on the - * AUX event. - */ - if (!cpu_map__empty(cpus)) - perf_evsel__set_sample_bit(cs_etm_evsel, CPU); - } + /* + * To obtain the auxtrace buffer file descriptor, the auxtrace + * event must come first. + */ + perf_evlist__to_front(evlist, cs_etm_evsel); + + /* + * In the case of per-cpu mmaps, we need the CPU on the + * AUX event. + */ + if (!cpu_map__empty(cpus)) + perf_evsel__set_sample_bit(cs_etm_evsel, CPU); /* Add dummy event to keep tracking */ if (opts->full_auxtrace) { @@ -582,8 +583,7 @@ static FILE *cs_device__open_file(const char *name) } -static __attribute__((format(printf, 2, 3))) -int cs_device__print_file(const char *name, const char *fmt, ...) +static int __printf(2, 3) cs_device__print_file(const char *name, const char *fmt, ...) { va_list args; FILE *file; diff --git a/tools/perf/arch/arm/util/dwarf-regs.c b/tools/perf/arch/arm/util/dwarf-regs.c index 33ec5b339da8..8bb176a37990 100644 --- a/tools/perf/arch/arm/util/dwarf-regs.c +++ b/tools/perf/arch/arm/util/dwarf-regs.c @@ -9,6 +9,7 @@ */ #include <stddef.h> +#include <linux/stringify.h> #include <dwarf-regs.h> struct pt_regs_dwarfnum { @@ -16,10 +17,9 @@ struct pt_regs_dwarfnum { unsigned int dwarfnum; }; -#define STR(s) #s #define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num} #define GPR_DWARFNUM_NAME(num) \ - {.name = STR(%r##num), .dwarfnum = num} + {.name = __stringify(%r##num), .dwarfnum = num} #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0} /* diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c index b4176c60117a..bacfa00fca39 100644 --- a/tools/perf/arch/arm/util/unwind-libdw.c +++ b/tools/perf/arch/arm/util/unwind-libdw.c @@ -1,6 +1,7 @@ #include <elfutils/libdwfl.h> #include "../../util/unwind-libdw.h" #include "../../util/perf_regs.h" +#include "../../util/event.h" bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index 18b13518d8d8..eebe1ec9d2ee 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -2,3 +2,4 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 endif PERF_HAVE_JITDUMP := 1 +PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c index 44eafd6f2d50..8f1908756cb6 100644 --- a/tools/perf/arch/arm64/annotate/instructions.c +++ b/tools/perf/arch/arm64/annotate/instructions.c @@ -50,7 +50,7 @@ static int arm64__annotate_init(struct arch *arch) arch->initialized = true; arch->priv = arm; arch->associate_instruction_ops = arm64__associate_instruction_ops; - arch->objdump.comment_char = ';'; + arch->objdump.comment_char = '/'; arch->objdump.skip_functions_char = '+'; return 0; diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h index 26759363f921..36e375f5a211 100644 --- a/tools/perf/arch/arm64/include/dwarf-regs-table.h +++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h @@ -2,12 +2,12 @@ /* This is included in perf/util/dwarf-regs.c */ static const char * const aarch64_regstr_tbl[] = { - "%r0", "%r1", "%r2", "%r3", "%r4", - "%r5", "%r6", "%r7", "%r8", "%r9", - "%r10", "%r11", "%r12", "%r13", "%r14", - "%r15", "%r16", "%r17", "%r18", "%r19", - "%r20", "%r21", "%r22", "%r23", "%r24", - "%r25", "%r26", "%r27", "%r28", "%r29", + "%x0", "%x1", "%x2", "%x3", "%x4", + "%x5", "%x6", "%x7", "%x8", "%x9", + "%x10", "%x11", "%x12", "%x13", "%x14", + "%x15", "%x16", "%x17", "%x18", "%x19", + "%x20", "%x21", "%x22", "%x23", "%x24", + "%x25", "%x26", "%x27", "%x28", "%x29", "%lr", "%sp", }; #endif diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c index d49efeb8172e..cd764a9fd098 100644 --- a/tools/perf/arch/arm64/util/dwarf-regs.c +++ b/tools/perf/arch/arm64/util/dwarf-regs.c @@ -8,19 +8,25 @@ * published by the Free Software Foundation. */ +#include <errno.h> #include <stddef.h> +#include <string.h> #include <dwarf-regs.h> +#include <linux/ptrace.h> /* for struct user_pt_regs */ +#include <linux/stringify.h> +#include "util.h" struct pt_regs_dwarfnum { const char *name; unsigned int dwarfnum; }; -#define STR(s) #s #define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num} #define GPR_DWARFNUM_NAME(num) \ - {.name = STR(%x##num), .dwarfnum = num} + {.name = __stringify(%x##num), .dwarfnum = num} #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0} +#define DWARFNUM2OFFSET(index) \ + (index * sizeof((struct user_pt_regs *)0)->regs[0]) /* * Reference: @@ -78,3 +84,13 @@ const char *get_arch_regstr(unsigned int n) return roff->name; return NULL; } + +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_dwarfnum *roff; + + for (roff = regdwarfnum_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return DWARFNUM2OFFSET(roff->dwarfnum); + return -EINVAL; +} diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c index c116b713f7f7..b415dfdbccca 100644 --- a/tools/perf/arch/arm64/util/unwind-libunwind.c +++ b/tools/perf/arch/arm64/util/unwind-libunwind.c @@ -1,6 +1,6 @@ +#include <errno.h> #ifndef REMOTE_UNWIND_LIBUNWIND -#include <errno.h> #include <libunwind.h> #include "perf_regs.h" #include "../../util/unwind.h" diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index 886dd2aaff0d..6b40e9f01740 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -4,6 +4,8 @@ #include "../util/util.h" #include "../util/debug.h" +#include "sane_ctype.h" + const char *const arm_triplets[] = { "arm-eabi-", "arm-linux-androideabi-", @@ -24,6 +26,7 @@ const char *const arm64_triplets[] = { const char *const powerpc_triplets[] = { "powerpc-unknown-linux-gnu-", + "powerpc-linux-gnu-", "powerpc64-unknown-linux-gnu-", "powerpc64-linux-gnu-", "powerpc64le-linux-gnu-", diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 90ad64b231cd..2e6595310420 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -5,4 +5,6 @@ libperf-y += perf_regs.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_DWARF) += skip-callchain-idx.o + libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o +libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c index 41bdf9530d82..98ac87052a74 100644 --- a/tools/perf/arch/powerpc/util/dwarf-regs.c +++ b/tools/perf/arch/powerpc/util/dwarf-regs.c @@ -15,6 +15,7 @@ #include <dwarf-regs.h> #include <linux/ptrace.h> #include <linux/kernel.h> +#include <linux/stringify.h> #include "util.h" struct pt_regs_dwarfnum { @@ -24,10 +25,10 @@ struct pt_regs_dwarfnum { }; #define REG_DWARFNUM_NAME(r, num) \ - {.name = STR(%)STR(r), .dwarfnum = num, \ + {.name = __stringify(%)__stringify(r), .dwarfnum = num, \ .ptregs_offset = offsetof(struct pt_regs, r)} #define GPR_DWARFNUM_NAME(num) \ - {.name = STR(%gpr##num), .dwarfnum = num, \ + {.name = __stringify(%gpr##num), .dwarfnum = num, \ .ptregs_offset = offsetof(struct pt_regs, gpr[num])} #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0, .ptregs_offset = 0} diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c index 74eee30398f8..249723f0e6a9 100644 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -1,3 +1,4 @@ +#include <errno.h> #include "util/kvm-stat.h" #include "util/parse-events.h" #include "util/debug.h" diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index a3c3e1ce6807..f860dc411f69 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -1,5 +1,11 @@ +#include <errno.h> +#include <string.h> +#include <regex.h> + #include "../../perf.h" +#include "../../util/util.h" #include "../../util/perf_regs.h" +#include "../../util/debug.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG(r0, PERF_REG_POWERPC_R0), @@ -47,3 +53,109 @@ const struct sample_reg sample_reg_masks[] = { SMPL_REG(dsisr, PERF_REG_POWERPC_DSISR), SMPL_REG_END }; + +/* REG or %rREG */ +#define SDT_OP_REGEX1 "^(%r)?([1-2]?[0-9]|3[0-1])$" + +/* -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) */ +#define SDT_OP_REGEX2 "^(\\-)?([0-9]+)\\((%r)?([1-2]?[0-9]|3[0-1])\\)$" + +static regex_t sdt_op_regex1, sdt_op_regex2; + +static int sdt_init_op_regex(void) +{ + static int initialized; + int ret = 0; + + if (initialized) + return 0; + + ret = regcomp(&sdt_op_regex1, SDT_OP_REGEX1, REG_EXTENDED); + if (ret) + goto error; + + ret = regcomp(&sdt_op_regex2, SDT_OP_REGEX2, REG_EXTENDED); + if (ret) + goto free_regex1; + + initialized = 1; + return 0; + +free_regex1: + regfree(&sdt_op_regex1); +error: + pr_debug4("Regex compilation error.\n"); + return ret; +} + +/* + * Parse OP and convert it into uprobe format, which is, +/-NUM(%gprREG). + * Possible variants of OP are: + * Format Example + * ------------------------- + * NUM(REG) 48(18) + * -NUM(REG) -48(18) + * NUM(%rREG) 48(%r18) + * -NUM(%rREG) -48(%r18) + * REG 18 + * %rREG %r18 + * iNUM i0 + * i-NUM i-1 + * + * SDT marker arguments on Powerpc uses %rREG form with -mregnames flag + * and REG form with -mno-regnames. Here REG is general purpose register, + * which is in 0 to 31 range. + */ +int arch_sdt_arg_parse_op(char *old_op, char **new_op) +{ + int ret, new_len; + regmatch_t rm[5]; + char prefix; + + /* Constant argument. Uprobe does not support it */ + if (old_op[0] == 'i') { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + ret = sdt_init_op_regex(); + if (ret < 0) + return ret; + + if (!regexec(&sdt_op_regex1, old_op, 3, rm, 0)) { + /* REG or %rREG --> %gprREG */ + + new_len = 5; /* % g p r NULL */ + new_len += (int)(rm[2].rm_eo - rm[2].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%%gpr%.*s", + (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so); + } else if (!regexec(&sdt_op_regex2, old_op, 5, rm, 0)) { + /* + * -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) --> + * +/-NUM(%gprREG) + */ + prefix = (rm[1].rm_so == -1) ? '+' : '-'; + + new_len = 8; /* +/- ( % g p r ) NULL */ + new_len += (int)(rm[2].rm_eo - rm[2].rm_so); + new_len += (int)(rm[4].rm_eo - rm[4].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%c%.*s(%%gpr%.*s)", prefix, + (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so, + (int)(rm[4].rm_eo - rm[4].rm_so), old_op + rm[4].rm_so); + } else { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + return SDT_ARG_VALID; +} diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 1030a6e504bb..bf9a2594572c 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -10,6 +10,7 @@ #include "symbol.h" #include "map.h" #include "probe-event.h" +#include "probe-file.h" #ifdef HAVE_LIBELF_SUPPORT bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) @@ -51,6 +52,18 @@ int arch__compare_symbol_names(const char *namea, const char *nameb) return strcmp(namea, nameb); } + +int arch__compare_symbol_names_n(const char *namea, const char *nameb, + unsigned int n) +{ + /* Skip over initial dot */ + if (*namea == '.') + namea++; + if (*nameb == '.') + nameb++; + + return strncmp(namea, nameb, n); +} #endif #if defined(_CALL_ELF) && _CALL_ELF == 2 @@ -79,13 +92,18 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev, * However, if the user specifies an offset, we fall back to using the * GEP since all userspace applications (objdump/readelf) show function * disassembly with offsets from the GEP. - * - * In addition, we shouldn't specify an offset for kretprobes. */ - if (pev->point.offset || (!pev->uprobes && pev->point.retprobe) || - !map || !sym) + if (pev->point.offset || !map || !sym) return; + /* For kretprobes, add an offset only if the kernel supports it */ + if (!pev->uprobes && pev->point.retprobe) { +#ifdef HAVE_LIBELF_SUPPORT + if (!kretprobe_offset_is_supported()) +#endif + return; + } + lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym); if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) diff --git a/tools/perf/arch/powerpc/util/unwind-libdw.c b/tools/perf/arch/powerpc/util/unwind-libdw.c new file mode 100644 index 000000000000..3a24b3c43273 --- /dev/null +++ b/tools/perf/arch/powerpc/util/unwind-libdw.c @@ -0,0 +1,73 @@ +#include <elfutils/libdwfl.h> +#include "../../util/unwind-libdw.h" +#include "../../util/perf_regs.h" +#include "../../util/event.h" + +/* See backends/ppc_initreg.c and backends/ppc_regs.c in elfutils. */ +static const int special_regs[3][2] = { + { 65, PERF_REG_POWERPC_LINK }, + { 101, PERF_REG_POWERPC_XER }, + { 109, PERF_REG_POWERPC_CTR }, +}; + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct unwind_info *ui = arg; + struct regs_dump *user_regs = &ui->sample->user_regs; + Dwarf_Word dwarf_regs[32], dwarf_nip; + size_t i; + +#define REG(r) ({ \ + Dwarf_Word val = 0; \ + perf_reg_value(&val, user_regs, PERF_REG_POWERPC_##r); \ + val; \ +}) + + dwarf_regs[0] = REG(R0); + dwarf_regs[1] = REG(R1); + dwarf_regs[2] = REG(R2); + dwarf_regs[3] = REG(R3); + dwarf_regs[4] = REG(R4); + dwarf_regs[5] = REG(R5); + dwarf_regs[6] = REG(R6); + dwarf_regs[7] = REG(R7); + dwarf_regs[8] = REG(R8); + dwarf_regs[9] = REG(R9); + dwarf_regs[10] = REG(R10); + dwarf_regs[11] = REG(R11); + dwarf_regs[12] = REG(R12); + dwarf_regs[13] = REG(R13); + dwarf_regs[14] = REG(R14); + dwarf_regs[15] = REG(R15); + dwarf_regs[16] = REG(R16); + dwarf_regs[17] = REG(R17); + dwarf_regs[18] = REG(R18); + dwarf_regs[19] = REG(R19); + dwarf_regs[20] = REG(R20); + dwarf_regs[21] = REG(R21); + dwarf_regs[22] = REG(R22); + dwarf_regs[23] = REG(R23); + dwarf_regs[24] = REG(R24); + dwarf_regs[25] = REG(R25); + dwarf_regs[26] = REG(R26); + dwarf_regs[27] = REG(R27); + dwarf_regs[28] = REG(R28); + dwarf_regs[29] = REG(R29); + dwarf_regs[30] = REG(R30); + dwarf_regs[31] = REG(R31); + if (!dwfl_thread_state_registers(thread, 0, 32, dwarf_regs)) + return false; + + dwarf_nip = REG(NIP); + dwfl_thread_state_register_pc(thread, dwarf_nip); + for (i = 0; i < ARRAY_SIZE(special_regs); i++) { + Dwarf_Word val = 0; + perf_reg_value(&val, user_regs, special_regs[i][1]); + if (!dwfl_thread_state_registers(thread, + special_regs[i][0], 1, + &val)) + return false; + } + + return true; +} diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c new file mode 100644 index 000000000000..745b4b1b8b21 --- /dev/null +++ b/tools/perf/arch/s390/annotate/instructions.c @@ -0,0 +1,30 @@ +static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name) +{ + struct ins_ops *ops = NULL; + + /* catch all kind of jumps */ + if (strchr(name, 'j') || + !strncmp(name, "bct", 3) || + !strncmp(name, "br", 2)) + ops = &jump_ops; + /* override call/returns */ + if (!strcmp(name, "bras") || + !strcmp(name, "brasl") || + !strcmp(name, "basr")) + ops = &call_ops; + if (!strcmp(name, "br")) + ops = &ret_ops; + + arch__associate_ins_ops(arch, name, ops); + return ops; +} + +static int s390__annotate_init(struct arch *arch) +{ + if (!arch->initialized) { + arch->initialized = true; + arch->associate_instruction_ops = s390__associate_ins_ops; + } + + return 0; +} diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c index ed57df2e6d68..d233e2eb9592 100644 --- a/tools/perf/arch/s390/util/kvm-stat.c +++ b/tools/perf/arch/s390/util/kvm-stat.c @@ -9,6 +9,7 @@ * as published by the Free Software Foundation. */ +#include <errno.h> #include "../../util/kvm-stat.h" #include <asm/sie.h> diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index e93ef0b38db8..5aef183e2f85 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -338,6 +338,7 @@ 329 common pkey_mprotect sys_pkey_mprotect 330 common pkey_alloc sys_pkey_alloc 331 common pkey_free sys_pkey_free +332 common statx sys_statx # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c index 0f196eec9f48..3cbf6fad169f 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c @@ -1664,3 +1664,15 @@ "0f c7 1d 78 56 34 12 \txrstors 0x12345678",}, {{0x0f, 0xc7, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", "0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%eax,%ecx,8)",}, +{{0xf3, 0x0f, 0xae, 0x20, }, 4, 0, "", "", +"f3 0f ae 20 \tptwritel (%eax)",}, +{{0xf3, 0x0f, 0xae, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"f3 0f ae 25 78 56 34 12 \tptwritel 0x12345678",}, +{{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%eax,%ecx,8)",}, +{{0xf3, 0x0f, 0xae, 0x20, }, 4, 0, "", "", +"f3 0f ae 20 \tptwritel (%eax)",}, +{{0xf3, 0x0f, 0xae, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"f3 0f ae 25 78 56 34 12 \tptwritel 0x12345678",}, +{{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%eax,%ecx,8)",}, diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c index af25bc8240d0..aa512fa944dd 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c @@ -1696,3 +1696,33 @@ "0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%rax,%rcx,8)",}, {{0x41, 0x0f, 0xc7, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", "41 0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%r8,%rcx,8)",}, +{{0xf3, 0x0f, 0xae, 0x20, }, 4, 0, "", "", +"f3 0f ae 20 \tptwritel (%rax)",}, +{{0xf3, 0x41, 0x0f, 0xae, 0x20, }, 5, 0, "", "", +"f3 41 0f ae 20 \tptwritel (%r8)",}, +{{0xf3, 0x0f, 0xae, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae 24 25 78 56 34 12 \tptwritel 0x12345678",}, +{{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%rax,%rcx,8)",}, +{{0xf3, 0x41, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 41 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%r8,%rcx,8)",}, +{{0xf3, 0x0f, 0xae, 0x20, }, 4, 0, "", "", +"f3 0f ae 20 \tptwritel (%rax)",}, +{{0xf3, 0x41, 0x0f, 0xae, 0x20, }, 5, 0, "", "", +"f3 41 0f ae 20 \tptwritel (%r8)",}, +{{0xf3, 0x0f, 0xae, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae 24 25 78 56 34 12 \tptwritel 0x12345678",}, +{{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%rax,%rcx,8)",}, +{{0xf3, 0x41, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 41 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%r8,%rcx,8)",}, +{{0xf3, 0x48, 0x0f, 0xae, 0x20, }, 5, 0, "", "", +"f3 48 0f ae 20 \tptwriteq (%rax)",}, +{{0xf3, 0x49, 0x0f, 0xae, 0x20, }, 5, 0, "", "", +"f3 49 0f ae 20 \tptwriteq (%r8)",}, +{{0xf3, 0x48, 0x0f, 0xae, 0x24, 0x25, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 48 0f ae 24 25 78 56 34 12 \tptwriteq 0x12345678",}, +{{0xf3, 0x48, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 48 0f ae a4 c8 78 56 34 12 \tptwriteq 0x12345678(%rax,%rcx,8)",}, +{{0xf3, 0x49, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"f3 49 0f ae a4 c8 78 56 34 12 \tptwriteq 0x12345678(%r8,%rcx,8)",}, diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c index 979487dae8d4..6cdb65d25b79 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c @@ -1343,6 +1343,26 @@ int main(void) asm volatile("xrstors 0x12345678(%rax,%rcx,8)"); asm volatile("xrstors 0x12345678(%r8,%rcx,8)"); + /* ptwrite */ + + asm volatile("ptwrite (%rax)"); + asm volatile("ptwrite (%r8)"); + asm volatile("ptwrite (0x12345678)"); + asm volatile("ptwrite 0x12345678(%rax,%rcx,8)"); + asm volatile("ptwrite 0x12345678(%r8,%rcx,8)"); + + asm volatile("ptwritel (%rax)"); + asm volatile("ptwritel (%r8)"); + asm volatile("ptwritel (0x12345678)"); + asm volatile("ptwritel 0x12345678(%rax,%rcx,8)"); + asm volatile("ptwritel 0x12345678(%r8,%rcx,8)"); + + asm volatile("ptwriteq (%rax)"); + asm volatile("ptwriteq (%r8)"); + asm volatile("ptwriteq (0x12345678)"); + asm volatile("ptwriteq 0x12345678(%rax,%rcx,8)"); + asm volatile("ptwriteq 0x12345678(%r8,%rcx,8)"); + #else /* #ifdef __x86_64__ */ /* bound r32, mem (same op code as EVEX prefix) */ @@ -2653,6 +2673,16 @@ int main(void) asm volatile("xrstors (0x12345678)"); asm volatile("xrstors 0x12345678(%eax,%ecx,8)"); + /* ptwrite */ + + asm volatile("ptwrite (%eax)"); + asm volatile("ptwrite (0x12345678)"); + asm volatile("ptwrite 0x12345678(%eax,%ecx,8)"); + + asm volatile("ptwritel (%eax)"); + asm volatile("ptwritel (0x12345678)"); + asm volatile("ptwritel 0x12345678(%eax,%ecx,8)"); + #endif /* #ifndef __x86_64__ */ /* Following line is a marker for the awk script - do not change */ diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 7f064eb37158..f9713a71d77e 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -6,7 +6,10 @@ #include "evsel.h" #include "arch-tests.h" +#include <signal.h> #include <sys/mman.h> +#include <sys/wait.h> +#include <errno.h> #include <string.h> static pid_t spawn(void) diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index 5c76cc83186a..e3ae9cff2b67 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> #include <stdio.h> #include <unistd.h> #include <linux/types.h> diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c index cc1d865e31f1..6aa3f2a38321 100644 --- a/tools/perf/arch/x86/util/auxtrace.c +++ b/tools/perf/arch/x86/util/auxtrace.c @@ -13,6 +13,7 @@ * */ +#include <errno.h> #include <stdbool.h> #include "../../util/header.h" diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 5132775a044f..781df40b2966 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -13,6 +13,7 @@ * */ +#include <errno.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/bitops.h> @@ -34,10 +35,6 @@ #define KiB_MASK(x) (KiB(x) - 1) #define MiB_MASK(x) (MiB(x) - 1) -#define INTEL_BTS_DFLT_SAMPLE_SIZE KiB(4) - -#define INTEL_BTS_MAX_SAMPLE_SIZE KiB(60) - struct intel_bts_snapshot_ref { void *ref_buf; size_t ref_offset; diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 90fa2286edcf..9535be57033f 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -13,6 +13,7 @@ * */ +#include <errno.h> #include <stdbool.h> #include <linux/kernel.h> #include <linux/types.h> @@ -39,10 +40,6 @@ #define KiB_MASK(x) (KiB(x) - 1) #define MiB_MASK(x) (MiB(x) - 1) -#define INTEL_PT_DEFAULT_SAMPLE_SIZE KiB(4) - -#define INTEL_PT_MAX_SAMPLE_SIZE KiB(60) - #define INTEL_PT_PSB_PERIOD_NEAR 256 struct intel_pt_snapshot_ref { @@ -195,6 +192,7 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) int psb_cyc, psb_periods, psb_period; int pos = 0; u64 config; + char c; pos += scnprintf(buf + pos, sizeof(buf) - pos, "tsc"); @@ -228,6 +226,10 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) } } + if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 && + perf_pmu__scan_file(intel_pt_pmu, "format/branch", "%c", &c) == 1) + pos += scnprintf(buf + pos, sizeof(buf) - pos, ",pt,branch"); + pr_debug2("%s default config: %s\n", intel_pt_pmu->name, buf); intel_pt_parse_terms(&intel_pt_pmu->format, buf, &config); diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c index b63d4be655a2..bf817beca0a8 100644 --- a/tools/perf/arch/x86/util/kvm-stat.c +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -1,3 +1,4 @@ +#include <errno.h> #include "../../util/kvm-stat.h" #include <asm/svm.h> #include <asm/vmx.h> diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index c5db14f36cc7..f95edebfb716 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -1,5 +1,11 @@ +#include <errno.h> +#include <string.h> +#include <regex.h> + #include "../../perf.h" +#include "../../util/util.h" #include "../../util/perf_regs.h" +#include "../../util/debug.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG(AX, PERF_REG_X86_AX), @@ -26,3 +32,224 @@ const struct sample_reg sample_reg_masks[] = { #endif SMPL_REG_END }; + +struct sdt_name_reg { + const char *sdt_name; + const char *uprobe_name; +}; +#define SDT_NAME_REG(n, m) {.sdt_name = "%" #n, .uprobe_name = "%" #m} +#define SDT_NAME_REG_END {.sdt_name = NULL, .uprobe_name = NULL} + +static const struct sdt_name_reg sdt_reg_tbl[] = { + SDT_NAME_REG(eax, ax), + SDT_NAME_REG(rax, ax), + SDT_NAME_REG(al, ax), + SDT_NAME_REG(ah, ax), + SDT_NAME_REG(ebx, bx), + SDT_NAME_REG(rbx, bx), + SDT_NAME_REG(bl, bx), + SDT_NAME_REG(bh, bx), + SDT_NAME_REG(ecx, cx), + SDT_NAME_REG(rcx, cx), + SDT_NAME_REG(cl, cx), + SDT_NAME_REG(ch, cx), + SDT_NAME_REG(edx, dx), + SDT_NAME_REG(rdx, dx), + SDT_NAME_REG(dl, dx), + SDT_NAME_REG(dh, dx), + SDT_NAME_REG(esi, si), + SDT_NAME_REG(rsi, si), + SDT_NAME_REG(sil, si), + SDT_NAME_REG(edi, di), + SDT_NAME_REG(rdi, di), + SDT_NAME_REG(dil, di), + SDT_NAME_REG(ebp, bp), + SDT_NAME_REG(rbp, bp), + SDT_NAME_REG(bpl, bp), + SDT_NAME_REG(rsp, sp), + SDT_NAME_REG(esp, sp), + SDT_NAME_REG(spl, sp), + + /* rNN registers */ + SDT_NAME_REG(r8b, r8), + SDT_NAME_REG(r8w, r8), + SDT_NAME_REG(r8d, r8), + SDT_NAME_REG(r9b, r9), + SDT_NAME_REG(r9w, r9), + SDT_NAME_REG(r9d, r9), + SDT_NAME_REG(r10b, r10), + SDT_NAME_REG(r10w, r10), + SDT_NAME_REG(r10d, r10), + SDT_NAME_REG(r11b, r11), + SDT_NAME_REG(r11w, r11), + SDT_NAME_REG(r11d, r11), + SDT_NAME_REG(r12b, r12), + SDT_NAME_REG(r12w, r12), + SDT_NAME_REG(r12d, r12), + SDT_NAME_REG(r13b, r13), + SDT_NAME_REG(r13w, r13), + SDT_NAME_REG(r13d, r13), + SDT_NAME_REG(r14b, r14), + SDT_NAME_REG(r14w, r14), + SDT_NAME_REG(r14d, r14), + SDT_NAME_REG(r15b, r15), + SDT_NAME_REG(r15w, r15), + SDT_NAME_REG(r15d, r15), + SDT_NAME_REG_END, +}; + +/* + * Perf only supports OP which is in +/-NUM(REG) form. + * Here plus-minus sign, NUM and parenthesis are optional, + * only REG is mandatory. + * + * SDT events also supports indirect addressing mode with a + * symbol as offset, scaled mode and constants in OP. But + * perf does not support them yet. Below are few examples. + * + * OP with scaled mode: + * (%rax,%rsi,8) + * 10(%ras,%rsi,8) + * + * OP with indirect addressing mode: + * check_action(%rip) + * mp_+52(%rip) + * 44+mp_(%rip) + * + * OP with constant values: + * $0 + * $123 + * $-1 + */ +#define SDT_OP_REGEX "^([+\\-]?)([0-9]*)(\\(?)(%[a-z][a-z0-9]+)(\\)?)$" + +static regex_t sdt_op_regex; + +static int sdt_init_op_regex(void) +{ + static int initialized; + int ret = 0; + + if (initialized) + return 0; + + ret = regcomp(&sdt_op_regex, SDT_OP_REGEX, REG_EXTENDED); + if (ret < 0) { + pr_debug4("Regex compilation error.\n"); + return ret; + } + + initialized = 1; + return 0; +} + +/* + * Max x86 register name length is 5(ex: %r15d). So, 6th char + * should always contain NULL. This helps to find register name + * length using strlen, insted of maintaing one more variable. + */ +#define SDT_REG_NAME_SIZE 6 + +/* + * The uprobe parser does not support all gas register names; + * so, we have to replace them (ex. for x86_64: %rax -> %ax). + * Note: If register does not require renaming, just copy + * paste as it is, but don't leave it empty. + */ +static void sdt_rename_register(char *sdt_reg, int sdt_len, char *uprobe_reg) +{ + int i = 0; + + for (i = 0; sdt_reg_tbl[i].sdt_name != NULL; i++) { + if (!strncmp(sdt_reg_tbl[i].sdt_name, sdt_reg, sdt_len)) { + strcpy(uprobe_reg, sdt_reg_tbl[i].uprobe_name); + return; + } + } + + strncpy(uprobe_reg, sdt_reg, sdt_len); +} + +int arch_sdt_arg_parse_op(char *old_op, char **new_op) +{ + char new_reg[SDT_REG_NAME_SIZE] = {0}; + int new_len = 0, ret; + /* + * rm[0]: +/-NUM(REG) + * rm[1]: +/- + * rm[2]: NUM + * rm[3]: ( + * rm[4]: REG + * rm[5]: ) + */ + regmatch_t rm[6]; + /* + * Max prefix length is 2 as it may contains sign(+/-) + * and displacement 0 (Both sign and displacement 0 are + * optional so it may be empty). Use one more character + * to hold last NULL so that strlen can be used to find + * prefix length, instead of maintaing one more variable. + */ + char prefix[3] = {0}; + + ret = sdt_init_op_regex(); + if (ret < 0) + return ret; + + /* + * If unsupported OR does not match with regex OR + * register name too long, skip it. + */ + if (strchr(old_op, ',') || strchr(old_op, '$') || + regexec(&sdt_op_regex, old_op, 6, rm, 0) || + rm[4].rm_eo - rm[4].rm_so > SDT_REG_NAME_SIZE) { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + /* + * Prepare prefix. + * If SDT OP has parenthesis but does not provide + * displacement, add 0 for displacement. + * SDT Uprobe Prefix + * ----------------------------- + * +24(%rdi) +24(%di) + + * 24(%rdi) +24(%di) + + * %rdi %di + * (%rdi) +0(%di) +0 + * -80(%rbx) -80(%bx) - + */ + if (rm[3].rm_so != rm[3].rm_eo) { + if (rm[1].rm_so != rm[1].rm_eo) + prefix[0] = *(old_op + rm[1].rm_so); + else if (rm[2].rm_so != rm[2].rm_eo) + prefix[0] = '+'; + else + strncpy(prefix, "+0", 2); + } + + /* Rename register */ + sdt_rename_register(old_op + rm[4].rm_so, rm[4].rm_eo - rm[4].rm_so, + new_reg); + + /* Prepare final OP which should be valid for uprobe_events */ + new_len = strlen(prefix) + + (rm[2].rm_eo - rm[2].rm_so) + + (rm[3].rm_eo - rm[3].rm_so) + + strlen(new_reg) + + (rm[5].rm_eo - rm[5].rm_so) + + 1; /* NULL */ + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%.*s%.*s%.*s%.*s%.*s", + strlen(prefix), prefix, + (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so, + (int)(rm[3].rm_eo - rm[3].rm_so), old_op + rm[3].rm_so, + strlen(new_reg), new_reg, + (int)(rm[5].rm_eo - rm[5].rm_so), old_op + rm[5].rm_so); + + return SDT_ARG_VALID; +} diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c index c4b72176ca83..38dc9bb2a7c9 100644 --- a/tools/perf/arch/x86/util/unwind-libdw.c +++ b/tools/perf/arch/x86/util/unwind-libdw.c @@ -1,6 +1,7 @@ #include <elfutils/libdwfl.h> #include "../../util/unwind-libdw.h" #include "../../util/perf_regs.h" +#include "../../util/event.h" bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index 579a592990dd..842ab2781cdc 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -25,17 +25,17 @@ # endif #endif -int bench_numa(int argc, const char **argv, const char *prefix); -int bench_sched_messaging(int argc, const char **argv, const char *prefix); -int bench_sched_pipe(int argc, const char **argv, const char *prefix); -int bench_mem_memcpy(int argc, const char **argv, const char *prefix); -int bench_mem_memset(int argc, const char **argv, const char *prefix); -int bench_futex_hash(int argc, const char **argv, const char *prefix); -int bench_futex_wake(int argc, const char **argv, const char *prefix); -int bench_futex_wake_parallel(int argc, const char **argv, const char *prefix); -int bench_futex_requeue(int argc, const char **argv, const char *prefix); +int bench_numa(int argc, const char **argv); +int bench_sched_messaging(int argc, const char **argv); +int bench_sched_pipe(int argc, const char **argv); +int bench_mem_memcpy(int argc, const char **argv); +int bench_mem_memset(int argc, const char **argv); +int bench_futex_hash(int argc, const char **argv); +int bench_futex_wake(int argc, const char **argv); +int bench_futex_wake_parallel(int argc, const char **argv); +int bench_futex_requeue(int argc, const char **argv); /* pi futexes */ -int bench_futex_lock_pi(int argc, const char **argv, const char *prefix); +int bench_futex_lock_pi(int argc, const char **argv); #define BENCH_FORMAT_DEFAULT_STR "default" #define BENCH_FORMAT_DEFAULT 0 diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index bfbb6b5f609c..fe16b310097f 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -9,6 +9,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <errno.h> @@ -113,8 +114,7 @@ static void print_summary(void) (int) runtime.tv_sec); } -int bench_futex_hash(int argc, const char **argv, - const char *prefix __maybe_unused) +int bench_futex_hash(int argc, const char **argv) { int ret = 0; cpu_set_t cpu; @@ -130,8 +130,6 @@ int bench_futex_hash(int argc, const char **argv, } ncpus = sysconf(_SC_NPROCESSORS_ONLN); - nsecs = futexbench_sanitize_numeric(nsecs); - nfutexes = futexbench_sanitize_numeric(nfutexes); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; @@ -139,8 +137,6 @@ int bench_futex_hash(int argc, const char **argv, if (!nthreads) /* default to the number of CPUs */ nthreads = ncpus; - else - nthreads = futexbench_sanitize_numeric(nthreads); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 6d9d6c40a916..73a1c44ea63c 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -3,6 +3,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <signal.h> @@ -139,8 +140,7 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr) } } -int bench_futex_lock_pi(int argc, const char **argv, - const char *prefix __maybe_unused) +int bench_futex_lock_pi(int argc, const char **argv) { int ret = 0; unsigned int i; @@ -152,7 +152,6 @@ int bench_futex_lock_pi(int argc, const char **argv, goto err; ncpus = sysconf(_SC_NPROCESSORS_ONLN); - nsecs = futexbench_sanitize_numeric(nsecs); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; @@ -160,8 +159,6 @@ int bench_futex_lock_pi(int argc, const char **argv, if (!nthreads) nthreads = ncpus; - else - nthreads = futexbench_sanitize_numeric(nthreads); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index fd4ee95b689a..41786cbea24c 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -9,6 +9,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <signal.h> @@ -108,8 +109,7 @@ static void toggle_done(int sig __maybe_unused, done = true; } -int bench_futex_requeue(int argc, const char **argv, - const char *prefix __maybe_unused) +int bench_futex_requeue(int argc, const char **argv) { int ret = 0; unsigned int i, j; @@ -128,8 +128,6 @@ int bench_futex_requeue(int argc, const char **argv, if (!nthreads) nthreads = ncpus; - else - nthreads = futexbench_sanitize_numeric(nthreads); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index beaa6c142477..4ab12c8e016a 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -8,6 +8,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <signal.h> @@ -196,8 +197,7 @@ static void toggle_done(int sig __maybe_unused, done = true; } -int bench_futex_wake_parallel(int argc, const char **argv, - const char *prefix __maybe_unused) +int bench_futex_wake_parallel(int argc, const char **argv) { int ret = 0; unsigned int i, j; @@ -217,12 +217,8 @@ int bench_futex_wake_parallel(int argc, const char **argv, sigaction(SIGINT, &act, NULL); ncpus = sysconf(_SC_NPROCESSORS_ONLN); - nwaking_threads = futexbench_sanitize_numeric(nwaking_threads); - if (!nblocked_threads) nblocked_threads = ncpus; - else - nblocked_threads = futexbench_sanitize_numeric(nblocked_threads); /* some sanity checks */ if (nwaking_threads > nblocked_threads || !nwaking_threads) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index 46efcb98b5a4..2fa49222ef8d 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -9,6 +9,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <signal.h> @@ -114,8 +115,7 @@ static void toggle_done(int sig __maybe_unused, done = true; } -int bench_futex_wake(int argc, const char **argv, - const char *prefix __maybe_unused) +int bench_futex_wake(int argc, const char **argv) { int ret = 0; unsigned int i, j; @@ -129,7 +129,6 @@ int bench_futex_wake(int argc, const char **argv, } ncpus = sysconf(_SC_NPROCESSORS_ONLN); - nwakes = futexbench_sanitize_numeric(nwakes); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; @@ -137,8 +136,6 @@ int bench_futex_wake(int argc, const char **argv, if (!nthreads) nthreads = ncpus; - else - nthreads = futexbench_sanitize_numeric(nthreads); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h index ba7c735c0c62..e44fd3239530 100644 --- a/tools/perf/bench/futex.h +++ b/tools/perf/bench/futex.h @@ -7,7 +7,6 @@ #ifndef _FUTEX_H #define _FUTEX_H -#include <stdlib.h> #include <unistd.h> #include <sys/syscall.h> #include <sys/types.h> @@ -89,18 +88,13 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak #ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP #include <pthread.h> -static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr, - size_t cpusetsize, - cpu_set_t *cpuset) +#include <linux/compiler.h> +static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused, + size_t cpusetsize __maybe_unused, + cpu_set_t *cpuset __maybe_unused) { - attr = attr; - cpusetsize = cpusetsize; - cpuset = cpuset; return 0; } #endif -/* User input sanitation */ -#define futexbench_sanitize_numeric(__n) abs((__n)) - #endif /* _FUTEX_H */ diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c index 52504a83b5a1..fbd732b54047 100644 --- a/tools/perf/bench/mem-functions.c +++ b/tools/perf/bench/mem-functions.c @@ -12,6 +12,7 @@ #include <subcmd/parse-options.h> #include "../util/header.h" #include "../util/cloexec.h" +#include "../util/string2.h" #include "bench.h" #include "mem-memcpy-arch.h" #include "mem-memset-arch.h" @@ -284,7 +285,7 @@ static const char * const bench_mem_memcpy_usage[] = { NULL }; -int bench_mem_memcpy(int argc, const char **argv, const char *prefix __maybe_unused) +int bench_mem_memcpy(int argc, const char **argv) { struct bench_mem_info info = { .functions = memcpy_functions, @@ -358,7 +359,7 @@ static const struct function memset_functions[] = { { .name = NULL, } }; -int bench_mem_memset(int argc, const char **argv, const char *prefix __maybe_unused) +int bench_mem_memset(int argc, const char **argv) { struct bench_mem_info info = { .functions = memset_functions, diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 8efe904e486b..469d65b21122 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -4,6 +4,7 @@ * numa: Simulate NUMA-sensitive workload and measure their NUMA performance */ +#include <inttypes.h> /* For the CLR_() macros */ #include <pthread.h> @@ -30,6 +31,7 @@ #include <sys/wait.h> #include <sys/prctl.h> #include <sys/types.h> +#include <linux/kernel.h> #include <linux/time64.h> #include <numa.h> @@ -43,6 +45,7 @@ /* * Debug printf: */ +#undef dprintf #define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0) struct thread_data { @@ -186,7 +189,8 @@ static const struct option options[] = { OPT_INCR ('d', "show_details" , &p0.show_details, "Show details"), OPT_INCR ('a', "all" , &p0.run_all, "Run all tests in the suite"), OPT_INTEGER('H', "thp" , &p0.thp, "MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"), - OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"), + OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details, " + "convergence is reached when each process (all its threads) is running on a single NUMA node."), OPT_BOOLEAN('m', "measure_convergence", &p0.measure_convergence, "measure convergence latency"), OPT_BOOLEAN('q', "quiet" , &p0.show_quiet, "quiet mode"), OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"), @@ -696,7 +700,7 @@ static inline uint32_t lfsr_32(uint32_t lfsr) * kernel (KSM, zero page, etc.) cannot optimize away RAM * accesses: */ -static inline u64 access_data(u64 *data __attribute__((unused)), u64 val) +static inline u64 access_data(u64 *data, u64 val) { if (g->p.data_reads) val += *data; @@ -1573,13 +1577,13 @@ static int __bench_numa(const char *name) "GB/sec,", "total-speed", "GB/sec total speed"); if (g->p.show_details >= 2) { - char tname[32]; + char tname[14 + 2 * 10 + 1]; struct thread_data *td; for (p = 0; p < g->p.nr_proc; p++) { for (t = 0; t < g->p.nr_threads; t++) { - memset(tname, 0, 32); + memset(tname, 0, sizeof(tname)); td = g->threads + p*g->p.nr_threads + t; - snprintf(tname, 32, "process%d:thread%d", p, t); + snprintf(tname, sizeof(tname), "process%d:thread%d", p, t); print_res(tname, td->speed_gbs, "GB/sec", "thread-speed", "GB/sec/thread speed"); print_res(tname, td->system_time_ns / NSEC_PER_SEC, @@ -1765,7 +1769,7 @@ static int bench_all(void) return 0; } -int bench_numa(int argc, const char **argv, const char *prefix __maybe_unused) +int bench_numa(int argc, const char **argv) { init_params(&p0, "main,", argc, argv); argc = parse_options(argc, argv, options, bench_numa_usage, 0); diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c index 6a111e775210..4f961e74535b 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -260,8 +260,7 @@ static const char * const bench_sched_message_usage[] = { NULL }; -int bench_sched_messaging(int argc, const char **argv, - const char *prefix __maybe_unused) +int bench_sched_messaging(int argc, const char **argv) { unsigned int i, total_children; struct timeval start, stop, diff; diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index 2243f0150d76..a152737370c5 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -76,7 +76,7 @@ static void *worker_thread(void *__tdata) return NULL; } -int bench_sched_pipe(int argc, const char **argv, const char *prefix __maybe_unused) +int bench_sched_pipe(int argc, const char **argv) { struct thread_data threads[2], *td; int pipe_1[2], pipe_2[2]; diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index ebb628332a6e..7a5dc7e5c577 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -33,6 +33,7 @@ #include "util/block-range.h" #include <dlfcn.h> +#include <errno.h> #include <linux/bitmap.h> struct perf_annotate { @@ -383,7 +384,7 @@ static const char * const annotate_usage[] = { NULL }; -int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_annotate(int argc, const char **argv) { struct perf_annotate annotate = { .tool = { @@ -393,6 +394,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) .comm = perf_event__process_comm, .exit = perf_event__process_exit, .fork = perf_event__process_fork, + .namespaces = perf_event__process_namespaces, + .attr = perf_event__process_attr, + .build_id = perf_event__process_build_id, .ordered_events = true, .ordering_requires_timestamps = true, }, @@ -410,6 +414,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('q', "quiet", &quiet, "do now show any message"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"), @@ -463,6 +468,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) annotate.sym_hist_filter = argv[0]; } + if (quiet) + perf_quiet_option(); + file.path = input_name; annotate.session = perf_session__new(&file, false, &annotate.tool); diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index a1cddc6bbf0f..445e62881254 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -25,7 +25,7 @@ #include <string.h> #include <sys/prctl.h> -typedef int (*bench_fn_t)(int argc, const char **argv, const char *prefix); +typedef int (*bench_fn_t)(int argc, const char **argv); struct bench { const char *name; @@ -155,7 +155,7 @@ static int bench_str2int(const char *str) * 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 argc, const char **argv) { int size; char *name; @@ -171,7 +171,7 @@ static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t f prctl(PR_SET_NAME, name); argv[0] = name; - ret = fn(argc, argv, prefix); + ret = fn(argc, argv); free(name); @@ -198,7 +198,7 @@ static void run_collection(struct collection *coll) fflush(stdout); argv[1] = bench->name; - run_bench(coll->name, bench->name, bench->fn, 1, argv, NULL); + run_bench(coll->name, bench->name, bench->fn, 1, argv); printf("\n"); } } @@ -211,7 +211,7 @@ static void run_all_collections(void) run_collection(coll); } -int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_bench(int argc, const char **argv) { struct collection *coll; int ret = 0; @@ -270,7 +270,7 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused) if (bench_format == BENCH_FORMAT_DEFAULT) printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name); fflush(stdout); - ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1, prefix); + ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1); goto end; } diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 30e2b2cb2421..9eba7f1add1f 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -10,6 +10,7 @@ #include <sys/time.h> #include <time.h> #include <dirent.h> +#include <errno.h> #include <unistd.h> #include "builtin.h" #include "perf.h" @@ -21,6 +22,7 @@ #include "util/build-id.h" #include "util/session.h" #include "util/symbol.h" +#include "util/time-utils.h" static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid) { @@ -47,19 +49,22 @@ static bool same_kallsyms_reloc(const char *from_dir, char *to_dir) char to[PATH_MAX]; const char *name; u64 addr1 = 0, addr2 = 0; - int i; + int i, err = -1; scnprintf(from, sizeof(from), "%s/kallsyms", from_dir); scnprintf(to, sizeof(to), "%s/kallsyms", to_dir); for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { - addr1 = kallsyms__get_function_start(from, name); - if (addr1) + err = kallsyms__get_function_start(from, name, &addr1); + if (!err) break; } - if (name) - addr2 = kallsyms__get_function_start(to, name); + if (err) + return false; + + if (kallsyms__get_function_start(to, name, &addr2)) + return false; return addr1 == addr2; } @@ -276,8 +281,7 @@ static int build_id_cache__update_file(const char *filename) return err; } -int cmd_buildid_cache(int argc, const char **argv, - const char *prefix __maybe_unused) +int cmd_buildid_cache(int argc, const char **argv) { struct strlist *list; struct str_node *pos; diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 5e914ee79eb3..fdaca16e0c74 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -16,6 +16,7 @@ #include "util/session.h" #include "util/symbol.h" #include "util/data.h" +#include <errno.h> static int sysfs__fprintf_build_id(FILE *fp) { @@ -87,8 +88,7 @@ out: return 0; } -int cmd_buildid_list(int argc, const char **argv, - const char *prefix __maybe_unused) +int cmd_buildid_list(int argc, const char **argv) { bool show_kernel = false; bool with_hits = false; diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index f8ca7a4ebabc..475999e48f66 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -9,10 +9,13 @@ * Dick Fowles <fowles@inreach.com> * Joe Mario <jmario@redhat.com> */ +#include <errno.h> +#include <inttypes.h> #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/stringify.h> #include <asm/bug.h> +#include <sys/param.h> #include "util.h" #include "debug.h" #include "builtin.h" @@ -24,11 +27,13 @@ #include "tool.h" #include "data.h" #include "sort.h" +#include "event.h" #include "evlist.h" #include "evsel.h" #include <asm/bug.h> #include "ui/browsers/hists.h" #include "evlist.h" +#include "thread.h" struct c2c_hists { struct hists hists; @@ -58,7 +63,7 @@ struct c2c_hist_entry { struct hist_entry he; }; -static char const *coalesce_default = "pid,tid,iaddr"; +static char const *coalesce_default = "pid,iaddr"; struct perf_c2c { struct perf_tool tool; @@ -1720,10 +1725,10 @@ static int c2c_hists__init_sort(struct perf_hpp_list *hpp_list, char *name) tok; tok = strtok_r(NULL, ", ", &tmp)) { \ ret = _fn(hpp_list, tok); \ if (ret == -EINVAL) { \ - error("Invalid --fields key: `%s'", tok); \ + pr_err("Invalid --fields key: `%s'", tok); \ break; \ } else if (ret == -ESRCH) { \ - error("Unknown --fields key: `%s'", tok); \ + pr_err("Unknown --fields key: `%s'", tok); \ break; \ } \ } \ @@ -2334,7 +2339,7 @@ out: static void perf_c2c_display(struct perf_session *session) { - if (c2c.use_stdio) + if (use_browser == 0) perf_c2c__hists_fprintf(stdout, session); else perf_c2c__hists_browse(&c2c.hists.hists); @@ -2476,6 +2481,7 @@ static int build_cl_output(char *cl_sort, bool no_source) "mean_rmt," "mean_lcl," "mean_load," + "tot_recs," "cpucnt,", add_sym ? "symbol," : "", add_dso ? "dso," : "", @@ -2535,7 +2541,7 @@ static int perf_c2c__report(int argc, const char **argv) OPT_BOOLEAN(0, "stdio", &c2c.use_stdio, "Use the stdio interface"), #endif OPT_BOOLEAN(0, "stats", &c2c.stats_only, - "Use the stdio interface"), + "Display only statistic tables (implies --stdio)"), OPT_BOOLEAN(0, "full-symbols", &c2c.symbol_full, "Display full length of symbols"), OPT_BOOLEAN(0, "no-source", &no_source, @@ -2754,12 +2760,12 @@ static int perf_c2c__record(int argc, const char **argv) pr_debug("\n"); } - ret = cmd_record(i, rec_argv, NULL); + ret = cmd_record(i, rec_argv); free(rec_argv); return ret; } -int cmd_c2c(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_c2c(int argc, const char **argv) { argc = parse_options(argc, argv, c2c_options, c2c_usage, PARSE_OPT_STOP_AT_NON_OPTION); diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c index 8c0d93b7c2f0..ece45582a48d 100644 --- a/tools/perf/builtin-config.c +++ b/tools/perf/builtin-config.c @@ -154,11 +154,12 @@ static int parse_config_arg(char *arg, char **var, char **value) return 0; } -int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_config(int argc, const char **argv) { - int i, ret = 0; + int i, ret = -1; struct perf_config_set *set; char *user_config = mkpath("%s/.perfconfig", getenv("HOME")); + const char *config_filename; argc = parse_options(argc, argv, config_options, config_usage, PARSE_OPT_STOP_AT_NON_OPTION); @@ -175,15 +176,18 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) else if (use_user_config) config_exclusive_filename = user_config; + if (!config_exclusive_filename) + config_filename = user_config; + else + config_filename = config_exclusive_filename; + /* * At only 'config' sub-command, individually use the config set * because of reinitializing with options config file location. */ set = perf_config_set__new(); - if (!set) { - ret = -1; + if (!set) goto out_err; - } switch (actions) { case ACTION_LIST: @@ -191,50 +195,54 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) pr_err("Error: takes no arguments\n"); parse_options_usage(config_usage, config_options, "l", 1); } else { - ret = show_config(set); - if (ret < 0) { - const char * config_filename = config_exclusive_filename; - if (!config_exclusive_filename) - config_filename = user_config; + if (show_config(set) < 0) { pr_err("Nothing configured, " "please check your %s \n", config_filename); + goto out_err; } } break; default: - if (argc) { - for (i = 0; argv[i]; i++) { - char *var, *value; - char *arg = strdup(argv[i]); - - if (!arg) { - pr_err("%s: strdup failed\n", __func__); - ret = -1; - break; - } + if (!argc) { + usage_with_options(config_usage, config_options); + break; + } - if (parse_config_arg(arg, &var, &value) < 0) { - free(arg); - ret = -1; - break; - } + for (i = 0; argv[i]; i++) { + char *var, *value; + char *arg = strdup(argv[i]); - if (value == NULL) - ret = show_spec_config(set, var); - else { - const char *config_filename = config_exclusive_filename; + if (!arg) { + pr_err("%s: strdup failed\n", __func__); + goto out_err; + } - if (!config_exclusive_filename) - config_filename = user_config; - ret = set_config(set, config_filename, var, value); - } + if (parse_config_arg(arg, &var, &value) < 0) { free(arg); + goto out_err; } - } else - usage_with_options(config_usage, config_options); + + if (value == NULL) { + if (show_spec_config(set, var) < 0) { + pr_err("%s is not configured: %s\n", + var, config_filename); + free(arg); + goto out_err; + } + } else { + if (set_config(set, config_filename, var, value) < 0) { + pr_err("Failed to set '%s=%s' on %s\n", + var, value, config_filename); + free(arg); + goto out_err; + } + } + free(arg); + } } - perf_config_set__delete(set); + ret = 0; out_err: + perf_config_set__delete(set); return ret; } diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c index 7ad6e17ac6b3..0adb5f82335a 100644 --- a/tools/perf/builtin-data.c +++ b/tools/perf/builtin-data.c @@ -6,7 +6,7 @@ #include "data-convert.h" #include "data-convert-bt.h" -typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix); +typedef int (*data_cmd_fn_t)(int argc, const char **argv); struct data_cmd { const char *name; @@ -50,8 +50,7 @@ static const char * const data_convert_usage[] = { NULL }; -static int cmd_data_convert(int argc, const char **argv, - const char *prefix __maybe_unused) +static int cmd_data_convert(int argc, const char **argv) { const char *to_ctf = NULL; struct perf_data_convert_opts opts = { @@ -98,7 +97,7 @@ static struct data_cmd data_cmds[] = { { .name = NULL, }, }; -int cmd_data(int argc, const char **argv, const char *prefix) +int cmd_data(int argc, const char **argv) { struct data_cmd *cmd; const char *cmdstr; @@ -118,7 +117,7 @@ int cmd_data(int argc, const char **argv, const char *prefix) if (strcmp(cmd->name, cmdstr)) continue; - return cmd->fn(argc, argv, prefix); + return cmd->fn(argc, argv); } pr_err("Unknown command: %s\n", cmdstr); diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 9ff0db4e2d0c..0cd4cf6a344b 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -17,7 +17,10 @@ #include "util/symbol.h" #include "util/util.h" #include "util/data.h" +#include "util/config.h" +#include <errno.h> +#include <inttypes.h> #include <stdlib.h> #include <math.h> @@ -30,6 +33,7 @@ enum { PERF_HPP_DIFF__RATIO, PERF_HPP_DIFF__WEIGHTED_DIFF, PERF_HPP_DIFF__FORMULA, + PERF_HPP_DIFF__DELTA_ABS, PERF_HPP_DIFF__MAX_INDEX }; @@ -64,7 +68,7 @@ static bool force; static bool show_period; static bool show_formula; static bool show_baseline_only; -static unsigned int sort_compute; +static unsigned int sort_compute = 1; static s64 compute_wdiff_w1; static s64 compute_wdiff_w2; @@ -73,19 +77,22 @@ enum { COMPUTE_DELTA, COMPUTE_RATIO, COMPUTE_WEIGHTED_DIFF, + COMPUTE_DELTA_ABS, COMPUTE_MAX, }; const char *compute_names[COMPUTE_MAX] = { [COMPUTE_DELTA] = "delta", + [COMPUTE_DELTA_ABS] = "delta-abs", [COMPUTE_RATIO] = "ratio", [COMPUTE_WEIGHTED_DIFF] = "wdiff", }; -static int compute; +static int compute = COMPUTE_DELTA_ABS; static int compute_2_hpp[COMPUTE_MAX] = { [COMPUTE_DELTA] = PERF_HPP_DIFF__DELTA, + [COMPUTE_DELTA_ABS] = PERF_HPP_DIFF__DELTA_ABS, [COMPUTE_RATIO] = PERF_HPP_DIFF__RATIO, [COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF, }; @@ -111,6 +118,10 @@ static struct header_column { .name = "Delta", .width = 7, }, + [PERF_HPP_DIFF__DELTA_ABS] = { + .name = "Delta Abs", + .width = 7, + }, [PERF_HPP_DIFF__RATIO] = { .name = "Ratio", .width = 14, @@ -298,6 +309,7 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair, { switch (compute) { case COMPUTE_DELTA: + case COMPUTE_DELTA_ABS: return formula_delta(he, pair, buf, size); case COMPUTE_RATIO: return formula_ratio(he, pair, buf, size); @@ -354,6 +366,7 @@ static struct perf_tool tool = { .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost, + .namespaces = perf_event__process_namespaces, .ordered_events = true, .ordering_requires_timestamps = true, }; @@ -461,6 +474,7 @@ static void hists__precompute(struct hists *hists) switch (compute) { case COMPUTE_DELTA: + case COMPUTE_DELTA_ABS: compute_delta(he, pair); break; case COMPUTE_RATIO: @@ -498,6 +512,13 @@ __hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, return cmp_doubles(l, r); } + case COMPUTE_DELTA_ABS: + { + double l = fabs(left->diff.period_ratio_delta); + double r = fabs(right->diff.period_ratio_delta); + + return cmp_doubles(l, r); + } case COMPUTE_RATIO: { double l = left->diff.period_ratio; @@ -564,7 +585,7 @@ hist_entry__cmp_compute_idx(struct hist_entry *left, struct hist_entry *right, if (!p_left || !p_right) return p_left ? -1 : 1; - if (c != COMPUTE_DELTA) { + if (c != COMPUTE_DELTA && c != COMPUTE_DELTA_ABS) { /* * The delta can be computed without the baseline, but * others are not. Put those entries which have no @@ -607,6 +628,15 @@ hist_entry__cmp_delta(struct perf_hpp_fmt *fmt, } static int64_t +hist_entry__cmp_delta_abs(struct perf_hpp_fmt *fmt, + struct hist_entry *left, struct hist_entry *right) +{ + struct data__file *d = fmt_to_data_file(fmt); + + return hist_entry__cmp_compute(right, left, COMPUTE_DELTA_ABS, d->idx); +} + +static int64_t hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt, struct hist_entry *left, struct hist_entry *right) { @@ -633,6 +663,14 @@ hist_entry__cmp_delta_idx(struct perf_hpp_fmt *fmt __maybe_unused, } static int64_t +hist_entry__cmp_delta_abs_idx(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA_ABS, + sort_compute); +} + +static int64_t hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused, struct hist_entry *left, struct hist_entry *right) { @@ -656,7 +694,7 @@ static void hists__process(struct hists *hists) hists__precompute(hists); hists__output_resort(hists, NULL); - hists__fprintf(hists, true, 0, 0, 0, stdout, + hists__fprintf(hists, !quiet, 0, 0, 0, stdout, symbol_conf.use_callchain); } @@ -704,12 +742,14 @@ static void data_process(void) hists__link(hists_base, hists); } - fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n", - perf_evsel__name(evsel_base)); + if (!quiet) { + fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n", + perf_evsel__name(evsel_base)); + } first = false; - if (verbose || data__files_cnt > 2) + if (verbose > 0 || ((data__files_cnt > 2) && !quiet)) data__fprintf(); /* Don't sort callchain for perf diff */ @@ -772,10 +812,11 @@ static const char * const diff_usage[] = { static const struct option options[] = { OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"), OPT_BOOLEAN('b', "baseline-only", &show_baseline_only, "Show only items with match in baseline"), OPT_CALLBACK('c', "compute", &compute, - "delta,ratio,wdiff:w1,w2 (default delta)", + "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs)", "Entries differential computation selection", setup_compute), OPT_BOOLEAN('p', "period", &show_period, @@ -945,6 +986,7 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair, switch (idx) { case PERF_HPP_DIFF__DELTA: + case PERF_HPP_DIFF__DELTA_ABS: if (pair->diff.computed) diff = pair->diff.period_ratio_delta; else @@ -1118,6 +1160,10 @@ static void data__hpp_register(struct data__file *d, int idx) fmt->color = hpp__color_wdiff; fmt->sort = hist_entry__cmp_wdiff; break; + case PERF_HPP_DIFF__DELTA_ABS: + fmt->color = hpp__color_delta; + fmt->sort = hist_entry__cmp_delta_abs; + break; default: fmt->sort = hist_entry__cmp_nop; break; @@ -1195,11 +1241,14 @@ static int ui_init(void) case COMPUTE_WEIGHTED_DIFF: fmt->sort = hist_entry__cmp_wdiff_idx; break; + case COMPUTE_DELTA_ABS: + fmt->sort = hist_entry__cmp_delta_abs_idx; + break; default: BUG_ON(1); } - perf_hpp__register_sort_field(fmt); + perf_hpp__prepend_sort_field(fmt); return 0; } @@ -1249,15 +1298,48 @@ static int data_init(int argc, const char **argv) return 0; } -int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) +static int diff__config(const char *var, const char *value, + void *cb __maybe_unused) +{ + if (!strcmp(var, "diff.order")) { + int ret; + if (perf_config_int(&ret, var, value) < 0) + return -1; + sort_compute = ret; + return 0; + } + if (!strcmp(var, "diff.compute")) { + if (!strcmp(value, "delta")) { + compute = COMPUTE_DELTA; + } else if (!strcmp(value, "delta-abs")) { + compute = COMPUTE_DELTA_ABS; + } else if (!strcmp(value, "ratio")) { + compute = COMPUTE_RATIO; + } else if (!strcmp(value, "wdiff")) { + compute = COMPUTE_WEIGHTED_DIFF; + } else { + pr_err("Invalid compute method: %s\n", value); + return -1; + } + } + + return 0; +} + +int cmd_diff(int argc, const char **argv) { int ret = hists__init(); if (ret < 0) return ret; + perf_config(diff__config, NULL); + argc = parse_options(argc, argv, options, diff_usage, 0); + if (quiet) + perf_quiet_option(); + if (symbol__init(NULL) < 0) return -1; diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index e09c4287fe87..6d210e40d611 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -46,7 +46,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details return 0; } -int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_evlist(int argc, const char **argv) { struct perf_attr_details details = { .verbose = false, }; const struct option options[] = { diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c new file mode 100644 index 000000000000..dd26c62c9893 --- /dev/null +++ b/tools/perf/builtin-ftrace.c @@ -0,0 +1,507 @@ +/* + * builtin-ftrace.c + * + * Copyright (c) 2013 LG Electronics, Namhyung Kim <namhyung@kernel.org> + * + * Released under the GPL v2. + */ + +#include "builtin.h" +#include "perf.h" + +#include <errno.h> +#include <unistd.h> +#include <signal.h> +#include <fcntl.h> +#include <poll.h> + +#include "debug.h" +#include <subcmd/parse-options.h> +#include <api/fs/tracing_path.h> +#include "evlist.h" +#include "target.h" +#include "cpumap.h" +#include "thread_map.h" +#include "util/config.h" + + +#define DEFAULT_TRACER "function_graph" + +struct perf_ftrace { + struct perf_evlist *evlist; + struct target target; + const char *tracer; + struct list_head filters; + struct list_head notrace; + struct list_head graph_funcs; + struct list_head nograph_funcs; + int graph_depth; +}; + +struct filter_entry { + struct list_head list; + char name[]; +}; + +static bool done; + +static void sig_handler(int sig __maybe_unused) +{ + done = true; +} + +/* + * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since + * we asked by setting its exec_error to the function below, + * ftrace__workload_exec_failed_signal. + * + * XXX We need to handle this more appropriately, emitting an error, etc. + */ +static void ftrace__workload_exec_failed_signal(int signo __maybe_unused, + siginfo_t *info __maybe_unused, + void *ucontext __maybe_unused) +{ + /* workload_exec_errno = info->si_value.sival_int; */ + done = true; +} + +static int __write_tracing_file(const char *name, const char *val, bool append) +{ + char *file; + int fd, ret = -1; + ssize_t size = strlen(val); + int flags = O_WRONLY; + char errbuf[512]; + + file = get_tracing_file(name); + if (!file) { + pr_debug("cannot get tracing file: %s\n", name); + return -1; + } + + if (append) + flags |= O_APPEND; + else + flags |= O_TRUNC; + + fd = open(file, flags); + if (fd < 0) { + pr_debug("cannot open tracing file: %s: %s\n", + name, str_error_r(errno, errbuf, sizeof(errbuf))); + goto out; + } + + if (write(fd, val, size) == size) + ret = 0; + else + pr_debug("write '%s' to tracing/%s failed: %s\n", + val, name, str_error_r(errno, errbuf, sizeof(errbuf))); + + close(fd); +out: + put_tracing_file(file); + return ret; +} + +static int write_tracing_file(const char *name, const char *val) +{ + return __write_tracing_file(name, val, false); +} + +static int append_tracing_file(const char *name, const char *val) +{ + return __write_tracing_file(name, val, true); +} + +static int reset_tracing_cpu(void); +static void reset_tracing_filters(void); + +static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused) +{ + if (write_tracing_file("tracing_on", "0") < 0) + return -1; + + if (write_tracing_file("current_tracer", "nop") < 0) + return -1; + + if (write_tracing_file("set_ftrace_pid", " ") < 0) + return -1; + + if (reset_tracing_cpu() < 0) + return -1; + + if (write_tracing_file("max_graph_depth", "0") < 0) + return -1; + + reset_tracing_filters(); + return 0; +} + +static int set_tracing_pid(struct perf_ftrace *ftrace) +{ + int i; + char buf[16]; + + if (target__has_cpu(&ftrace->target)) + return 0; + + for (i = 0; i < thread_map__nr(ftrace->evlist->threads); i++) { + scnprintf(buf, sizeof(buf), "%d", + ftrace->evlist->threads->map[i]); + if (append_tracing_file("set_ftrace_pid", buf) < 0) + return -1; + } + return 0; +} + +static int set_tracing_cpumask(struct cpu_map *cpumap) +{ + char *cpumask; + size_t mask_size; + int ret; + int last_cpu; + + last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1); + mask_size = (last_cpu + 3) / 4 + 1; + mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */ + + cpumask = malloc(mask_size); + if (cpumask == NULL) { + pr_debug("failed to allocate cpu mask\n"); + return -1; + } + + cpu_map__snprint_mask(cpumap, cpumask, mask_size); + + ret = write_tracing_file("tracing_cpumask", cpumask); + + free(cpumask); + return ret; +} + +static int set_tracing_cpu(struct perf_ftrace *ftrace) +{ + struct cpu_map *cpumap = ftrace->evlist->cpus; + + if (!target__has_cpu(&ftrace->target)) + return 0; + + return set_tracing_cpumask(cpumap); +} + +static int reset_tracing_cpu(void) +{ + struct cpu_map *cpumap = cpu_map__new(NULL); + int ret; + + ret = set_tracing_cpumask(cpumap); + cpu_map__put(cpumap); + return ret; +} + +static int __set_tracing_filter(const char *filter_file, struct list_head *funcs) +{ + struct filter_entry *pos; + + list_for_each_entry(pos, funcs, list) { + if (append_tracing_file(filter_file, pos->name) < 0) + return -1; + } + + return 0; +} + +static int set_tracing_filters(struct perf_ftrace *ftrace) +{ + int ret; + + ret = __set_tracing_filter("set_ftrace_filter", &ftrace->filters); + if (ret < 0) + return ret; + + ret = __set_tracing_filter("set_ftrace_notrace", &ftrace->notrace); + if (ret < 0) + return ret; + + ret = __set_tracing_filter("set_graph_function", &ftrace->graph_funcs); + if (ret < 0) + return ret; + + /* old kernels do not have this filter */ + __set_tracing_filter("set_graph_notrace", &ftrace->nograph_funcs); + + return ret; +} + +static void reset_tracing_filters(void) +{ + write_tracing_file("set_ftrace_filter", " "); + write_tracing_file("set_ftrace_notrace", " "); + write_tracing_file("set_graph_function", " "); + write_tracing_file("set_graph_notrace", " "); +} + +static int set_tracing_depth(struct perf_ftrace *ftrace) +{ + char buf[16]; + + if (ftrace->graph_depth == 0) + return 0; + + if (ftrace->graph_depth < 0) { + pr_err("invalid graph depth: %d\n", ftrace->graph_depth); + return -1; + } + + snprintf(buf, sizeof(buf), "%d", ftrace->graph_depth); + + if (write_tracing_file("max_graph_depth", buf) < 0) + return -1; + + return 0; +} + +static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) +{ + char *trace_file; + int trace_fd; + char buf[4096]; + struct pollfd pollfd = { + .events = POLLIN, + }; + + if (geteuid() != 0) { + pr_err("ftrace only works for root!\n"); + return -1; + } + + signal(SIGINT, sig_handler); + signal(SIGUSR1, sig_handler); + signal(SIGCHLD, sig_handler); + signal(SIGPIPE, sig_handler); + + if (reset_tracing_files(ftrace) < 0) + goto out; + + /* reset ftrace buffer */ + if (write_tracing_file("trace", "0") < 0) + goto out; + + if (argc && perf_evlist__prepare_workload(ftrace->evlist, + &ftrace->target, argv, false, + ftrace__workload_exec_failed_signal) < 0) { + goto out; + } + + if (set_tracing_pid(ftrace) < 0) { + pr_err("failed to set ftrace pid\n"); + goto out_reset; + } + + if (set_tracing_cpu(ftrace) < 0) { + pr_err("failed to set tracing cpumask\n"); + goto out_reset; + } + + if (set_tracing_filters(ftrace) < 0) { + pr_err("failed to set tracing filters\n"); + goto out_reset; + } + + if (set_tracing_depth(ftrace) < 0) { + pr_err("failed to set graph depth\n"); + goto out_reset; + } + + if (write_tracing_file("current_tracer", ftrace->tracer) < 0) { + pr_err("failed to set current_tracer to %s\n", ftrace->tracer); + goto out_reset; + } + + setup_pager(); + + trace_file = get_tracing_file("trace_pipe"); + if (!trace_file) { + pr_err("failed to open trace_pipe\n"); + goto out_reset; + } + + trace_fd = open(trace_file, O_RDONLY); + + put_tracing_file(trace_file); + + if (trace_fd < 0) { + pr_err("failed to open trace_pipe\n"); + goto out_reset; + } + + fcntl(trace_fd, F_SETFL, O_NONBLOCK); + pollfd.fd = trace_fd; + + if (write_tracing_file("tracing_on", "1") < 0) { + pr_err("can't enable tracing\n"); + goto out_close_fd; + } + + perf_evlist__start_workload(ftrace->evlist); + + while (!done) { + if (poll(&pollfd, 1, -1) < 0) + break; + + if (pollfd.revents & POLLIN) { + int n = read(trace_fd, buf, sizeof(buf)); + if (n < 0) + break; + if (fwrite(buf, n, 1, stdout) != 1) + break; + } + } + + write_tracing_file("tracing_on", "0"); + + /* read remaining buffer contents */ + while (true) { + int n = read(trace_fd, buf, sizeof(buf)); + if (n <= 0) + break; + if (fwrite(buf, n, 1, stdout) != 1) + break; + } + +out_close_fd: + close(trace_fd); +out_reset: + reset_tracing_files(ftrace); +out: + return done ? 0 : -1; +} + +static int perf_ftrace_config(const char *var, const char *value, void *cb) +{ + struct perf_ftrace *ftrace = cb; + + if (prefixcmp(var, "ftrace.")) + return 0; + + if (strcmp(var, "ftrace.tracer")) + return -1; + + if (!strcmp(value, "function_graph") || + !strcmp(value, "function")) { + ftrace->tracer = value; + return 0; + } + + pr_err("Please select \"function_graph\" (default) or \"function\"\n"); + return -1; +} + +static int parse_filter_func(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + struct list_head *head = opt->value; + struct filter_entry *entry; + + entry = malloc(sizeof(*entry) + strlen(str) + 1); + if (entry == NULL) + return -ENOMEM; + + strcpy(entry->name, str); + list_add_tail(&entry->list, head); + + return 0; +} + +static void delete_filter_func(struct list_head *head) +{ + struct filter_entry *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, head, list) { + list_del(&pos->list); + free(pos); + } +} + +int cmd_ftrace(int argc, const char **argv) +{ + int ret; + struct perf_ftrace ftrace = { + .tracer = DEFAULT_TRACER, + .target = { .uid = UINT_MAX, }, + }; + const char * const ftrace_usage[] = { + "perf ftrace [<options>] [<command>]", + "perf ftrace [<options>] -- <command> [<options>]", + NULL + }; + const struct option ftrace_options[] = { + OPT_STRING('t', "tracer", &ftrace.tracer, "tracer", + "tracer to use: function_graph(default) or function"), + OPT_STRING('p', "pid", &ftrace.target.pid, "pid", + "trace on existing process id"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose"), + OPT_BOOLEAN('a', "all-cpus", &ftrace.target.system_wide, + "system-wide collection from all CPUs"), + OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu", + "list of cpus to monitor"), + OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func", + "trace given functions only", parse_filter_func), + OPT_CALLBACK('N', "notrace-funcs", &ftrace.notrace, "func", + "do not trace given functions", parse_filter_func), + OPT_CALLBACK('G', "graph-funcs", &ftrace.graph_funcs, "func", + "Set graph filter on given functions", parse_filter_func), + OPT_CALLBACK('g', "nograph-funcs", &ftrace.nograph_funcs, "func", + "Set nograph filter on given functions", parse_filter_func), + OPT_INTEGER('D', "graph-depth", &ftrace.graph_depth, + "Max depth for function graph tracer"), + OPT_END() + }; + + INIT_LIST_HEAD(&ftrace.filters); + INIT_LIST_HEAD(&ftrace.notrace); + INIT_LIST_HEAD(&ftrace.graph_funcs); + INIT_LIST_HEAD(&ftrace.nograph_funcs); + + ret = perf_config(perf_ftrace_config, &ftrace); + if (ret < 0) + return -1; + + argc = parse_options(argc, argv, ftrace_options, ftrace_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + if (!argc && target__none(&ftrace.target)) + usage_with_options(ftrace_usage, ftrace_options); + + ret = target__validate(&ftrace.target); + if (ret) { + char errbuf[512]; + + target__strerror(&ftrace.target, ret, errbuf, 512); + pr_err("%s\n", errbuf); + goto out_delete_filters; + } + + ftrace.evlist = perf_evlist__new(); + if (ftrace.evlist == NULL) { + ret = -ENOMEM; + goto out_delete_filters; + } + + ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target); + if (ret < 0) + goto out_delete_evlist; + + ret = __cmd_ftrace(&ftrace, argc, argv); + +out_delete_evlist: + perf_evlist__delete(ftrace.evlist); + +out_delete_filters: + delete_filter_func(&ftrace.filters); + delete_filter_func(&ftrace.notrace); + delete_filter_func(&ftrace.graph_funcs); + delete_filter_func(&ftrace.nograph_funcs); + + return ret; +} diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 3bdb2c78a21b..530a7f2fa0f3 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -12,16 +12,22 @@ #include <subcmd/run-command.h> #include <subcmd/help.h> #include "util/debug.h" +#include <linux/kernel.h> +#include <errno.h> +#include <stdio.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> static struct man_viewer_list { struct man_viewer_list *next; - char name[FLEX_ARRAY]; + char name[0]; } *man_viewer_list; static struct man_viewer_info_list { struct man_viewer_info_list *next; const char *info; - char name[FLEX_ARRAY]; + char name[0]; } *man_viewer_info_list; enum help_format { @@ -102,10 +108,14 @@ out: return ret; } -static void exec_woman_emacs(const char *path, const char *page) +static void exec_failed(const char *cmd) { char sbuf[STRERR_BUFSIZE]; + pr_warning("failed to exec '%s': %s", cmd, str_error_r(errno, sbuf, sizeof(sbuf))); +} +static void exec_woman_emacs(const char *path, const char *page) +{ if (!check_emacsclient_version()) { /* This works only with emacsclient version >= 22. */ char *man_page; @@ -116,8 +126,7 @@ static void exec_woman_emacs(const char *path, const char *page) execlp(path, "emacsclient", "-e", man_page, NULL); free(man_page); } - warning("failed to exec '%s': %s", path, - str_error_r(errno, sbuf, sizeof(sbuf))); + exec_failed(path); } } @@ -128,7 +137,6 @@ static void exec_man_konqueror(const char *path, const char *page) if (display && *display) { char *man_page; const char *filename = "kfmclient"; - char sbuf[STRERR_BUFSIZE]; /* It's simpler to launch konqueror using kfmclient. */ if (path) { @@ -149,33 +157,27 @@ static void exec_man_konqueror(const char *path, const char *page) execlp(path, filename, "newTab", man_page, NULL); free(man_page); } - warning("failed to exec '%s': %s", path, - str_error_r(errno, sbuf, sizeof(sbuf))); + exec_failed(path); } } static void exec_man_man(const char *path, const char *page) { - char sbuf[STRERR_BUFSIZE]; - if (!path) path = "man"; execlp(path, "man", page, NULL); - warning("failed to exec '%s': %s", path, - str_error_r(errno, sbuf, sizeof(sbuf))); + exec_failed(path); } static void exec_man_cmd(const char *cmd, const char *page) { - char sbuf[STRERR_BUFSIZE]; char *shell_cmd; if (asprintf(&shell_cmd, "%s %s", cmd, page) > 0) { execl("/bin/sh", "sh", "-c", shell_cmd, NULL); free(shell_cmd); } - warning("failed to exec '%s': %s", cmd, - str_error_r(errno, sbuf, sizeof(sbuf))); + exec_failed(cmd); } static void add_man_viewer(const char *name) @@ -208,6 +210,12 @@ static void do_add_man_viewer_info(const char *name, man_viewer_info_list = new; } +static void unsupported_man_viewer(const char *name, const char *var) +{ + pr_warning("'%s': path for unsupported man viewer.\n" + "Please consider using 'man.<tool>.%s' instead.", name, var); +} + static int add_man_viewer_path(const char *name, size_t len, const char *value) @@ -215,9 +223,7 @@ static int add_man_viewer_path(const char *name, if (supported_man_viewer(name, len)) do_add_man_viewer_info(name, len, value); else - warning("'%s': path for unsupported man viewer.\n" - "Please consider using 'man.<tool>.cmd' instead.", - name); + unsupported_man_viewer(name, "cmd"); return 0; } @@ -227,9 +233,7 @@ static int add_man_viewer_cmd(const char *name, const char *value) { if (supported_man_viewer(name, len)) - warning("'%s': cmd for supported man viewer.\n" - "Please consider using 'man.<tool>.path' instead.", - name); + unsupported_man_viewer(name, "path"); else do_add_man_viewer_info(name, len, value); @@ -241,8 +245,10 @@ static int add_man_viewer_info(const char *var, const char *value) const char *name = var + 4; const char *subkey = strrchr(name, '.'); - if (!subkey) - return error("Config with no key for man viewer: %s", name); + if (!subkey) { + pr_err("Config with no key for man viewer: %s", name); + return -1; + } if (!strcmp(subkey, ".path")) { if (!value) @@ -255,7 +261,7 @@ static int add_man_viewer_info(const char *var, const char *value) return add_man_viewer_cmd(name, subkey - name, value); } - warning("'%s': unsupported man viewer sub key.", subkey); + pr_warning("'%s': unsupported man viewer sub key.", subkey); return 0; } @@ -301,12 +307,6 @@ void list_common_cmds_help(void) } } -static int is_perf_command(const char *s) -{ - return is_in_cmdlist(&main_cmds, s) || - is_in_cmdlist(&other_cmds, s); -} - static const char *cmd_to_page(const char *perf_cmd) { char *s; @@ -332,7 +332,7 @@ static void setup_man_path(void) setenv("MANPATH", new_path, 1); free(new_path); } else { - error("Unable to setup man path"); + pr_err("Unable to setup man path"); } } @@ -349,7 +349,7 @@ static void exec_viewer(const char *name, const char *page) else if (info) exec_man_cmd(info, page); else - warning("'%s': unknown man viewer.", name); + pr_warning("'%s': unknown man viewer.", name); } static int show_man_page(const char *perf_cmd) @@ -418,7 +418,7 @@ static int show_html_page(const char *perf_cmd) return 0; } -int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_help(int argc, const char **argv) { bool show_all = false; enum help_format help_format = HELP_FORMAT_MAN; @@ -434,7 +434,7 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) const char * const builtin_help_subcommands[] = { "buildid-cache", "buildid-list", "diff", "evlist", "help", "list", "record", "report", "bench", "stat", "timechart", "top", "annotate", - "script", "sched", "kmem", "lock", "kvm", "test", "inject", "mem", "data", + "script", "sched", "kallsyms", "kmem", "lock", "kvm", "test", "inject", "mem", "data", #ifdef HAVE_LIBELF_SUPPORT "probe", #endif @@ -446,12 +446,13 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) "perf help [--all] [--man|--web|--info] [command]", NULL }; - const char *alias; - int rc = 0; + int rc; load_command_list("perf-", &main_cmds, &other_cmds); - perf_config(perf_help_config, &help_format); + rc = perf_config(perf_help_config, &help_format); + if (rc) + return rc; argc = parse_options_subcommand(argc, argv, builtin_help_options, builtin_help_subcommands, builtin_help_usage, 0); @@ -470,12 +471,6 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) return 0; } - alias = alias_lookup(argv[0]); - if (alias && !is_perf_command(argv[0])) { - printf("`perf %s' is aliased to `%s'\n", argv[0], alias); - return 0; - } - switch (help_format) { case HELP_FORMAT_MAN: rc = show_man_page(argv[0]); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index b9bc7e39833a..ea8db38eedd1 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -18,10 +18,13 @@ #include "util/data.h" #include "util/auxtrace.h" #include "util/jit.h" +#include "util/thread.h" #include <subcmd/parse-options.h> #include <linux/list.h> +#include <errno.h> +#include <signal.h> struct perf_inject { struct perf_tool tool; @@ -333,6 +336,18 @@ static int perf_event__repipe_comm(struct perf_tool *tool, return err; } +static int perf_event__repipe_namespaces(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + int err = perf_event__process_namespaces(tool, event, sample, machine); + + perf_event__repipe(tool, event, sample, machine); + + return err; +} + static int perf_event__repipe_exit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -660,6 +675,7 @@ static int __cmd_inject(struct perf_inject *inject) session->itrace_synth_opts = &inject->itrace_synth_opts; inject->itrace_synth_opts.inject = true; inject->tool.comm = perf_event__repipe_comm; + inject->tool.namespaces = perf_event__repipe_namespaces; inject->tool.exit = perf_event__repipe_exit; inject->tool.id_index = perf_event__repipe_id_index; inject->tool.auxtrace_info = perf_event__process_auxtrace_info; @@ -681,6 +697,8 @@ static int __cmd_inject(struct perf_inject *inject) lseek(fd, output_data_offset, SEEK_SET); ret = perf_session__process_events(session); + if (ret) + return ret; if (!file_out->is_pipe) { if (inject->build_ids) @@ -725,7 +743,7 @@ static int __cmd_inject(struct perf_inject *inject) return ret; } -int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_inject(int argc, const char **argv) { struct perf_inject inject = { .tool = { diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c new file mode 100644 index 000000000000..bcfb363112d3 --- /dev/null +++ b/tools/perf/builtin-kallsyms.c @@ -0,0 +1,68 @@ +/* + * builtin-kallsyms.c + * + * Builtin command: Look for a symbol in the running kernel and its modules + * + * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Released under the GPL v2. (and only v2, not any later version) + */ +#include <inttypes.h> +#include "builtin.h" +#include <linux/compiler.h> +#include <subcmd/parse-options.h> +#include "debug.h" +#include "machine.h" +#include "symbol.h" + +static int __cmd_kallsyms(int argc, const char **argv) +{ + int i; + struct machine *machine = machine__new_kallsyms(); + + if (machine == NULL) { + pr_err("Couldn't read /proc/kallsyms\n"); + return -1; + } + + for (i = 0; i < argc; ++i) { + struct map *map; + struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map); + + if (symbol == NULL) { + printf("%s: not found\n", argv[i]); + continue; + } + + printf("%s: %s %s %#" PRIx64 "-%#" PRIx64 " (%#" PRIx64 "-%#" PRIx64")\n", + symbol->name, map->dso->short_name, map->dso->long_name, + map->unmap_ip(map, symbol->start), map->unmap_ip(map, symbol->end), + symbol->start, symbol->end); + } + + machine__delete(machine); + return 0; +} + +int cmd_kallsyms(int argc, const char **argv) +{ + const struct option options[] = { + OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), + OPT_END() + }; + const char * const kallsyms_usage[] = { + "perf kallsyms [<options>] symbol_name", + NULL + }; + + argc = parse_options(argc, argv, options, kallsyms_usage, 0); + if (argc < 1) + usage_with_options(kallsyms_usage, options); + + symbol_conf.sort_by_name = true; + symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); + if (symbol__init(NULL) < 0) + return -1; + + return __cmd_kallsyms(argc, argv); +} diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 915869e00d86..a1497c516d85 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -20,11 +20,16 @@ #include "util/debug.h" +#include <linux/kernel.h> #include <linux/rbtree.h> #include <linux/string.h> +#include <errno.h> +#include <inttypes.h> #include <locale.h> #include <regex.h> +#include "sane_ctype.h" + static int kmem_slab; static int kmem_page; @@ -638,7 +643,7 @@ static const struct { { "__GFP_FS", "F" }, { "__GFP_COLD", "CO" }, { "__GFP_NOWARN", "NWR" }, - { "__GFP_REPEAT", "R" }, + { "__GFP_RETRY_MAYFAIL", "R" }, { "__GFP_NOFAIL", "NF" }, { "__GFP_NORETRY", "NR" }, { "__GFP_COMP", "C" }, @@ -964,6 +969,7 @@ static struct perf_tool perf_kmem = { .comm = perf_event__process_comm, .mmap = perf_event__process_mmap, .mmap2 = perf_event__process_mmap2, + .namespaces = perf_event__process_namespaces, .ordered_events = true, }; @@ -1065,7 +1071,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines) data = rb_entry(next, struct page_stat, node); sym = machine__find_kernel_function(machine, data->callsite, &map); - if (sym && sym->name) + if (sym) caller = sym->name; else scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite); @@ -1107,7 +1113,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines data = rb_entry(next, struct page_stat, node); sym = machine__find_kernel_function(machine, data->callsite, &map); - if (sym && sym->name) + if (sym) caller = sym->name; else scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite); @@ -1709,7 +1715,7 @@ static int setup_slab_sorting(struct list_head *sort_list, const char *arg) if (!tok) break; if (slab_sort_dimension__add(tok, sort_list) < 0) { - error("Unknown slab --sort key: '%s'", tok); + pr_err("Unknown slab --sort key: '%s'", tok); free(str); return -1; } @@ -1735,7 +1741,7 @@ static int setup_page_sorting(struct list_head *sort_list, const char *arg) if (!tok) break; if (page_sort_dimension__add(tok, sort_list) < 0) { - error("Unknown page --sort key: '%s'", tok); + pr_err("Unknown page --sort key: '%s'", tok); free(str); return -1; } @@ -1865,7 +1871,7 @@ static int __cmd_record(int argc, const char **argv) for (j = 1; j < (unsigned int)argc; j++, i++) rec_argv[i] = argv[j]; - return cmd_record(i, rec_argv, NULL); + return cmd_record(i, rec_argv); } static int kmem_config(const char *var, const char *value, void *cb __maybe_unused) @@ -1884,7 +1890,7 @@ static int kmem_config(const char *var, const char *value, void *cb __maybe_unus return 0; } -int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_kmem(int argc, const char **argv) { const char * const default_slab_sort = "frag,hit,bytes"; const char * const default_page_sort = "bytes,hit"; @@ -1920,10 +1926,12 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; struct perf_session *session; - int ret = -1; const char errmsg[] = "No %s allocation events found. Have you run 'perf kmem record --%s'?\n"; + int ret = perf_config(kmem_config, NULL); + + if (ret) + return ret; - perf_config(kmem_config, NULL); argc = parse_options_subcommand(argc, argv, kmem_options, kmem_subcommands, kmem_usage, 0); @@ -1948,6 +1956,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) if (session == NULL) return -1; + ret = -1; + if (kmem_slab) { if (!perf_evlist__find_tracepoint_by_name(session->evlist, "kmem:kmalloc")) { diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 08fa88f62a24..f309c3773522 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -3,6 +3,7 @@ #include "util/evsel.h" #include "util/evlist.h" +#include "util/term.h" #include "util/util.h" #include "util/cache.h" #include "util/symbol.h" @@ -23,13 +24,33 @@ #ifdef HAVE_TIMERFD_SUPPORT #include <sys/timerfd.h> #endif +#include <sys/time.h> +#include <linux/kernel.h> #include <linux/time64.h> +#include <errno.h> +#include <inttypes.h> +#include <poll.h> #include <termios.h> #include <semaphore.h> +#include <signal.h> #include <pthread.h> #include <math.h> +static const char *get_filename_for_perf_kvm(void) +{ + const char *filename; + + if (perf_host && !perf_guest) + filename = strdup("perf.data.host"); + else if (!perf_host && perf_guest) + filename = strdup("perf.data.guest"); + else + filename = strdup("perf.data.kvm"); + + return filename; +} + #ifdef HAVE_KVM_STAT_SUPPORT #include "util/kvm-stat.h" @@ -1044,6 +1065,7 @@ static int read_events(struct perf_kvm_stat *kvm) struct perf_tool eops = { .sample = process_sample_event, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .ordered_events = true, }; struct perf_data_file file = { @@ -1208,7 +1230,7 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) set_option_flag(record_options, 0, "transaction", PARSE_OPT_DISABLED); record_usage = kvm_stat_record_usage; - return cmd_record(i, rec_argv, NULL); + return cmd_record(i, rec_argv); } static int @@ -1348,6 +1370,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, kvm->tool.exit = perf_event__process_exit; kvm->tool.fork = perf_event__process_fork; kvm->tool.lost = process_lost_event; + kvm->tool.namespaces = perf_event__process_namespaces; kvm->tool.ordered_events = true; perf_tool__fill_defaults(&kvm->tool); @@ -1475,7 +1498,7 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv) #endif perf_stat: - return cmd_stat(argc, argv, NULL); + return cmd_stat(argc, argv); } #endif /* HAVE_KVM_STAT_SUPPORT */ @@ -1494,7 +1517,7 @@ static int __cmd_record(const char *file_name, int argc, const char **argv) BUG_ON(i != rec_argc); - return cmd_record(i, rec_argv, NULL); + return cmd_record(i, rec_argv); } static int __cmd_report(const char *file_name, int argc, const char **argv) @@ -1512,7 +1535,7 @@ static int __cmd_report(const char *file_name, int argc, const char **argv) BUG_ON(i != rec_argc); - return cmd_report(i, rec_argv, NULL); + return cmd_report(i, rec_argv); } static int @@ -1531,10 +1554,10 @@ __cmd_buildid_list(const char *file_name, int argc, const char **argv) BUG_ON(i != rec_argc); - return cmd_buildid_list(i, rec_argv, NULL); + return cmd_buildid_list(i, rec_argv); } -int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_kvm(int argc, const char **argv) { const char *file_name = NULL; const struct option kvm_options[] = { @@ -1589,9 +1612,9 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) else if (!strncmp(argv[0], "rep", 3)) return __cmd_report(file_name, argc, argv); else if (!strncmp(argv[0], "diff", 4)) - return cmd_diff(argc, argv, NULL); + return cmd_diff(argc, argv); else if (!strncmp(argv[0], "top", 3)) - return cmd_top(argc, argv, NULL); + return cmd_top(argc, argv); else if (!strncmp(argv[0], "buildid-list", 12)) return __cmd_buildid_list(file_name, argc, argv); #ifdef HAVE_KVM_STAT_SUPPORT diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index ba9322ff858b..4bf2cb4d25aa 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -14,11 +14,13 @@ #include "util/parse-events.h" #include "util/cache.h" #include "util/pmu.h" +#include "util/debug.h" #include <subcmd/parse-options.h> static bool desc_flag = true; +static bool details_flag; -int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_list(int argc, const char **argv) { int i; bool raw_dump = false; @@ -29,6 +31,10 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) "Print extra event descriptions. --no-desc to not print."), OPT_BOOLEAN('v', "long-desc", &long_desc_flag, "Print longer event descriptions."), + OPT_BOOLEAN(0, "details", &details_flag, + "Print information on the perf event names and expressions used internally by events."), + OPT_INCR(0, "debug", &verbose, + "Enable debugging output"), OPT_END() }; const char * const list_usage[] = { @@ -47,7 +53,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) printf("\nList of pre-defined events (to be used in -e):\n\n"); if (argc == 0) { - print_events(NULL, raw_dump, !desc_flag, long_desc_flag); + print_events(NULL, raw_dump, !desc_flag, long_desc_flag, + details_flag); return 0; } @@ -69,7 +76,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) print_hwcache_events(NULL, raw_dump); else if (strcmp(argv[i], "pmu") == 0) print_pmu_events(NULL, raw_dump, !desc_flag, - long_desc_flag); + long_desc_flag, details_flag); else if (strcmp(argv[i], "sdt") == 0) print_sdt_events(NULL, NULL, raw_dump); else if ((sep = strchr(argv[i], ':')) != NULL) { @@ -77,7 +84,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) if (sep == NULL) { print_events(argv[i], raw_dump, !desc_flag, - long_desc_flag); + long_desc_flag, + details_flag); continue; } sep_idx = sep - argv[i]; @@ -100,7 +108,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump); print_hwcache_events(s, raw_dump); print_pmu_events(s, raw_dump, !desc_flag, - long_desc_flag); + long_desc_flag, + details_flag); print_tracepoint_events(NULL, s, raw_dump); print_sdt_events(NULL, s, raw_dump); free(s); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index ce3bfb48b26f..ff98652484a7 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> #include "builtin.h" #include "perf.h" @@ -26,6 +28,7 @@ #include <linux/list.h> #include <linux/hash.h> +#include <linux/kernel.h> static struct perf_session *session; @@ -858,6 +861,7 @@ static int __cmd_report(bool display_info) struct perf_tool eops = { .sample = process_sample_event, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .ordered_events = true, }; struct perf_data_file file = { @@ -940,34 +944,36 @@ static int __cmd_record(int argc, const char **argv) BUG_ON(i != rec_argc); - ret = cmd_record(i, rec_argv, NULL); + ret = cmd_record(i, rec_argv); free(rec_argv); return ret; } -int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_lock(int argc, const char **argv) { - const struct option info_options[] = { - OPT_BOOLEAN('t', "threads", &info_threads, - "dump thread list in perf.data"), - OPT_BOOLEAN('m', "map", &info_map, - "map of lock instances (address:name table)"), - OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), - OPT_END() - }; const struct option lock_options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), + OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), OPT_END() }; + + const struct option info_options[] = { + OPT_BOOLEAN('t', "threads", &info_threads, + "dump thread list in perf.data"), + OPT_BOOLEAN('m', "map", &info_map, + "map of lock instances (address:name table)"), + OPT_PARENT(lock_options) + }; + const struct option report_options[] = { OPT_STRING('k', "key", &sort_key, "acquired", "key for sorting (acquired / contended / avg_wait / wait_total / wait_max / wait_min)"), - OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), /* TODO: type */ - OPT_END() + OPT_PARENT(lock_options) }; + const char * const info_usage[] = { "perf lock info [<options>]", NULL @@ -1006,7 +1012,7 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) rc = __cmd_report(false); } else if (!strcmp(argv[0], "script")) { /* Aliased to 'perf script' */ - return cmd_script(argc, argv, prefix); + return cmd_script(argc, argv); } else if (!strcmp(argv[0], "info")) { if (argc) { argc = parse_options(argc, argv, diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index cd7bc4d104e2..e001c0290793 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -1,3 +1,7 @@ +#include <inttypes.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> #include "builtin.h" #include "perf.h" @@ -8,6 +12,7 @@ #include "util/data.h" #include "util/mem-events.h" #include "util/debug.h" +#include "util/symbol.h" #define MEM_OPERATION_LOAD 0x1 #define MEM_OPERATION_STORE 0x2 @@ -42,8 +47,8 @@ static int parse_record_events(const struct option *opt, fprintf(stderr, "%-13s%-*s%s\n", e->tag, - verbose ? 25 : 0, - verbose ? perf_mem_events__name(j) : "", + verbose > 0 ? 25 : 0, + verbose > 0 ? perf_mem_events__name(j) : "", e->supported ? ": available" : ""); } exit(0); @@ -129,7 +134,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) pr_debug("\n"); } - ret = cmd_record(i, rec_argv, NULL); + ret = cmd_record(i, rec_argv); free(rec_argv); return ret; } @@ -256,7 +261,7 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem) for (j = 1; j < argc; j++, i++) rep_argv[i] = argv[j]; - ret = cmd_report(i, rep_argv, NULL); + ret = cmd_report(i, rep_argv); free(rep_argv); return ret; } @@ -330,7 +335,7 @@ error: return ret; } -int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_mem(int argc, const char **argv) { struct stat st; struct perf_mem mem = { @@ -342,6 +347,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) .lost = perf_event__process_lost, .fork = perf_event__process_fork, .build_id = perf_event__process_build_id, + .namespaces = perf_event__process_namespaces, .ordered_events = true, }, .input_name = "perf.data", diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index f87996b0cb29..cf9f9e9c2fc0 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -442,9 +442,9 @@ static int perf_del_probe_events(struct strfilter *filter) } if (ret == -ENOENT && ret2 == -ENOENT) - pr_debug("\"%s\" does not hit any event.\n", str); - /* Note that this is silently ignored */ - ret = 0; + pr_warning("\"%s\" does not hit any event.\n", str); + else + ret = 0; error: if (kfd >= 0) @@ -468,7 +468,7 @@ out: static int -__cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) +__cmd_probe(int argc, const char **argv) { const char * const probe_usage[] = { "perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]", @@ -486,7 +486,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) OPT_INCR('v', "verbose", &verbose, "be more verbose (show parsed arguments, etc)"), OPT_BOOLEAN('q', "quiet", ¶ms.quiet, - "be quiet (do not show any mesages)"), + "be quiet (do not show any messages)"), OPT_CALLBACK_DEFAULT('l', "list", NULL, "[GROUP:]EVENT", "list up probe events", opt_set_filter_with_command, DEFAULT_LIST_FILTER), @@ -552,6 +552,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"), + OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", + "Look for files with symbols relative to this directory"), OPT_END() }; int ret; @@ -685,13 +687,13 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) return 0; } -int cmd_probe(int argc, const char **argv, const char *prefix) +int cmd_probe(int argc, const char **argv) { int ret; ret = init_params(); if (!ret) { - ret = __cmd_probe(argc, argv, prefix); + ret = __cmd_probe(argc, argv); cleanup_params(); } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 4ec10e9427d9..17a14bcce34a 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -38,14 +38,30 @@ #include "util/bpf-loader.h" #include "util/trigger.h" #include "util/perf-hooks.h" +#include "util/time-utils.h" +#include "util/units.h" #include "asm/bug.h" +#include <errno.h> +#include <inttypes.h> +#include <poll.h> #include <unistd.h> #include <sched.h> +#include <signal.h> #include <sys/mman.h> +#include <sys/wait.h> #include <asm/bug.h> #include <linux/time64.h> +struct switch_output { + bool enabled; + bool signal; + unsigned long size; + unsigned long time; + const char *str; + bool set; +}; + struct record { struct perf_tool tool; struct record_opts opts; @@ -62,10 +78,33 @@ struct record { bool no_buildid_cache_set; bool buildid_all; bool timestamp_filename; - bool switch_output; + struct switch_output switch_output; unsigned long long samples; }; +static volatile int auxtrace_record__snapshot_started; +static DEFINE_TRIGGER(auxtrace_snapshot_trigger); +static DEFINE_TRIGGER(switch_output_trigger); + +static bool switch_output_signal(struct record *rec) +{ + return rec->switch_output.signal && + trigger_is_ready(&switch_output_trigger); +} + +static bool switch_output_size(struct record *rec) +{ + return rec->switch_output.size && + trigger_is_ready(&switch_output_trigger) && + (rec->bytes_written >= rec->switch_output.size); +} + +static bool switch_output_time(struct record *rec) +{ + return rec->switch_output.time && + trigger_is_ready(&switch_output_trigger); +} + static int record__write(struct record *rec, void *bf, size_t size) { if (perf_data_file__write(rec->session->file, bf, size) < 0) { @@ -74,6 +113,10 @@ static int record__write(struct record *rec, void *bf, size_t size) } rec->bytes_written += size; + + if (switch_output_size(rec)) + trigger_hit(&switch_output_trigger); + return 0; } @@ -193,10 +236,6 @@ static volatile int done; static volatile int signr = -1; static volatile int child_finished; -static volatile int auxtrace_record__snapshot_started; -static DEFINE_TRIGGER(auxtrace_snapshot_trigger); -static DEFINE_TRIGGER(switch_output_trigger); - static void sig_handler(int sig) { if (sig == SIGCHLD) @@ -386,7 +425,7 @@ static int record__mmap(struct record *rec) static int record__open(struct record *rec) { - char msg[512]; + char msg[BUFSIZ]; struct perf_evsel *pos; struct perf_evlist *evlist = rec->evlist; struct perf_session *session = rec->session; @@ -400,7 +439,7 @@ static int record__open(struct record *rec) try_again: if (perf_evsel__open(pos, pos->cpus, pos->threads) < 0) { if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) { - if (verbose) + if (verbose > 0) ui__warning("%s\n", msg); goto try_again; } @@ -414,7 +453,7 @@ try_again: } if (perf_evlist__apply_filters(evlist, &pos)) { - error("failed to set filter \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", pos->filter, perf_evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); rc = -1; @@ -422,7 +461,7 @@ try_again: } if (perf_evlist__apply_drv_configs(evlist, &pos, &err_term)) { - error("failed to set config \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set config \"%s\" on event %s with %d (%s)\n", err_term->val.drv_cfg, perf_evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); rc = -1; @@ -623,22 +662,23 @@ record__finish_output(struct record *rec) static int record__synthesize_workload(struct record *rec, bool tail) { - struct { - struct thread_map map; - struct thread_map_data map_data; - } thread_map; + int err; + struct thread_map *thread_map; if (rec->opts.tail_synthesize != tail) return 0; - thread_map.map.nr = 1; - thread_map.map.map[0].pid = rec->evlist->workload.pid; - thread_map.map.map[0].comm = NULL; - return perf_event__synthesize_thread_map(&rec->tool, &thread_map.map, + thread_map = thread_map__new_by_tid(rec->evlist->workload.pid); + if (thread_map == NULL) + return -1; + + err = perf_event__synthesize_thread_map(&rec->tool, thread_map, process_synthesized_event, &rec->session->machines.host, rec->opts.sample_address, rec->opts.proc_map_timeout); + thread_map__put(thread_map); + return err; } static int record__synthesize(struct record *rec, bool tail); @@ -712,6 +752,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused, } static void snapshot_sig_handler(int sig); +static void alarm_sig_handler(int sig); int __weak perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused, @@ -842,11 +883,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) signal(SIGTERM, sig_handler); signal(SIGSEGV, sigsegv_handler); - if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) { + if (rec->opts.record_namespaces) + tool->namespace_events = true; + + if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) { signal(SIGUSR2, snapshot_sig_handler); if (rec->opts.auxtrace_snapshot_mode) trigger_on(&auxtrace_snapshot_trigger); - if (rec->switch_output) + if (rec->switch_output.enabled) trigger_on(&switch_output_trigger); } else { signal(SIGUSR2, SIG_IGN); @@ -949,6 +993,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) */ if (forks) { union perf_event *event; + pid_t tgid; event = malloc(sizeof(event->comm) + machine->id_hdr_size); if (event == NULL) { @@ -962,10 +1007,30 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * cannot see a correct process name for those events. * Synthesize COMM event to prevent it. */ - perf_event__synthesize_comm(tool, event, - rec->evlist->workload.pid, - process_synthesized_event, - machine); + tgid = perf_event__synthesize_comm(tool, event, + rec->evlist->workload.pid, + process_synthesized_event, + machine); + free(event); + + if (tgid == -1) + goto out_child; + + event = malloc(sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (event == NULL) { + err = -ENOMEM; + goto out_child; + } + + /* + * Synthesize NAMESPACES event for the command specified. + */ + perf_event__synthesize_namespaces(tool, event, + rec->evlist->workload.pid, + tgid, process_synthesized_event, + machine); free(event); perf_evlist__start_workload(rec->evlist); @@ -1043,6 +1108,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) err = fd; goto out_child; } + + /* re-arm the alarm */ + if (rec->switch_output.time) + alarm(rec->switch_output.time); } if (hits == rec->samples) { @@ -1352,6 +1421,78 @@ out_free: return ret; } +static void switch_output_size_warn(struct record *rec) +{ + u64 wakeup_size = perf_evlist__mmap_size(rec->opts.mmap_pages); + struct switch_output *s = &rec->switch_output; + + wakeup_size /= 2; + + if (s->size < wakeup_size) { + char buf[100]; + + unit_number__scnprintf(buf, sizeof(buf), wakeup_size); + pr_warning("WARNING: switch-output data size lower than " + "wakeup kernel buffer size (%s) " + "expect bigger perf.data sizes\n", buf); + } +} + +static int switch_output_setup(struct record *rec) +{ + struct switch_output *s = &rec->switch_output; + static struct parse_tag tags_size[] = { + { .tag = 'B', .mult = 1 }, + { .tag = 'K', .mult = 1 << 10 }, + { .tag = 'M', .mult = 1 << 20 }, + { .tag = 'G', .mult = 1 << 30 }, + { .tag = 0 }, + }; + static struct parse_tag tags_time[] = { + { .tag = 's', .mult = 1 }, + { .tag = 'm', .mult = 60 }, + { .tag = 'h', .mult = 60*60 }, + { .tag = 'd', .mult = 60*60*24 }, + { .tag = 0 }, + }; + unsigned long val; + + if (!s->set) + return 0; + + if (!strcmp(s->str, "signal")) { + s->signal = true; + pr_debug("switch-output with SIGUSR2 signal\n"); + goto enabled; + } + + val = parse_tag_value(s->str, tags_size); + if (val != (unsigned long) -1) { + s->size = val; + pr_debug("switch-output with %s size threshold\n", s->str); + goto enabled; + } + + val = parse_tag_value(s->str, tags_time); + if (val != (unsigned long) -1) { + s->time = val; + pr_debug("switch-output with %s time threshold (%lu seconds)\n", + s->str, s->time); + goto enabled; + } + + return -1; + +enabled: + rec->timestamp_filename = true; + s->enabled = true; + + if (s->size && !rec->opts.no_buffering) + switch_output_size_warn(rec); + + return 0; +} + static const char * const __record_usage[] = { "perf record [<options>] [<command>]", "perf record [<options>] -- <command> [<options>]", @@ -1387,6 +1528,7 @@ static struct record record = { .fork = perf_event__process_fork, .exit = perf_event__process_exit, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .mmap = perf_event__process_mmap, .mmap2 = perf_event__process_mmap2, .ordered_events = true, @@ -1501,6 +1643,8 @@ static struct option __record_options[] = { "opts", "AUX area tracing Snapshot Mode", ""), OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout, "per thread proc mmap processing timeout in ms"), + OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces, + "Record namespaces events"), OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events, "Record context switch events"), OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel, @@ -1519,8 +1663,10 @@ static struct option __record_options[] = { "Record build-id of all DSOs regardless of hits"), OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename, "append timestamp to output filename"), - OPT_BOOLEAN(0, "switch-output", &record.switch_output, - "Switch output when receive SIGUSR2"), + OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str, + &record.switch_output.set, "signal,size,time", + "Switch output when receive SIGUSR2 or cross size,time threshold", + "signal"), OPT_BOOLEAN(0, "dry-run", &dry_run, "Parse options then exit"), OPT_END() @@ -1528,7 +1674,7 @@ static struct option __record_options[] = { struct option *record_options = __record_options; -int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_record(int argc, const char **argv) { int err; struct record *rec = &record; @@ -1559,12 +1705,18 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (rec->evlist == NULL) return -ENOMEM; - perf_config(perf_record_config, rec); + err = perf_config(perf_record_config, rec); + if (err) + return err; argc = parse_options(argc, argv, record_options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); + if (quiet) + perf_quiet_option(); + + /* Make system wide (-a) the default target. */ if (!argc && target__none(&rec->opts.target)) - usage_with_options(record_usage, record_options); + rec->opts.target.system_wide = true; if (nr_cgroups && !rec->opts.target.system_wide) { usage_with_options_msg(record_usage, record_options, @@ -1578,8 +1730,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) return -EINVAL; } - if (rec->switch_output) - rec->timestamp_filename = true; + if (switch_output_setup(rec)) { + parse_options_usage(record_usage, record_options, "switch-output", 0); + return -EINVAL; + } + + if (rec->switch_output.time) { + signal(SIGALRM, alarm_sig_handler); + alarm(rec->switch_output.time); + } if (!rec->itr) { rec->itr = auxtrace_record__init(rec->evlist, &err); @@ -1629,7 +1788,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (rec->no_buildid_cache || rec->no_buildid) { disable_buildid_cache(); - } else if (rec->switch_output) { + } else if (rec->switch_output.enabled) { /* * In 'perf record --switch-output', disable buildid * generation by default to reduce data file switching @@ -1721,6 +1880,8 @@ out: static void snapshot_sig_handler(int sig __maybe_unused) { + struct record *rec = &record; + if (trigger_is_ready(&auxtrace_snapshot_trigger)) { trigger_hit(&auxtrace_snapshot_trigger); auxtrace_record__snapshot_started = 1; @@ -1728,6 +1889,14 @@ static void snapshot_sig_handler(int sig __maybe_unused) trigger_error(&auxtrace_snapshot_trigger); } - if (trigger_is_ready(&switch_output_trigger)) + if (switch_output_signal(rec)) + trigger_hit(&switch_output_trigger); +} + +static void alarm_sig_handler(int sig __maybe_unused) +{ + struct record *rec = &record; + + if (switch_output_time(rec)) trigger_hit(&switch_output_trigger); } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 06cc759a4597..79a33eb1a10d 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -16,7 +16,6 @@ #include <linux/rbtree.h> #include "util/symbol.h" #include "util/callchain.h" -#include "util/strlist.h" #include "util/values.h" #include "perf.h" @@ -38,10 +37,18 @@ #include "arch/common.h" #include "util/time-utils.h" #include "util/auxtrace.h" +#include "util/units.h" #include <dlfcn.h> +#include <errno.h> +#include <inttypes.h> +#include <regex.h> +#include <signal.h> #include <linux/bitmap.h> #include <linux/stringify.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> struct report { struct perf_tool tool; @@ -87,10 +94,9 @@ static int report__config(const char *var, const char *value, void *cb) symbol_conf.cumulate_callchain = perf_config_bool(var, value); return 0; } - if (!strcmp(var, "report.queue-size")) { - rep->queue_size = perf_config_u64(var, value); - return 0; - } + if (!strcmp(var, "report.queue-size")) + return perf_config_u64(&rep->queue_size, var, value); + if (!strcmp(var, "report.sort_order")) { default_sort_order = strdup(value); return 0; @@ -320,6 +326,9 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report size_t size = sizeof(buf); int socked_id = hists->socket_filter; + if (quiet) + return 0; + if (symbol_conf.filter_relative) { nr_samples = hists->stats.nr_non_filtered_samples; nr_events = hists->stats.total_non_filtered_period; @@ -372,7 +381,11 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, { struct perf_evsel *pos; - fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples); + if (!quiet) { + fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", + evlist->stats.total_lost_samples); + } + evlist__for_each_entry(evlist, pos) { struct hists *hists = evsel__hists(pos); const char *evname = perf_evsel__name(pos); @@ -382,13 +395,12 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, continue; hists__fprintf_nr_sample_events(hists, rep, evname, stdout); - hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout, + hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout, symbol_conf.use_callchain); fprintf(stdout, "\n\n"); } - if (sort_order == NULL && - parent_pattern == default_parent_pattern) + if (!quiet) fprintf(stdout, "#\n# (%s)\n#\n", help); if (rep->show_threads) { @@ -545,6 +557,7 @@ static int __cmd_report(struct report *rep) ui__error("failed to set cpu bitmap\n"); return ret; } + session->itrace_synth_opts->cpu_bitmap = rep->cpu_bitmap; } if (rep->show_threads) { @@ -675,7 +688,7 @@ const char report_callchain_help[] = "Display call graph (stack chain/backtrace) CALLCHAIN_REPORT_HELP "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT; -int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_report(int argc, const char **argv) { struct perf_session *session; struct itrace_synth_opts itrace_synth_opts = { .set = 0, }; @@ -694,6 +707,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .mmap = perf_event__process_mmap, .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost, @@ -716,6 +730,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "input file name"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, @@ -837,6 +852,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) stdio__config_color, "always"), OPT_STRING(0, "time", &report.time_str, "str", "Time span of interest (start,stop)"), + OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name, + "Show inline function"), OPT_END() }; struct perf_data_file file = { @@ -847,7 +864,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) if (ret < 0) return ret; - perf_config(report__config, &report); + ret = perf_config(report__config, &report); + if (ret) + return ret; argc = parse_options(argc, argv, options, report_usage, 0); if (argc) { @@ -861,6 +880,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) report.symbol_filter_str = argv[0]; } + if (quiet) + perf_quiet_option(); + if (symbol_conf.vmlinux_name && access(symbol_conf.vmlinux_name, R_OK)) { pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name); @@ -981,14 +1003,14 @@ repeat: goto error; } - if (report.header || report.header_only) { + if ((report.header || report.header_only) && !quiet) { perf_session__fprintf_info(session, stdout, report.show_full_info); if (report.header_only) { ret = 0; goto error; } - } else if (use_browser == 0) { + } else if (use_browser == 0 && !quiet) { fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n", stdout); } @@ -1007,7 +1029,7 @@ repeat: * providing it only in verbose mode not to bloat too * much struct symbol. */ - if (verbose) { + if (verbose > 0) { /* * XXX: Need to provide a less kludgy way to ask for * more space per symbol, the u32 is for the index on diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 5b134b0d1ff3..322b4def8411 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -22,16 +22,21 @@ #include "util/debug.h" +#include <linux/kernel.h> #include <linux/log2.h> #include <sys/prctl.h> #include <sys/resource.h> +#include <inttypes.h> +#include <errno.h> #include <semaphore.h> #include <pthread.h> #include <math.h> #include <api/fs/fs.h> #include <linux/time64.h> +#include "sane_ctype.h" + #define PR_SET_NAME 15 /* Set process name */ #define MAX_CPUS 4096 #define COMM_LEN 20 @@ -77,6 +82,22 @@ struct sched_atom { #define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP" +/* task state bitmask, copied from include/linux/sched.h */ +#define TASK_RUNNING 0 +#define TASK_INTERRUPTIBLE 1 +#define TASK_UNINTERRUPTIBLE 2 +#define __TASK_STOPPED 4 +#define __TASK_TRACED 8 +/* in tsk->exit_state */ +#define EXIT_DEAD 16 +#define EXIT_ZOMBIE 32 +#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) +/* in tsk->state again */ +#define TASK_DEAD 64 +#define TASK_WAKEKILL 128 +#define TASK_WAKING 256 +#define TASK_PARKED 512 + enum thread_state { THREAD_SLEEPING = 0, THREAD_WAIT_CPU, @@ -205,7 +226,9 @@ struct perf_sched { unsigned int max_stack; bool show_cpu_visual; bool show_wakeups; + bool show_next; bool show_migrations; + bool show_state; u64 skipped_samples; const char *time_str; struct perf_time_interval ptime; @@ -216,13 +239,20 @@ struct perf_sched { struct thread_runtime { u64 last_time; /* time of previous sched in/out event */ u64 dt_run; /* run time */ - u64 dt_wait; /* time between CPU access (off cpu) */ + u64 dt_sleep; /* time between CPU access by sleep (off cpu) */ + u64 dt_iowait; /* time between CPU access by iowait (off cpu) */ + u64 dt_preempt; /* time between CPU access by preempt (off cpu) */ u64 dt_delay; /* time between wakeup and sched-in */ u64 ready_to_run; /* time of wakeup */ struct stats run_stats; u64 total_run_time; + u64 total_sleep_time; + u64 total_iowait_time; + u64 total_preempt_time; + u64 total_delay_time; + int last_state; u64 migrations; }; @@ -436,7 +466,7 @@ static struct task_desc *register_pid(struct perf_sched *sched, BUG_ON(!sched->tasks); sched->tasks[task->nr] = task; - if (verbose) + if (verbose > 0) printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm); return task; @@ -770,7 +800,7 @@ replay_wakeup_event(struct perf_sched *sched, const u32 pid = perf_evsel__intval(evsel, sample, "pid"); struct task_desc *waker, *wakee; - if (verbose) { + if (verbose > 0) { printf("sched_wakeup event %p\n", evsel); printf(" ... pid %d woke up %s/%d\n", sample->tid, comm, pid); @@ -798,7 +828,7 @@ static int replay_switch_event(struct perf_sched *sched, int cpu = sample->cpu; s64 delta; - if (verbose) + if (verbose > 0) printf("sched_switch event %p\n", evsel); if (cpu >= MAX_CPUS || cpu < 0) @@ -846,7 +876,7 @@ static int replay_fork_event(struct perf_sched *sched, goto out_put; } - if (verbose) { + if (verbose > 0) { 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); @@ -1549,7 +1579,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp)); color_fprintf(stdout, color, " %12s secs ", stimestamp); - if (new_shortname || (verbose && sched_in->tid)) { + if (new_shortname || (verbose > 0 && sched_in->tid)) { const char *pid_color = color; if (thread__has_color(sched_in)) @@ -1821,6 +1851,9 @@ static void timehist_header(struct perf_sched *sched) printf(" %-*s %9s %9s %9s", comm_width, "task name", "wait time", "sch delay", "run time"); + if (sched->show_state) + printf(" %s", "state"); + printf("\n"); /* @@ -1831,9 +1864,14 @@ static void timehist_header(struct perf_sched *sched) if (sched->show_cpu_visual) printf(" %*s ", ncpus, ""); - printf(" %-*s %9s %9s %9s\n", comm_width, + printf(" %-*s %9s %9s %9s", comm_width, "[tid/pid]", "(msec)", "(msec)", "(msec)"); + if (sched->show_state) + printf(" %5s", ""); + + printf("\n"); + /* * separator */ @@ -1846,18 +1884,38 @@ static void timehist_header(struct perf_sched *sched) graph_dotted_line, graph_dotted_line, graph_dotted_line, graph_dotted_line); + if (sched->show_state) + printf(" %.5s", graph_dotted_line); + printf("\n"); } +static char task_state_char(struct thread *thread, int state) +{ + static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; + unsigned bit = state ? ffs(state) : 0; + + /* 'I' for idle */ + if (thread->tid == 0) + return 'I'; + + return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; +} + static void timehist_print_sample(struct perf_sched *sched, + struct perf_evsel *evsel, struct perf_sample *sample, struct addr_location *al, struct thread *thread, - u64 t) + u64 t, int state) { struct thread_runtime *tr = thread__priv(thread); + const char *next_comm = perf_evsel__strval(evsel, sample, "next_comm"); + const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid"); u32 max_cpus = sched->max_cpu + 1; char tstr[64]; + char nstr[30]; + u64 wait_time; timestamp__scnprintf_usec(t, tstr, sizeof(tstr)); printf("%15s [%04d] ", tstr, sample->cpu); @@ -1880,11 +1938,21 @@ static void timehist_print_sample(struct perf_sched *sched, printf(" %-*s ", comm_width, timehist_get_commstr(thread)); - print_sched_time(tr->dt_wait, 6); + wait_time = tr->dt_sleep + tr->dt_iowait + tr->dt_preempt; + print_sched_time(wait_time, 6); + print_sched_time(tr->dt_delay, 6); print_sched_time(tr->dt_run, 6); - if (sched->show_wakeups) + if (sched->show_state) + printf(" %5c ", task_state_char(thread, state)); + + if (sched->show_next) { + snprintf(nstr, sizeof(nstr), "next: %s[%d]", next_comm, next_pid); + printf(" %-*s", comm_width, nstr); + } + + if (sched->show_wakeups && !sched->show_next) printf(" %-*s", comm_width, ""); if (thread->tid == 0) @@ -1930,8 +1998,11 @@ static void timehist_update_runtime_stats(struct thread_runtime *r, u64 t, u64 tprev) { r->dt_delay = 0; - r->dt_wait = 0; + r->dt_sleep = 0; + r->dt_iowait = 0; + r->dt_preempt = 0; r->dt_run = 0; + if (tprev) { r->dt_run = t - tprev; if (r->ready_to_run) { @@ -1943,12 +2014,25 @@ static void timehist_update_runtime_stats(struct thread_runtime *r, if (r->last_time > tprev) pr_debug("time travel: last sched out time for task > previous sched_switch event\n"); - else if (r->last_time) - r->dt_wait = tprev - r->last_time; + else if (r->last_time) { + u64 dt_wait = tprev - r->last_time; + + if (r->last_state == TASK_RUNNING) + r->dt_preempt = dt_wait; + else if (r->last_state == TASK_UNINTERRUPTIBLE) + r->dt_iowait = dt_wait; + else + r->dt_sleep = dt_wait; + } } update_stats(&r->run_stats, r->dt_run); - r->total_run_time += r->dt_run; + + r->total_run_time += r->dt_run; + r->total_delay_time += r->dt_delay; + r->total_sleep_time += r->dt_sleep; + r->total_iowait_time += r->dt_iowait; + r->total_preempt_time += r->dt_preempt; } static bool is_idle_sample(struct perf_sample *sample, @@ -1981,8 +2065,8 @@ static void save_task_callchain(struct perf_sched *sched, if (thread__resolve_callchain(thread, cursor, evsel, sample, NULL, NULL, sched->max_stack + 2) != 0) { - if (verbose) - error("Failed to resolve callchain. Skipping\n"); + if (verbose > 0) + pr_err("Failed to resolve callchain. Skipping\n"); return; } @@ -1998,7 +2082,7 @@ static void save_task_callchain(struct perf_sched *sched, break; sym = node->sym; - if (sym && sym->name) { + if (sym) { if (!strcmp(sym->name, "schedule") || !strcmp(sym->name, "__schedule") || !strcmp(sym->name, "preempt_schedule")) @@ -2373,6 +2457,8 @@ static int timehist_sched_change_event(struct perf_tool *tool, struct thread_runtime *tr = NULL; u64 tprev, t = sample->time; int rc = 0; + int state = perf_evsel__intval(evsel, sample, "prev_state"); + if (machine__resolve(machine, &al, sample) < 0) { pr_err("problem processing %d event. skipping it\n", @@ -2447,8 +2533,10 @@ static int timehist_sched_change_event(struct perf_tool *tool, * time. we only care total run time and run stat. */ last_tr->dt_run = 0; - last_tr->dt_wait = 0; last_tr->dt_delay = 0; + last_tr->dt_sleep = 0; + last_tr->dt_iowait = 0; + last_tr->dt_preempt = 0; if (itr->cursor.nr) callchain_append(&itr->callchain, &itr->cursor, t - tprev); @@ -2458,7 +2546,7 @@ static int timehist_sched_change_event(struct perf_tool *tool, } if (!sched->summary_only) - timehist_print_sample(sched, sample, &al, thread, t); + timehist_print_sample(sched, evsel, sample, &al, thread, t, state); out: if (sched->hist_time.start == 0 && t >= ptime->start) @@ -2470,6 +2558,9 @@ out: /* time of this sched_switch event becomes last time task seen */ tr->last_time = sample->time; + /* last state is used to determine where to account wait time */ + tr->last_state = state; + /* sched out event for task so reset ready to run time */ tr->ready_to_run = 0; } @@ -2526,7 +2617,26 @@ static void print_thread_runtime(struct thread *t, printf("\n"); } +static void print_thread_waittime(struct thread *t, + struct thread_runtime *r) +{ + printf("%*s %5d %9" PRIu64 " ", + comm_width, timehist_get_commstr(t), t->ppid, + (u64) r->run_stats.n); + + print_sched_time(r->total_run_time, 8); + print_sched_time(r->total_sleep_time, 6); + printf(" "); + print_sched_time(r->total_iowait_time, 6); + printf(" "); + print_sched_time(r->total_preempt_time, 6); + printf(" "); + print_sched_time(r->total_delay_time, 6); + printf("\n"); +} + struct total_run_stats { + struct perf_sched *sched; u64 sched_count; u64 task_count; u64 total_run_time; @@ -2545,7 +2655,11 @@ static int __show_thread_runtime(struct thread *t, void *priv) stats->task_count++; stats->sched_count += r->run_stats.n; stats->total_run_time += r->total_run_time; - print_thread_runtime(t, r); + + if (stats->sched->show_state) + print_thread_waittime(t, r); + else + print_thread_runtime(t, r); } return 0; @@ -2633,18 +2747,24 @@ static void timehist_print_summary(struct perf_sched *sched, u64 hist_time = sched->hist_time.end - sched->hist_time.start; memset(&totals, 0, sizeof(totals)); + totals.sched = sched; if (sched->idle_hist) { printf("\nIdle-time summary\n"); printf("%*s parent sched-out ", comm_width, "comm"); printf(" idle-time min-idle avg-idle max-idle stddev migrations\n"); + } else if (sched->show_state) { + printf("\nWait-time summary\n"); + printf("%*s parent sched-in ", comm_width, "comm"); + printf(" run-time sleep iowait preempt delay\n"); } else { printf("\nRuntime summary\n"); printf("%*s parent sched-in ", comm_width, "comm"); printf(" run-time min-run avg-run max-run stddev migrations\n"); } printf("%*s (count) ", comm_width, ""); - printf(" (msec) (msec) (msec) (msec) %%\n"); + printf(" (msec) (msec) (msec) (msec) %s\n", + sched->show_state ? "(msec)" : "%"); printf("%.117s\n", graph_dotted_line); machine__for_each_thread(m, show_thread_runtime, &totals); @@ -3157,16 +3277,17 @@ static int __cmd_record(int argc, const char **argv) BUG_ON(i != rec_argc); - return cmd_record(i, rec_argv, NULL); + return cmd_record(i, rec_argv); } -int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_sched(int argc, const char **argv) { const char default_sort_order[] = "avg, max, switch, runtime"; struct perf_sched sched = { .tool = { .sample = perf_sched__process_tracepoint_sample, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .lost = perf_event__process_lost, .fork = perf_sched__process_fork_event, .ordered_events = true, @@ -3235,11 +3356,13 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('S', "with-summary", &sched.summary, "Show all syscalls and summary with statistics"), OPT_BOOLEAN('w', "wakeups", &sched.show_wakeups, "Show wakeup events"), + OPT_BOOLEAN('n', "next", &sched.show_next, "Show next task"), OPT_BOOLEAN('M', "migrations", &sched.show_migrations, "Show migration events"), OPT_BOOLEAN('V', "cpu-visual", &sched.show_cpu_visual, "Add CPU visual"), OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"), OPT_STRING(0, "time", &sched.time_str, "str", "Time span for analysis (start,stop)"), + OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"), OPT_PARENT(sched_options) }; @@ -3294,7 +3417,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) * Aliased to 'perf script' for now: */ if (!strcmp(argv[0], "script")) - return cmd_script(argc, argv, prefix); + return cmd_script(argc, argv); if (!strncmp(argv[0], "rec", 3)) { return __cmd_record(argc, argv); @@ -3331,10 +3454,14 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) if (argc) usage_with_options(timehist_usage, timehist_options); } - if (sched.show_wakeups && sched.summary_only) { - pr_err(" Error: -s and -w are mutually exclusive.\n"); + if ((sched.show_wakeups || sched.show_next) && + sched.summary_only) { + pr_err(" Error: -s and -[n|w] are mutually exclusive.\n"); parse_options_usage(timehist_usage, timehist_options, "s", true); - parse_options_usage(NULL, timehist_options, "w", true); + if (sched.show_wakeups) + parse_options_usage(NULL, timehist_options, "w", true); + if (sched.show_next) + parse_options_usage(NULL, timehist_options, "n", true); return -EINVAL; } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 2f3ff69fc4e7..83cdc0a61fd6 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -21,13 +21,27 @@ #include "util/cpumap.h" #include "util/thread_map.h" #include "util/stat.h" +#include "util/string2.h" #include "util/thread-stack.h" #include "util/time-utils.h" +#include "print_binary.h" #include <linux/bitmap.h> +#include <linux/kernel.h> #include <linux/stringify.h> #include <linux/time64.h> #include "asm/bug.h" #include "util/mem-events.h" +#include "util/dump-insn.h" +#include <dirent.h> +#include <errno.h> +#include <inttypes.h> +#include <signal.h> +#include <sys/param.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +#include "sane_ctype.h" static char const *script_name; static char const *generate_script_lang; @@ -42,6 +56,7 @@ static bool nanosecs; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); static struct perf_stat_config stat_config; +static int max_blocks; unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; @@ -69,6 +84,9 @@ enum perf_output_field { PERF_OUTPUT_CALLINDENT = 1U << 20, PERF_OUTPUT_INSN = 1U << 21, PERF_OUTPUT_INSNLEN = 1U << 22, + PERF_OUTPUT_BRSTACKINSN = 1U << 23, + PERF_OUTPUT_BRSTACKOFF = 1U << 24, + PERF_OUTPUT_SYNTH = 1U << 25, }; struct output_option { @@ -98,6 +116,14 @@ struct output_option { {.str = "callindent", .field = PERF_OUTPUT_CALLINDENT}, {.str = "insn", .field = PERF_OUTPUT_INSN}, {.str = "insnlen", .field = PERF_OUTPUT_INSNLEN}, + {.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN}, + {.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF}, + {.str = "synth", .field = PERF_OUTPUT_SYNTH}, +}; + +enum { + OUTPUT_TYPE_SYNTH = PERF_TYPE_MAX, + OUTPUT_TYPE_MAX }; /* default set to maintain compatibility with current format */ @@ -107,7 +133,7 @@ static struct { unsigned int print_ip_opts; u64 fields; u64 invalid_fields; -} output[PERF_TYPE_MAX] = { +} output[OUTPUT_TYPE_MAX] = { [PERF_TYPE_HARDWARE] = { .user_set = false, @@ -165,12 +191,44 @@ static struct { .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, + + [OUTPUT_TYPE_SYNTH] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | + PERF_OUTPUT_SYNTH, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, }; +static inline int output_type(unsigned int type) +{ + switch (type) { + case PERF_TYPE_SYNTH: + return OUTPUT_TYPE_SYNTH; + default: + return type; + } +} + +static inline unsigned int attr_type(unsigned int type) +{ + switch (type) { + case OUTPUT_TYPE_SYNTH: + return PERF_TYPE_SYNTH; + default: + return type; + } +} + static bool output_set_by_user(void) { int j; - for (j = 0; j < PERF_TYPE_MAX; ++j) { + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { if (output[j].user_set) return true; } @@ -191,7 +249,7 @@ static const char *output_field2str(enum perf_output_field field) return str; } -#define PRINT_FIELD(x) (output[attr->type].fields & PERF_OUTPUT_##x) +#define PRINT_FIELD(x) (output[output_type(attr->type)].fields & PERF_OUTPUT_##x) static int perf_evsel__do_check_stype(struct perf_evsel *evsel, u64 sample_type, const char *sample_msg, @@ -199,7 +257,7 @@ static int perf_evsel__do_check_stype(struct perf_evsel *evsel, bool allow_user_set) { struct perf_event_attr *attr = &evsel->attr; - int type = attr->type; + int type = output_type(attr->type); const char *evname; if (attr->sample_type & sample_type) @@ -281,10 +339,10 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, "selected.\n"); return -EINVAL; } - if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) { - pr_err("Display of DSO requested but neither sample IP nor " - "sample address\nis selected. Hence, no addresses to convert " - "to DSO.\n"); + if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR) && + !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM) && !PRINT_FIELD(BRSTACKOFF)) { + pr_err("Display of DSO requested but no address to convert. Select\n" + "sample IP, sample address, brstack, brstacksym, or brstackoff.\n"); return -EINVAL; } if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) { @@ -292,7 +350,13 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, "selected. Hence, no address to lookup the source line number.\n"); return -EINVAL; } - + if (PRINT_FIELD(BRSTACKINSN) && + !(perf_evlist__combined_branch_type(session->evlist) & + PERF_SAMPLE_BRANCH_ANY)) { + pr_err("Display of branch stack assembler requested, but non all-branch filter set\n" + "Hint: run 'perf record -b ...'\n"); + return -EINVAL; + } if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) && perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID", PERF_OUTPUT_TID|PERF_OUTPUT_PID)) @@ -323,7 +387,7 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, static void set_print_ip_opts(struct perf_event_attr *attr) { - unsigned int type = attr->type; + unsigned int type = output_type(attr->type); output[type].print_ip_opts = 0; if (PRINT_FIELD(IP)) @@ -351,16 +415,17 @@ static int perf_session__check_output_opt(struct perf_session *session) unsigned int j; struct perf_evsel *evsel; - for (j = 0; j < PERF_TYPE_MAX; ++j) { - evsel = perf_session__find_first_evtype(session, j); + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { + evsel = perf_session__find_first_evtype(session, attr_type(j)); /* * even if fields is set to 0 (ie., show nothing) event must * exist if user explicitly includes it on the command line */ - if (!evsel && output[j].user_set && !output[j].wildcard_set) { + if (!evsel && output[j].user_set && !output[j].wildcard_set && + j != OUTPUT_TYPE_SYNTH) { pr_err("%s events do not exist. " - "Remove corresponding -f option to proceed.\n", + "Remove corresponding -F option to proceed.\n", event_type(j)); return -1; } @@ -491,18 +556,43 @@ mispred_str(struct branch_entry *br) return br->flags.predicted ? 'P' : 'M'; } -static void print_sample_brstack(struct perf_sample *sample) +static void print_sample_brstack(struct perf_sample *sample, + struct thread *thread, + struct perf_event_attr *attr) { struct branch_stack *br = sample->branch_stack; - u64 i; + struct addr_location alf, alt; + u64 i, from, to; if (!(br && br->nr)) return; for (i = 0; i < br->nr; i++) { - printf(" 0x%"PRIx64"/0x%"PRIx64"/%c/%c/%c/%d ", - br->entries[i].from, - br->entries[i].to, + from = br->entries[i].from; + to = br->entries[i].to; + + if (PRINT_FIELD(DSO)) { + memset(&alf, 0, sizeof(alf)); + memset(&alt, 0, sizeof(alt)); + thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); + thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); + } + + printf("0x%"PRIx64, from); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alf.map, stdout); + printf(")"); + } + + printf("/0x%"PRIx64, to); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alt.map, stdout); + printf(")"); + } + + printf("/%c/%c/%c/%d ", mispred_str( br->entries + i), br->entries[i].flags.in_tx? 'X' : '-', br->entries[i].flags.abort? 'A' : '-', @@ -511,7 +601,8 @@ static void print_sample_brstack(struct perf_sample *sample) } static void print_sample_brstacksym(struct perf_sample *sample, - struct thread *thread) + struct thread *thread, + struct perf_event_attr *attr) { struct branch_stack *br = sample->branch_stack; struct addr_location alf, alt; @@ -536,8 +627,18 @@ static void print_sample_brstacksym(struct perf_sample *sample, alt.sym = map__find_symbol(alt.map, alt.addr); symbol__fprintf_symname_offs(alf.sym, &alf, stdout); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alf.map, stdout); + printf(")"); + } putchar('/'); symbol__fprintf_symname_offs(alt.sym, &alt, stdout); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alt.map, stdout); + printf(")"); + } printf("/%c/%c/%c/%d ", mispred_str( br->entries + i), br->entries[i].flags.in_tx? 'X' : '-', @@ -546,6 +647,278 @@ static void print_sample_brstacksym(struct perf_sample *sample, } } +static void print_sample_brstackoff(struct perf_sample *sample, + struct thread *thread, + struct perf_event_attr *attr) +{ + struct branch_stack *br = sample->branch_stack; + struct addr_location alf, alt; + u64 i, from, to; + + if (!(br && br->nr)) + return; + + for (i = 0; i < br->nr; i++) { + + memset(&alf, 0, sizeof(alf)); + memset(&alt, 0, sizeof(alt)); + from = br->entries[i].from; + to = br->entries[i].to; + + thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf); + if (alf.map && !alf.map->dso->adjust_symbols) + from = map__map_ip(alf.map, from); + + thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt); + if (alt.map && !alt.map->dso->adjust_symbols) + to = map__map_ip(alt.map, to); + + printf("0x%"PRIx64, from); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alf.map, stdout); + printf(")"); + } + printf("/0x%"PRIx64, to); + if (PRINT_FIELD(DSO)) { + printf("("); + map__fprintf_dsoname(alt.map, stdout); + printf(")"); + } + printf("/%c/%c/%c/%d ", + mispred_str(br->entries + i), + br->entries[i].flags.in_tx ? 'X' : '-', + br->entries[i].flags.abort ? 'A' : '-', + br->entries[i].flags.cycles); + } +} +#define MAXBB 16384UL + +static int grab_bb(u8 *buffer, u64 start, u64 end, + struct machine *machine, struct thread *thread, + bool *is64bit, u8 *cpumode, bool last) +{ + long offset, len; + struct addr_location al; + bool kernel; + + if (!start || !end) + return 0; + + kernel = machine__kernel_ip(machine, start); + if (kernel) + *cpumode = PERF_RECORD_MISC_KERNEL; + else + *cpumode = PERF_RECORD_MISC_USER; + + /* + * Block overlaps between kernel and user. + * This can happen due to ring filtering + * On Intel CPUs the entry into the kernel is filtered, + * but the exit is not. Let the caller patch it up. + */ + if (kernel != machine__kernel_ip(machine, end)) { + printf("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n", + start, end); + return -ENXIO; + } + + memset(&al, 0, sizeof(al)); + if (end - start > MAXBB - MAXINSN) { + if (last) + printf("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end); + else + printf("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start); + return 0; + } + + thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al); + if (!al.map || !al.map->dso) { + printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); + return 0; + } + if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) { + printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); + return 0; + } + + /* Load maps to ensure dso->is_64_bit has been updated */ + map__load(al.map); + + offset = al.map->map_ip(al.map, start); + len = dso__data_read_offset(al.map->dso, machine, offset, (u8 *)buffer, + end - start + MAXINSN); + + *is64bit = al.map->dso->is_64_bit; + if (len <= 0) + printf("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n", + start, end); + return len; +} + +static void print_jump(uint64_t ip, struct branch_entry *en, + struct perf_insn *x, u8 *inbuf, int len, + int insn) +{ + printf("\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", + ip, + dump_insn(x, ip, inbuf, len, NULL), + en->flags.predicted ? " PRED" : "", + en->flags.mispred ? " MISPRED" : "", + en->flags.in_tx ? " INTX" : "", + en->flags.abort ? " ABORT" : ""); + if (en->flags.cycles) { + printf(" %d cycles", en->flags.cycles); + if (insn) + printf(" %.2f IPC", (float)insn / en->flags.cycles); + } + putchar('\n'); +} + +static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu, + uint64_t addr, struct symbol **lastsym, + struct perf_event_attr *attr) +{ + struct addr_location al; + int off; + + memset(&al, 0, sizeof(al)); + + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al); + if (!al.map) + thread__find_addr_map(thread, cpumode, MAP__VARIABLE, + addr, &al); + if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end) + return; + + al.cpu = cpu; + al.sym = NULL; + if (al.map) + al.sym = map__find_symbol(al.map, al.addr); + + if (!al.sym) + return; + + if (al.addr < al.sym->end) + off = al.addr - al.sym->start; + else + off = al.addr - al.map->start - al.sym->start; + printf("\t%s", al.sym->name); + if (off) + printf("%+d", off); + putchar(':'); + if (PRINT_FIELD(SRCLINE)) + map__fprintf_srcline(al.map, al.addr, "\t", stdout); + putchar('\n'); + *lastsym = al.sym; +} + +static void print_sample_brstackinsn(struct perf_sample *sample, + struct thread *thread, + struct perf_event_attr *attr, + struct machine *machine) +{ + struct branch_stack *br = sample->branch_stack; + u64 start, end; + int i, insn, len, nr, ilen; + struct perf_insn x; + u8 buffer[MAXBB]; + unsigned off; + struct symbol *lastsym = NULL; + + if (!(br && br->nr)) + return; + nr = br->nr; + if (max_blocks && nr > max_blocks + 1) + nr = max_blocks + 1; + + x.thread = thread; + x.cpu = sample->cpu; + + putchar('\n'); + + /* Handle first from jump, of which we don't know the entry. */ + len = grab_bb(buffer, br->entries[nr-1].from, + br->entries[nr-1].from, + machine, thread, &x.is64bit, &x.cpumode, false); + if (len > 0) { + print_ip_sym(thread, x.cpumode, x.cpu, + br->entries[nr - 1].from, &lastsym, attr); + print_jump(br->entries[nr - 1].from, &br->entries[nr - 1], + &x, buffer, len, 0); + } + + /* Print all blocks */ + for (i = nr - 2; i >= 0; i--) { + if (br->entries[i].from || br->entries[i].to) + pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i, + br->entries[i].from, + br->entries[i].to); + start = br->entries[i + 1].to; + end = br->entries[i].from; + + len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false); + /* Patch up missing kernel transfers due to ring filters */ + if (len == -ENXIO && i > 0) { + end = br->entries[--i].from; + pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end); + len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false); + } + if (len <= 0) + continue; + + insn = 0; + for (off = 0;; off += ilen) { + uint64_t ip = start + off; + + print_ip_sym(thread, x.cpumode, x.cpu, ip, &lastsym, attr); + if (ip == end) { + print_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn); + break; + } else { + printf("\t%016" PRIx64 "\t%s\n", ip, + dump_insn(&x, ip, buffer + off, len - off, &ilen)); + if (ilen == 0) + break; + insn++; + } + } + } + + /* + * Hit the branch? In this case we are already done, and the target + * has not been executed yet. + */ + if (br->entries[0].from == sample->ip) + return; + if (br->entries[0].flags.abort) + return; + + /* + * Print final block upto sample + */ + start = br->entries[0].to; + end = sample->ip; + len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true); + print_ip_sym(thread, x.cpumode, x.cpu, start, &lastsym, attr); + if (len <= 0) { + /* Print at least last IP if basic block did not work */ + len = grab_bb(buffer, sample->ip, sample->ip, + machine, thread, &x.is64bit, &x.cpumode, false); + if (len <= 0) + return; + + printf("\t%016" PRIx64 "\t%s\n", sample->ip, + dump_insn(&x, sample->ip, buffer, len, NULL)); + return; + } + for (off = 0; off <= end - start; off += ilen) { + printf("\t%016" PRIx64 "\t%s\n", start + off, + dump_insn(&x, start + off, buffer + off, len - off, &ilen)); + if (ilen == 0) + break; + } +} static void print_sample_addr(struct perf_sample *sample, struct thread *thread, @@ -632,7 +1005,9 @@ static void print_sample_callindent(struct perf_sample *sample, } static void print_insn(struct perf_sample *sample, - struct perf_event_attr *attr) + struct perf_event_attr *attr, + struct thread *thread, + struct machine *machine) { if (PRINT_FIELD(INSNLEN)) printf(" ilen: %d", sample->insn_len); @@ -643,14 +1018,18 @@ static void print_insn(struct perf_sample *sample, for (i = 0; i < sample->insn_len; i++) printf(" %02x", (unsigned char)sample->insn[i]); } + if (PRINT_FIELD(BRSTACKINSN)) + print_sample_brstackinsn(sample, thread, attr, machine); } static void print_sample_bts(struct perf_sample *sample, struct perf_evsel *evsel, struct thread *thread, - struct addr_location *al) + struct addr_location *al, + struct machine *machine) { struct perf_event_attr *attr = &evsel->attr; + unsigned int type = output_type(attr->type); bool print_srcline_last = false; if (PRINT_FIELD(CALLINDENT)) @@ -658,7 +1037,7 @@ static void print_sample_bts(struct perf_sample *sample, /* print branch_from information */ if (PRINT_FIELD(IP)) { - unsigned int print_opts = output[attr->type].print_ip_opts; + unsigned int print_opts = output[type].print_ip_opts; struct callchain_cursor *cursor = NULL; if (symbol_conf.use_callchain && sample->callchain && @@ -681,7 +1060,7 @@ static void print_sample_bts(struct perf_sample *sample, /* print branch_to information */ if (PRINT_FIELD(ADDR) || ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) && - !output[attr->type].user_set)) { + !output[type].user_set)) { printf(" => "); print_sample_addr(sample, thread, attr); } @@ -689,7 +1068,7 @@ static void print_sample_bts(struct perf_sample *sample, if (print_srcline_last) map__fprintf_srcline(al->map, al->addr, "\n ", stdout); - print_insn(sample, attr); + print_insn(sample, attr, thread, machine); printf("\n"); } @@ -824,12 +1203,134 @@ static void print_sample_bpf_output(struct perf_sample *sample) (char *)(sample->raw_data)); } +static void print_sample_spacing(int len, int spacing) +{ + if (len > 0 && len < spacing) + printf("%*s", spacing - len, ""); +} + +static void print_sample_pt_spacing(int len) +{ + print_sample_spacing(len, 34); +} + +static void print_sample_synth_ptwrite(struct perf_sample *sample) +{ + struct perf_synth_intel_ptwrite *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" IP: %u payload: %#" PRIx64 " ", + data->ip, le64_to_cpu(data->payload)); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_mwait(struct perf_sample *sample) +{ + struct perf_synth_intel_mwait *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" hints: %#x extensions: %#x ", + data->hints, data->extensions); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_pwre(struct perf_sample *sample) +{ + struct perf_synth_intel_pwre *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" hw: %u cstate: %u sub-cstate: %u ", + data->hw, data->cstate, data->subcstate); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_exstop(struct perf_sample *sample) +{ + struct perf_synth_intel_exstop *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" IP: %u ", data->ip); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_pwrx(struct perf_sample *sample) +{ + struct perf_synth_intel_pwrx *data = perf_sample__synth_ptr(sample); + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + len = printf(" deepest cstate: %u last cstate: %u wake reason: %#x ", + data->deepest_cstate, data->last_cstate, + data->wake_reason); + print_sample_pt_spacing(len); +} + +static void print_sample_synth_cbr(struct perf_sample *sample) +{ + struct perf_synth_intel_cbr *data = perf_sample__synth_ptr(sample); + unsigned int percent, freq; + int len; + + if (perf_sample__bad_synth_size(sample, *data)) + return; + + freq = (le32_to_cpu(data->freq) + 500) / 1000; + len = printf(" cbr: %2u freq: %4u MHz ", data->cbr, freq); + if (data->max_nonturbo) { + percent = (5 + (1000 * data->cbr) / data->max_nonturbo) / 10; + len += printf("(%3u%%) ", percent); + } + print_sample_pt_spacing(len); +} + +static void print_sample_synth(struct perf_sample *sample, + struct perf_evsel *evsel) +{ + switch (evsel->attr.config) { + case PERF_SYNTH_INTEL_PTWRITE: + print_sample_synth_ptwrite(sample); + break; + case PERF_SYNTH_INTEL_MWAIT: + print_sample_synth_mwait(sample); + break; + case PERF_SYNTH_INTEL_PWRE: + print_sample_synth_pwre(sample); + break; + case PERF_SYNTH_INTEL_EXSTOP: + print_sample_synth_exstop(sample); + break; + case PERF_SYNTH_INTEL_PWRX: + print_sample_synth_pwrx(sample); + break; + case PERF_SYNTH_INTEL_CBR: + print_sample_synth_cbr(sample); + break; + default: + break; + } +} + struct perf_script { struct perf_tool tool; struct perf_session *session; bool show_task_events; bool show_mmap_events; bool show_switch_events; + bool show_namespace_events; bool allocated; struct cpu_map *cpus; struct thread_map *threads; @@ -871,12 +1372,14 @@ static size_t data_src__printf(u64 data_src) static void process_event(struct perf_script *script, struct perf_sample *sample, struct perf_evsel *evsel, - struct addr_location *al) + struct addr_location *al, + struct machine *machine) { struct thread *thread = al->thread; struct perf_event_attr *attr = &evsel->attr; + unsigned int type = output_type(attr->type); - if (output[attr->type].fields == 0) + if (output[type].fields == 0) return; print_sample_start(sample, thread, evsel); @@ -898,13 +1401,17 @@ static void process_event(struct perf_script *script, print_sample_flags(sample->flags); if (is_bts_event(attr)) { - print_sample_bts(sample, evsel, thread, al); + print_sample_bts(sample, evsel, thread, al, machine); return; } if (PRINT_FIELD(TRACE)) event_format__print(evsel->tp_format, sample->cpu, sample->raw_data, sample->raw_size); + + if (attr->type == PERF_TYPE_SYNTH && PRINT_FIELD(SYNTH)) + print_sample_synth(sample, evsel); + if (PRINT_FIELD(ADDR)) print_sample_addr(sample, thread, attr); @@ -923,20 +1430,22 @@ static void process_event(struct perf_script *script, cursor = &callchain_cursor; putchar(cursor ? '\n' : ' '); - sample__fprintf_sym(sample, al, 0, output[attr->type].print_ip_opts, cursor, stdout); + sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, stdout); } if (PRINT_FIELD(IREGS)) print_sample_iregs(sample, attr); if (PRINT_FIELD(BRSTACK)) - print_sample_brstack(sample); + print_sample_brstack(sample, thread, attr); else if (PRINT_FIELD(BRSTACKSYM)) - print_sample_brstacksym(sample, thread); + print_sample_brstacksym(sample, thread, attr); + else if (PRINT_FIELD(BRSTACKOFF)) + print_sample_brstackoff(sample, thread, attr); if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT)) print_sample_bpf_output(sample); - print_insn(sample, attr); + print_insn(sample, attr, thread, machine); printf("\n"); } @@ -1046,7 +1555,7 @@ static int process_sample_event(struct perf_tool *tool, if (scripting_ops) scripting_ops->process_event(event, sample, evsel, &al); else - process_event(scr, sample, evsel, &al); + process_event(scr, sample, evsel, &al, machine); out_put: addr_location__put(&al); @@ -1068,7 +1577,8 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, evlist = *pevlist; evsel = perf_evlist__last(*pevlist); - if (evsel->attr.type >= PERF_TYPE_MAX) + if (evsel->attr.type >= PERF_TYPE_MAX && + evsel->attr.type != PERF_TYPE_SYNTH) return 0; evlist__for_each_entry(evlist, pos) { @@ -1118,6 +1628,41 @@ out: return ret; } +static int process_namespaces_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct thread *thread; + struct perf_script *script = container_of(tool, struct perf_script, tool); + struct perf_session *session = script->session; + struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + int ret = -1; + + thread = machine__findnew_thread(machine, event->namespaces.pid, + event->namespaces.tid); + if (thread == NULL) { + pr_debug("problem processing NAMESPACES event, skipping it.\n"); + return -1; + } + + if (perf_event__process_namespaces(tool, event, sample, machine) < 0) + goto out; + + if (!evsel->attr.sample_id_all) { + sample->cpu = 0; + sample->time = 0; + sample->tid = event->namespaces.tid; + sample->pid = event->namespaces.pid; + } + print_sample_start(sample, thread, evsel); + perf_event__fprintf(event, stdout); + ret = 0; +out: + thread__put(thread); + return ret; +} + static int process_fork_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -1293,6 +1838,8 @@ static int __cmd_script(struct perf_script *script) } if (script->show_switch_events) script->tool.context_switch = process_switch_event; + if (script->show_namespace_events) + script->tool.namespaces = process_namespaces_event; ret = perf_session__process_events(script->session); @@ -1427,12 +1974,13 @@ static int parse_scriptname(const struct option *opt __maybe_unused, static int parse_output_fields(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused) { - char *tok; + char *tok, *strtok_saveptr = NULL; int i, imax = ARRAY_SIZE(all_output_options); int j; int rc = 0; char *str = strdup(arg); int type = -1; + enum { DEFAULT, SET, ADD, REMOVE } change = DEFAULT; if (!str) return -ENOMEM; @@ -1455,6 +2003,8 @@ static int parse_output_fields(const struct option *opt __maybe_unused, type = PERF_TYPE_RAW; else if (!strcmp(str, "break")) type = PERF_TYPE_BREAKPOINT; + else if (!strcmp(str, "synth")) + type = OUTPUT_TYPE_SYNTH; else { fprintf(stderr, "Invalid event type in field string.\n"); rc = -EINVAL; @@ -1478,23 +2028,44 @@ static int parse_output_fields(const struct option *opt __maybe_unused, goto out; } + /* Don't override defaults for +- */ + if (strchr(str, '+') || strchr(str, '-')) + goto parse; + if (output_set_by_user()) pr_warning("Overriding previous field request for all events.\n"); - for (j = 0; j < PERF_TYPE_MAX; ++j) { + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { output[j].fields = 0; output[j].user_set = true; output[j].wildcard_set = true; } } - for (tok = strtok(tok, ","); tok; tok = strtok(NULL, ",")) { +parse: + for (tok = strtok_r(tok, ",", &strtok_saveptr); tok; tok = strtok_r(NULL, ",", &strtok_saveptr)) { + if (*tok == '+') { + if (change == SET) + goto out_badmix; + change = ADD; + tok++; + } else if (*tok == '-') { + if (change == SET) + goto out_badmix; + change = REMOVE; + tok++; + } else { + if (change != SET && change != DEFAULT) + goto out_badmix; + change = SET; + } + for (i = 0; i < imax; ++i) { if (strcmp(tok, all_output_options[i].str) == 0) break; } if (i == imax && strcmp(tok, "flags") == 0) { - print_flags = true; + print_flags = change == REMOVE ? false : true; continue; } if (i == imax) { @@ -1507,12 +2078,16 @@ static int parse_output_fields(const struct option *opt __maybe_unused, /* add user option to all events types for * which it is valid */ - for (j = 0; j < PERF_TYPE_MAX; ++j) { + for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { if (output[j].invalid_fields & all_output_options[i].field) { pr_warning("\'%s\' not valid for %s events. Ignoring.\n", all_output_options[i].str, event_type(j)); - } else - output[j].fields |= all_output_options[i].field; + } else { + if (change == REMOVE) + output[j].fields &= ~all_output_options[i].field; + else + output[j].fields |= all_output_options[i].field; + } } } else { if (output[type].invalid_fields & all_output_options[i].field) { @@ -1532,7 +2107,11 @@ static int parse_output_fields(const struct option *opt __maybe_unused, "Events will not be displayed.\n", event_type(type)); } } + goto out; +out_badmix: + fprintf(stderr, "Cannot mix +-field with overridden fields\n"); + rc = -EINVAL; out: free(str); return rc; @@ -2078,7 +2657,7 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused, return set_maps(script); } -int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_script(int argc, const char **argv) { bool show_full_info = false; bool header = false; @@ -2097,6 +2676,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) .mmap = perf_event__process_mmap, .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .attr = process_attr, @@ -2149,10 +2729,12 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) symbol__config_symfs), OPT_CALLBACK('F', "fields", NULL, "str", "comma separated output fields prepend with 'type:'. " - "Valid types: hw,sw,trace,raw. " + "+field to add and -field to remove." + "Valid types: hw,sw,trace,raw,synth. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," "addr,symoff,period,iregs,brstack,brstacksym,flags," - "bpf-output,callindent,insn,insnlen", parse_output_fields), + "bpf-output,callindent,insn,insnlen,brstackinsn,synth", + parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", @@ -2180,7 +2762,11 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "Show the mmap events"), OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events, "Show context switch events (if recorded)"), - OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"), + OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events, + "Show namespace events (if recorded)"), + OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"), + OPT_INTEGER(0, "max-blocks", &max_blocks, + "Maximum number of code blocks to dump with brstackinsn"), OPT_BOOLEAN(0, "ns", &nanosecs, "Use 9 decimal places when displaying time"), OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts", @@ -2194,6 +2780,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "Enable kernel symbol demangling"), OPT_STRING(0, "time", &script.time_str, "str", "Time span of interest (start,stop)"), + OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name, + "Show inline function"), OPT_END() }; const char * const script_subcommands[] = { "record", "report", NULL }; @@ -2212,11 +2800,12 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) PARSE_OPT_STOP_AT_NON_OPTION); file.path = input_name; + file.force = symbol_conf.force; if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) { rec_script_path = get_script_path(argv[1], RECORD_SUFFIX); if (!rec_script_path) - return cmd_record(argc, argv, NULL); + return cmd_record(argc, argv); } if (argc > 1 && !strncmp(argv[0], "rep", strlen("rep"))) { @@ -2403,6 +2992,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap); if (err < 0) goto out_delete; + itrace_synth_opts.cpu_bitmap = cpu_bitmap; } if (!no_callchain) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index a02f2e965628..48ac53b199fc 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -64,18 +64,29 @@ #include "util/session.h" #include "util/tool.h" #include "util/group.h" +#include "util/string2.h" #include "asm/bug.h" #include <linux/time64.h> #include <api/fs/fs.h> +#include <errno.h> +#include <signal.h> #include <stdlib.h> #include <sys/prctl.h> +#include <inttypes.h> #include <locale.h> #include <math.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "sane_ctype.h" #define DEFAULT_SEPARATOR " " #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" +#define FREEZE_ON_SMI_PATH "devices/cpu/freeze_on_smi" static void print_counters(struct timespec *ts, int argc, const char **argv); @@ -112,6 +123,14 @@ static const char * topdown_attrs[] = { NULL, }; +static const char *smi_cost_attrs = { + "{" + "msr/aperf/," + "msr/smi/," + "cycles" + "}" +}; + static struct perf_evlist *evsel_list; static struct target target = { @@ -127,6 +146,8 @@ static bool null_run = false; static int detailed_run = 0; static bool transaction_run; static bool topdown_run = false; +static bool smi_cost = false; +static bool smi_reset = false; static bool big_num = true; static int big_num_opt = -1; static const char *csv_sep = NULL; @@ -140,12 +161,14 @@ static unsigned int unit_width = 4; /* strlen("unit") */ static bool forever = false; static bool metric_only = false; static bool force_metric_only = false; +static bool no_merge = false; static struct timespec ref_time; static struct cpu_map *aggr_map; static aggr_get_id_t aggr_get_id; static bool append_file; static const char *output_name; static int output_fd; +static int print_free_counters_hint; struct perf_stat { bool record; @@ -310,8 +333,12 @@ static int read_counter(struct perf_evsel *counter) struct perf_counts_values *count; count = perf_counts(counter->counts, cpu, thread); - if (perf_evsel__read(counter, cpu, thread, count)) + if (perf_evsel__read(counter, cpu, thread, count)) { + counter->counts->scaled = -1; + perf_counts(counter->counts, cpu, thread)->ena = 0; + perf_counts(counter->counts, cpu, thread)->run = 0; return -1; + } if (STAT_RECORD) { if (perf_evsel__write_stat_event(counter, cpu, thread, count)) { @@ -336,12 +363,14 @@ static int read_counter(struct perf_evsel *counter) static void read_counters(void) { struct perf_evsel *counter; + int ret; evlist__for_each_entry(evsel_list, counter) { - if (read_counter(counter)) + ret = read_counter(counter); + if (ret) pr_debug("failed to read counter %s\n", counter->name); - if (perf_stat_process_counter(&stat_config, counter)) + if (ret == 0 && perf_stat_process_counter(&stat_config, counter)) pr_warning("failed to process counter %s\n", counter->name); } } @@ -533,7 +562,7 @@ static int store_counter_ids(struct perf_evsel *counter) static int __run_perf_stat(int argc, const char **argv) { int interval = stat_config.interval; - char msg[512]; + char msg[BUFSIZ]; unsigned long long t0, t1; struct perf_evsel *counter; struct timespec ts; @@ -573,7 +602,7 @@ try_again: if (errno == EINVAL || errno == ENOSYS || errno == ENOENT || errno == EOPNOTSUPP || errno == ENXIO) { - if (verbose) + if (verbose > 0) ui__warning("%s event is not supported by the kernel.\n", perf_evsel__name(counter)); counter->supported = false; @@ -582,7 +611,7 @@ try_again: !(counter->leader->nr_members > 1)) continue; } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { - if (verbose) + if (verbose > 0) ui__warning("%s\n", msg); goto try_again; } @@ -607,14 +636,14 @@ try_again: } if (perf_evlist__apply_filters(evsel_list, &counter)) { - error("failed to set filter \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", counter->filter, perf_evsel__name(counter), errno, str_error_r(errno, msg, sizeof(msg))); return -1; } if (perf_evlist__apply_drv_configs(evsel_list, &counter, &err_term)) { - error("failed to set config \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set config \"%s\" on event %s with %d (%s)\n", err_term->val.drv_cfg, perf_evsel__name(counter), errno, str_error_r(errno, msg, sizeof(msg))); return -1; @@ -873,10 +902,7 @@ static void print_metric_csv(void *ctx, return; } snprintf(buf, sizeof(buf), fmt, val); - vals = buf; - while (isspace(*vals)) - vals++; - ends = vals; + ends = vals = ltrim(buf); while (isdigit(*ends) || *ends == '.') ends++; *ends = 0; @@ -948,10 +974,7 @@ static void print_metric_only_csv(void *ctx, const char *color __maybe_unused, return; unit = fixunit(tbuf, os->evsel, unit); snprintf(buf, sizeof buf, fmt, val); - vals = buf; - while (isspace(*vals)) - vals++; - ends = vals; + ends = vals = ltrim(buf); while (isdigit(*ends) || *ends == '.') ends++; *ends = 0; @@ -1109,6 +1132,9 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep); + if (counter->supported) + print_free_counters_hint = 1; + fprintf(stat_config.output, "%-*s%s", csv_output ? 0 : unit_width, counter->unit, csv_sep); @@ -1140,6 +1166,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, out.print_metric = pm; out.new_line = nl; out.ctx = &os; + out.force_header = false; if (csv_output && !metric_only) { print_noise(counter, noise); @@ -1178,11 +1205,81 @@ static void aggr_update_shadow(void) } } +static void collect_all_aliases(struct perf_evsel *counter, + void (*cb)(struct perf_evsel *counter, void *data, + bool first), + void *data) +{ + struct perf_evsel *alias; + + alias = list_prepare_entry(counter, &(evsel_list->entries), node); + list_for_each_entry_continue (alias, &evsel_list->entries, node) { + if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) || + alias->scale != counter->scale || + alias->cgrp != counter->cgrp || + strcmp(alias->unit, counter->unit) || + nsec_counter(alias) != nsec_counter(counter)) + break; + alias->merged_stat = true; + cb(alias, data, false); + } +} + +static bool collect_data(struct perf_evsel *counter, + void (*cb)(struct perf_evsel *counter, void *data, + bool first), + void *data) +{ + if (counter->merged_stat) + return false; + cb(counter, data, true); + if (!no_merge) + collect_all_aliases(counter, cb, data); + return true; +} + +struct aggr_data { + u64 ena, run, val; + int id; + int nr; + int cpu; +}; + +static void aggr_cb(struct perf_evsel *counter, void *data, bool first) +{ + struct aggr_data *ad = data; + int cpu, s2; + + for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { + struct perf_counts_values *counts; + + s2 = aggr_get_id(perf_evsel__cpus(counter), cpu); + if (s2 != ad->id) + continue; + if (first) + ad->nr++; + counts = perf_counts(counter->counts, cpu, 0); + /* + * When any result is bad, make them all to give + * consistent output in interval mode. + */ + if (counts->ena == 0 || counts->run == 0 || + counter->counts->scaled == -1) { + ad->ena = 0; + ad->run = 0; + break; + } + ad->val += counts->val; + ad->ena += counts->ena; + ad->run += counts->run; + } +} + static void print_aggr(char *prefix) { FILE *output = stat_config.output; struct perf_evsel *counter; - int cpu, s, s2, id, nr; + int s, id, nr; double uval; u64 ena, run, val; bool first; @@ -1197,23 +1294,21 @@ static void print_aggr(char *prefix) * Without each counter has its own line. */ for (s = 0; s < aggr_map->nr; s++) { + struct aggr_data ad; if (prefix && metric_only) fprintf(output, "%s", prefix); - id = aggr_map->map[s]; + ad.id = id = aggr_map->map[s]; first = true; evlist__for_each_entry(evsel_list, counter) { - val = ena = run = 0; - nr = 0; - for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - s2 = aggr_get_id(perf_evsel__cpus(counter), cpu); - if (s2 != id) - continue; - val += perf_counts(counter->counts, cpu, 0)->val; - ena += perf_counts(counter->counts, cpu, 0)->ena; - run += perf_counts(counter->counts, cpu, 0)->run; - nr++; - } + ad.val = ad.ena = ad.run = 0; + ad.nr = 0; + if (!collect_data(counter, aggr_cb, &ad)) + continue; + nr = ad.nr; + ena = ad.ena; + run = ad.run; + val = ad.val; if (first && metric_only) { first = false; aggr_printout(counter, id, nr); @@ -1257,6 +1352,21 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix) } } +struct caggr_data { + double avg, avg_enabled, avg_running; +}; + +static void counter_aggr_cb(struct perf_evsel *counter, void *data, + bool first __maybe_unused) +{ + struct caggr_data *cd = data; + struct perf_stat_evsel *ps = counter->priv; + + cd->avg += avg_stats(&ps->res_stats[0]); + cd->avg_enabled += avg_stats(&ps->res_stats[1]); + cd->avg_running += avg_stats(&ps->res_stats[2]); +} + /* * Print out the results of a single counter: * aggregated counts in system-wide mode @@ -1264,23 +1374,31 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix) static void print_counter_aggr(struct perf_evsel *counter, char *prefix) { FILE *output = stat_config.output; - struct perf_stat_evsel *ps = counter->priv; - double avg = avg_stats(&ps->res_stats[0]); double uval; - double avg_enabled, avg_running; + struct caggr_data cd = { .avg = 0.0 }; - avg_enabled = avg_stats(&ps->res_stats[1]); - avg_running = avg_stats(&ps->res_stats[2]); + if (!collect_data(counter, counter_aggr_cb, &cd)) + return; if (prefix && !metric_only) fprintf(output, "%s", prefix); - uval = avg * counter->scale; - printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg); + uval = cd.avg * counter->scale; + printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg); if (!metric_only) fprintf(output, "\n"); } +static void counter_cb(struct perf_evsel *counter, void *data, + bool first __maybe_unused) +{ + struct aggr_data *ad = data; + + ad->val += perf_counts(counter->counts, ad->cpu, 0)->val; + ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena; + ad->run += perf_counts(counter->counts, ad->cpu, 0)->run; +} + /* * Print out the results of a single counter: * does not use aggregated count in system-wide @@ -1293,9 +1411,13 @@ static void print_counter(struct perf_evsel *counter, char *prefix) int cpu; for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - val = perf_counts(counter->counts, cpu, 0)->val; - ena = perf_counts(counter->counts, cpu, 0)->ena; - run = perf_counts(counter->counts, cpu, 0)->run; + struct aggr_data ad = { .cpu = cpu }; + + if (!collect_data(counter, counter_cb, &ad)) + return; + val = ad.val; + ena = ad.ena; + run = ad.run; if (prefix) fprintf(output, "%s", prefix); @@ -1380,6 +1502,7 @@ static void print_metric_headers(const char *prefix, bool no_indent) out.ctx = &os; out.print_metric = print_metric_header; out.new_line = new_line_metric; + out.force_header = true; os.evsel = counter; perf_stat__print_shadow_stats(counter, 0, 0, @@ -1466,6 +1589,7 @@ static void print_header(int argc, const char **argv) static void print_footer(void) { FILE *output = stat_config.output; + int n; if (!null_run) fprintf(output, "\n"); @@ -1477,6 +1601,15 @@ static void print_footer(void) avg_stats(&walltime_nsecs_stats)); } fprintf(output, "\n\n"); + + if (print_free_counters_hint && + sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 && + n > 0) + fprintf(output, +"Some events weren't counted. Try disabling the NMI watchdog:\n" +" echo 0 > /proc/sys/kernel/nmi_watchdog\n" +" perf stat ...\n" +" echo 1 > /proc/sys/kernel/nmi_watchdog\n"); } static void print_counters(struct timespec *ts, int argc, const char **argv) @@ -1633,6 +1766,7 @@ static const struct option stat_options[] = { "list of cpus to monitor in system-wide"), OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode, "disable CPU count aggregation", AGGR_NONE), + OPT_BOOLEAN(0, "no-merge", &no_merge, "Do not merge identical named events"), OPT_STRING('x', "field-separator", &csv_sep, "separator", "print counts with custom separator"), OPT_CALLBACK('G', "cgroup", &evsel_list, "name", @@ -1659,6 +1793,8 @@ static const struct option stat_options[] = { "Only print computed metrics. No raw values", enable_metric_only), OPT_BOOLEAN(0, "topdown", &topdown_run, "measure topdown level 1 statistics"), + OPT_BOOLEAN(0, "smi-cost", &smi_cost, + "measure SMI cost"), OPT_END() }; @@ -1765,7 +1901,7 @@ static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, i cpu = map->map[idx]; - if (cpu >= env->nr_cpus_online) + if (cpu >= env->nr_cpus_avail) return -1; return cpu; @@ -2037,6 +2173,39 @@ static int add_default_attributes(void) return 0; } + if (smi_cost) { + int smi; + + if (sysfs__read_int(FREEZE_ON_SMI_PATH, &smi) < 0) { + fprintf(stderr, "freeze_on_smi is not supported.\n"); + return -1; + } + + if (!smi) { + if (sysfs__write_int(FREEZE_ON_SMI_PATH, 1) < 0) { + fprintf(stderr, "Failed to set freeze_on_smi.\n"); + return -1; + } + smi_reset = true; + } + + if (pmu_have_event("msr", "aperf") && + pmu_have_event("msr", "smi")) { + if (!force_metric_only) + metric_only = true; + err = parse_events(evsel_list, smi_cost_attrs, NULL); + } else { + fprintf(stderr, "To measure SMI cost, it needs " + "msr/aperf/, msr/smi/ and cpu/cycles/ support\n"); + return -1; + } + if (err) { + fprintf(stderr, "Cannot set up SMI cost events\n"); + return -1; + } + return 0; + } + if (topdown_run) { char *str = NULL; bool warn = false; @@ -2339,7 +2508,36 @@ static int __cmd_report(int argc, const char **argv) return 0; } -int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) +static void setup_system_wide(int forks) +{ + /* + * Make system wide (-a) the default target if + * no target was specified and one of following + * conditions is met: + * + * - there's no workload specified + * - there is workload specified but all requested + * events are system wide events + */ + if (!target__none(&target)) + return; + + if (!forks) + target.system_wide = true; + else { + struct perf_evsel *counter; + + evlist__for_each_entry(evsel_list, counter) { + if (!counter->system_wide) + return; + } + + if (evsel_list->nr_entries) + target.system_wide = true; + } +} + +int cmd_stat(int argc, const char **argv) { const char * const stat_usage[] = { "perf stat [<options>] [<command>]", @@ -2361,6 +2559,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands, (const char **) stat_usage, PARSE_OPT_STOP_AT_NON_OPTION); + perf_stat__collect_metric_expr(evsel_list); perf_stat__init_shadow_stats(); if (csv_sep) { @@ -2445,8 +2644,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) } else if (big_num_opt == 0) /* User passed --no-big-num */ big_num = false; - if (!argc && target__none(&target)) - usage_with_options(stat_usage, stat_options); + setup_system_wide(argc); if (run_count < 0) { pr_err("Run count must be a positive number\n"); @@ -2538,7 +2736,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) status = 0; for (run_idx = 0; forever || run_idx < run_count; run_idx++) { - if (run_count != 1 && verbose) + if (run_count != 1 && verbose > 0) fprintf(output, "[ perf stat: executing run #%d ... ]\n", run_idx + 1); @@ -2590,6 +2788,9 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) perf_stat__exit_aggr_mode(); perf_evlist__free_stats(evsel_list); out: + if (smi_cost && smi_reset) + sysfs__write_int(FREEZE_ON_SMI_PATH, 0); + perf_evlist__delete(evsel_list); return status; } diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index e7eaa298d34a..4e2e61695986 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -12,6 +12,8 @@ * of the License. */ +#include <errno.h> +#include <inttypes.h> #include <traceevent/event-parse.h> #include "builtin.h" @@ -23,11 +25,12 @@ #include "util/cache.h" #include "util/evlist.h" #include "util/evsel.h" +#include <linux/kernel.h> #include <linux/rbtree.h> #include <linux/time64.h> #include "util/symbol.h" +#include "util/thread.h" #include "util/callchain.h" -#include "util/strlist.h" #include "perf.h" #include "util/header.h" @@ -1773,7 +1776,7 @@ static int timechart__io_record(int argc, const char **argv) for (i = 0; i < (unsigned int)argc; i++) *p++ = argv[i]; - return cmd_record(rec_argc, rec_argv, NULL); + return cmd_record(rec_argc, rec_argv); } @@ -1864,7 +1867,7 @@ static int timechart__record(struct timechart *tchart, int argc, const char **ar for (j = 0; j < (unsigned int)argc; j++) *p++ = argv[j]; - return cmd_record(rec_argc, rec_argv, NULL); + return cmd_record(rec_argc, rec_argv); } static int @@ -1917,8 +1920,7 @@ parse_time(const struct option *opt, const char *arg, int __maybe_unused unset) return 0; } -int cmd_timechart(int argc, const char **argv, - const char *prefix __maybe_unused) +int cmd_timechart(int argc, const char **argv) { struct timechart tchart = { .tool = { @@ -1933,6 +1935,11 @@ int cmd_timechart(int argc, const char **argv, .merge_dist = 1000, }; const char *output_name = "output.svg"; + const struct option timechart_common_options[] = { + OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"), + OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only, "output processes data only"), + OPT_END() + }; const struct option timechart_options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_STRING('o', "output", &output_name, "file", "output file name"), @@ -1940,9 +1947,6 @@ int cmd_timechart(int argc, const char **argv, OPT_CALLBACK(0, "highlight", NULL, "duration or task name", "highlight tasks. Pass duration in ns or process name.", parse_highlight), - OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"), - OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only, - "output processes data only"), OPT_CALLBACK('p', "process", NULL, "process", "process selector. Pass a pid or process name.", parse_process), @@ -1962,22 +1966,18 @@ int cmd_timechart(int argc, const char **argv, "merge events that are merge-dist us apart", parse_time), OPT_BOOLEAN('f', "force", &tchart.force, "don't complain, do it"), - OPT_END() + OPT_PARENT(timechart_common_options), }; const char * const timechart_subcommands[] = { "record", NULL }; const char *timechart_usage[] = { "perf timechart [<options>] {record}", NULL }; - const struct option timechart_record_options[] = { - OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"), - OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only, - "output processes data only"), OPT_BOOLEAN('I', "io-only", &tchart.io_only, "record only IO data"), OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"), - OPT_END() + OPT_PARENT(timechart_common_options), }; const char * const timechart_record_usage[] = { "perf timechart record [<options>]", diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 3df4178ba378..6052376634c0 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -27,19 +27,20 @@ #include "util/drv_configs.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/event.h" #include "util/machine.h" #include "util/session.h" #include "util/symbol.h" #include "util/thread.h" #include "util/thread_map.h" #include "util/top.h" -#include "util/util.h" #include <linux/rbtree.h> #include <subcmd/parse-options.h> #include "util/parse-events.h" #include "util/cpumap.h" #include "util/xyarray.h" #include "util/sort.h" +#include "util/term.h" #include "util/intlist.h" #include "util/parse-branch-options.h" #include "arch/common.h" @@ -58,6 +59,7 @@ #include <errno.h> #include <time.h> #include <sched.h> +#include <signal.h> #include <sys/syscall.h> #include <sys/ioctl.h> @@ -72,6 +74,8 @@ #include <linux/time64.h> #include <linux/types.h> +#include "sane_ctype.h" + static volatile int done; #define HEADER_LINE_NR 5 @@ -130,7 +134,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) return err; } - err = symbol__disassemble(sym, map, NULL, 0); + err = symbol__disassemble(sym, map, NULL, 0, NULL); if (err == 0) { out_assign: top->sym_filter_entry = he; @@ -643,7 +647,7 @@ repeat: case -1: if (errno == EINTR) continue; - /* Fall trhu */ + __fallthrough; default: c = getc(stdin); tcsetattr(0, TCSAFLUSH, &save); @@ -859,7 +863,7 @@ static void perf_top__mmap_read(struct perf_top *top) static int perf_top__start_counters(struct perf_top *top) { - char msg[512]; + char msg[BUFSIZ]; struct perf_evsel *counter; struct perf_evlist *evlist = top->evlist; struct record_opts *opts = &top->record_opts; @@ -871,7 +875,7 @@ try_again: if (perf_evsel__open(counter, top->evlist->cpus, top->evlist->threads) < 0) { if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { - if (verbose) + if (verbose > 0) ui__warning("%s\n", msg); goto try_again; } @@ -954,7 +958,7 @@ static int __cmd_top(struct perf_top *top) ret = perf_evlist__apply_drv_configs(evlist, &pos, &err_term); if (ret) { - error("failed to set config \"%s\" on event %s with %d (%s)\n", + pr_err("failed to set config \"%s\" on event %s with %d (%s)\n", err_term->val.drv_cfg, perf_evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); goto out_delete; @@ -1075,7 +1079,7 @@ parse_percent_limit(const struct option *opt, const char *arg, const char top_callchain_help[] = CALLCHAIN_RECORD_HELP CALLCHAIN_REPORT_HELP "\n\t\t\t\tDefault: fp,graph,0.5,caller,function"; -int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_top(int argc, const char **argv) { char errbuf[BUFSIZ]; struct perf_top top = { @@ -1216,7 +1220,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (top.evlist == NULL) return -ENOMEM; - perf_config(perf_top_config, &top); + status = perf_config(perf_top_config, &top); + if (status) + return status; argc = parse_options(argc, argv, options, top_usage, 0); if (argc) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 206bf72b77fc..4b2a5d298197 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -21,9 +21,11 @@ #include "builtin.h" #include "util/color.h" #include "util/debug.h" +#include "util/event.h" #include "util/evlist.h" #include <subcmd/exec-cmd.h> #include "util/machine.h" +#include "util/path.h" #include "util/session.h" #include "util/thread.h" #include <subcmd/parse-options.h> @@ -31,22 +33,33 @@ #include "util/intlist.h" #include "util/thread_map.h" #include "util/stat.h" +#include "trace/beauty/beauty.h" #include "trace-event.h" #include "util/parse-events.h" #include "util/bpf-loader.h" #include "callchain.h" +#include "print_binary.h" +#include "string2.h" #include "syscalltbl.h" #include "rb_resort.h" +#include <errno.h> +#include <inttypes.h> #include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */ +#include <poll.h> +#include <signal.h> #include <stdlib.h> +#include <string.h> #include <linux/err.h> #include <linux/filter.h> #include <linux/audit.h> +#include <linux/kernel.h> #include <linux/random.h> #include <linux/stringify.h> #include <linux/time64.h> +#include "sane_ctype.h" + #ifndef O_CLOEXEC # define O_CLOEXEC 02000000 #endif @@ -266,15 +279,6 @@ out_delete: ({ struct syscall_tp *fields = evsel->priv; \ fields->name.pointer(&fields->name, sample); }) -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; @@ -677,6 +681,10 @@ static struct syscall_fmt { { .name = "mlockall", .errmsg = true, .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, }, { .name = "mmap", .hexret = true, +/* The standard mmap maps to old_mmap on s390x */ +#if defined(__s390x__) + .alias = "old_mmap", +#endif .arg_scnprintf = { [0] = SCA_HEX, /* addr */ [2] = SCA_MMAP_PROT, /* prot */ [3] = SCA_MMAP_FLAGS, /* flags */ }, }, @@ -770,6 +778,10 @@ static struct syscall_fmt { .arg_parm = { [0] = &strarray__socket_families, /* family */ }, }, { .name = "stat", .errmsg = true, .alias = "newstat", }, { .name = "statfs", .errmsg = true, }, + { .name = "statx", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* flags */ + [2] = SCA_STATX_FLAGS, /* flags */ + [3] = SCA_STATX_MASK, /* mask */ }, }, { .name = "swapoff", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, }, { .name = "swapon", .errmsg = true, @@ -820,12 +832,21 @@ struct syscall { void **arg_parm; }; -static size_t fprintf_duration(unsigned long t, FILE *fp) +/* + * We need to have this 'calculated' boolean because in some cases we really + * don't know what is the duration of a syscall, for instance, when we start + * a session and some threads are waiting for a syscall to finish, say 'poll', + * in which case all we can do is to print "( ? ) for duration and for the + * start timestamp. + */ +static size_t fprintf_duration(unsigned long t, bool calculated, FILE *fp) { double duration = (double)t / NSEC_PER_MSEC; size_t printed = fprintf(fp, "("); - if (duration >= 1.0) + if (!calculated) + printed += fprintf(fp, " ? "); + else if (duration >= 1.0) printed += color_fprintf(fp, PERF_COLOR_RED, "%6.3f ms", duration); else if (duration >= 0.01) printed += color_fprintf(fp, PERF_COLOR_YELLOW, "%6.3f ms", duration); @@ -1027,13 +1048,27 @@ static bool trace__filter_duration(struct trace *trace, double t) return t < (trace->duration_filter * NSEC_PER_MSEC); } -static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp) +static size_t __trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp) { double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC; return fprintf(fp, "%10.3f ", ts); } +/* + * We're handling tstamp=0 as an undefined tstamp, i.e. like when we are + * using ttrace->entry_time for a thread that receives a sys_exit without + * first having received a sys_enter ("poll" issued before tracing session + * starts, lost sys_enter exit due to ring buffer overflow). + */ +static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp) +{ + if (tstamp > 0) + return __trace__fprintf_tstamp(trace, tstamp, fp); + + return fprintf(fp, " ? "); +} + static bool done = false; static bool interrupted = false; @@ -1044,10 +1079,10 @@ static void sig_handler(int sig) } static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread, - u64 duration, u64 tstamp, FILE *fp) + u64 duration, bool duration_calculated, u64 tstamp, FILE *fp) { size_t printed = trace__fprintf_tstamp(trace, tstamp, fp); - printed += fprintf_duration(duration, fp); + printed += fprintf_duration(duration, duration_calculated, fp); if (trace->multiple_threads) { if (trace->show_comm) @@ -1398,7 +1433,7 @@ static struct syscall *trace__syscall_info(struct trace *trace, return &trace->syscalls.table[id]; out_cant_read: - if (verbose) { + if (verbose > 0) { 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); @@ -1449,7 +1484,7 @@ static int trace__printf_interrupted_entry(struct trace *trace, struct perf_samp duration = sample->time - ttrace->entry_time; - printed = trace__fprintf_entry_head(trace, trace->current, duration, ttrace->entry_time, trace->output); + printed = trace__fprintf_entry_head(trace, trace->current, duration, true, ttrace->entry_time, trace->output); printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str); ttrace->entry_pending = false; @@ -1496,7 +1531,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, if (sc->is_exit) { if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) { - trace__fprintf_entry_head(trace, thread, 1, ttrace->entry_time, trace->output); + trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output); fprintf(trace->output, "%-70s)\n", ttrace->entry_str); } } else { @@ -1544,6 +1579,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, { long ret; u64 duration = 0; + bool duration_calculated = false; struct thread *thread; int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0; struct syscall *sc = trace__syscall_info(trace, evsel, id); @@ -1572,6 +1608,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, duration = sample->time - ttrace->entry_time; if (trace__filter_duration(trace, duration)) goto out; + duration_calculated = true; } else if (trace->duration_filter) goto out; @@ -1587,7 +1624,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, if (trace->summary_only) goto out; - trace__fprintf_entry_head(trace, thread, duration, ttrace->entry_time, trace->output); + trace__fprintf_entry_head(trace, thread, duration, duration_calculated, ttrace->entry_time, trace->output); if (ttrace->entry_pending) { fprintf(trace->output, "%-70s", ttrace->entry_str); @@ -1652,15 +1689,17 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel, ttrace = thread__priv(thread); if (!ttrace) - goto out; + goto out_put; filename_len = strlen(filename); + if (filename_len == 0) + goto out_put; if (ttrace->filename.namelen < filename_len) { char *f = realloc(ttrace->filename.name, filename_len + 1); if (f == NULL) - goto out; + goto out_put; ttrace->filename.namelen = filename_len; ttrace->filename.name = f; @@ -1670,12 +1709,12 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel, ttrace->filename.pending_open = true; if (!ttrace->filename.ptr) - goto out; + goto out_put; entry_str_len = strlen(ttrace->entry_str); remaining_space = trace__entry_str_size - entry_str_len - 1; /* \0 */ if (remaining_space <= 0) - goto out; + goto out_put; if (filename_len > (size_t)remaining_space) { filename += filename_len - remaining_space; @@ -1689,6 +1728,8 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel, ttrace->filename.ptr = 0; ttrace->filename.entry_str_pos = 0; +out_put: + thread__put(thread); out: return 0; } @@ -1709,6 +1750,7 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs ttrace->runtime_ms += runtime_ms; trace->runtime_ms += runtime_ms; +out_put: thread__put(thread); return 0; @@ -1719,8 +1761,7 @@ out_dump: (pid_t)perf_evsel__intval(evsel, sample, "pid"), runtime, perf_evsel__intval(evsel, sample, "vruntime")); - thread__put(thread); - return 0; + goto out_put; } static void bpf_output__printer(enum binary_printer_ops op, @@ -1800,10 +1841,10 @@ static void print_location(FILE *f, struct perf_sample *sample, bool print_dso, bool print_sym) { - if ((verbose || print_dso) && al->map) + if ((verbose > 0 || print_dso) && al->map) fprintf(f, "%s@", al->map->dso->long_name); - if ((verbose || print_sym) && al->sym) + if ((verbose > 0 || print_sym) && al->sym) fprintf(f, "%s+0x%" PRIx64, al->sym->name, al->addr - al->sym->start); else if (al->map) @@ -1850,7 +1891,7 @@ static int trace__pgfault(struct trace *trace, thread__find_addr_location(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al); - trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output); + trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output); fprintf(trace->output, "%sfault [", evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ? @@ -1919,7 +1960,7 @@ static int trace__process_sample(struct perf_tool *tool, thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); if (thread && thread__is_filtered(thread)) - return 0; + goto out; trace__set_base_time(trace, evsel, sample); @@ -1927,7 +1968,8 @@ static int trace__process_sample(struct perf_tool *tool, ++trace->nr_events; handler(trace, evsel, event, sample); } - +out: + thread__put(thread); return err; } @@ -1987,7 +2029,7 @@ static int trace__record(struct trace *trace, int argc, const char **argv) for (i = 0; i < (unsigned int)argc; i++) rec_argv[j++] = argv[i]; - return cmd_record(j, rec_argv, NULL); + return cmd_record(j, rec_argv); } static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); @@ -2414,8 +2456,9 @@ static int trace__replay(struct trace *trace) 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.tracing_data = perf_event__process_tracing_data; trace->tool.build_id = perf_event__process_build_id; + trace->tool.namespaces = perf_event__process_namespaces; trace->tool.ordered_events = true; trace->tool.ordering_requires_timestamps = true; @@ -2699,7 +2742,92 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler) evsel->handler = handler; } -int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) +/* + * XXX: Hackish, just splitting the combined -e+--event (syscalls + * (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use + * existing facilities unchanged (trace->ev_qualifier + parse_options()). + * + * It'd be better to introduce a parse_options() variant that would return a + * list with the terms it didn't match to an event... + */ +static int trace__parse_events_option(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + struct trace *trace = (struct trace *)opt->value; + const char *s = str; + char *sep = NULL, *lists[2] = { NULL, NULL, }; + int len = strlen(str), err = -1, list; + char *strace_groups_dir = system_path(STRACE_GROUPS_DIR); + char group_name[PATH_MAX]; + + if (strace_groups_dir == NULL) + return -1; + + if (*s == '!') { + ++s; + trace->not_ev_qualifier = true; + } + + while (1) { + if ((sep = strchr(s, ',')) != NULL) + *sep = '\0'; + + list = 0; + if (syscalltbl__id(trace->sctbl, s) >= 0) { + list = 1; + } else { + path__join(group_name, sizeof(group_name), strace_groups_dir, s); + if (access(group_name, R_OK) == 0) + list = 1; + } + + if (lists[list]) { + sprintf(lists[list] + strlen(lists[list]), ",%s", s); + } else { + lists[list] = malloc(len); + if (lists[list] == NULL) + goto out; + strcpy(lists[list], s); + } + + if (!sep) + break; + + *sep = ','; + s = sep + 1; + } + + if (lists[1] != NULL) { + struct strlist_config slist_config = { + .dirname = strace_groups_dir, + }; + + trace->ev_qualifier = strlist__new(lists[1], &slist_config); + if (trace->ev_qualifier == NULL) { + fputs("Not enough memory to parse event qualifier", trace->output); + goto out; + } + + if (trace__validate_ev_qualifier(trace)) + goto out; + } + + err = 0; + + if (lists[0]) { + struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event", + "event selector. use 'perf list' to list available events", + parse_events_option); + err = parse_events_option(&o, lists[0], 0); + } +out: + if (sep) + *sep = ','; + + return err; +} + +int cmd_trace(int argc, const char **argv) { const char *trace_usage[] = { "perf trace [<options>] [<command>]", @@ -2730,15 +2858,15 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) .max_stack = UINT_MAX, }; const char *output_name = NULL; - const char *ev_qualifier_str = NULL; const struct option trace_options[] = { - OPT_CALLBACK(0, "event", &trace.evlist, "event", - "event selector. use 'perf list' to list available events", - parse_events_option), + OPT_CALLBACK('e', "event", &trace, "event", + "event/syscall selector. use 'perf list' to list available events", + trace__parse_events_option), 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 syscalls to trace"), + OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace", + trace__parse_events_option), 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", @@ -2863,7 +2991,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) return -1; } - if (!trace.trace_syscalls && ev_qualifier_str) { + if (!trace.trace_syscalls && trace.ev_qualifier) { pr_err("The -e option can't be used with --no-syscalls.\n"); goto out; } @@ -2878,28 +3006,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) trace.open_id = syscalltbl__id(trace.sctbl, "open"); - if (ev_qualifier_str != NULL) { - const char *s = ev_qualifier_str; - struct strlist_config slist_config = { - .dirname = system_path(STRACE_GROUPS_DIR), - }; - - trace.not_ev_qualifier = *s == '!'; - if (trace.not_ev_qualifier) - ++s; - trace.ev_qualifier = strlist__new(s, &slist_config); - if (trace.ev_qualifier == NULL) { - fputs("Not enough memory to parse event qualifier", - trace.output); - err = -ENOMEM; - goto out_close; - } - - err = trace__validate_ev_qualifier(&trace); - if (err) - goto out_close; - } - err = target__validate(&trace.opts.target); if (err) { target__strerror(&trace.opts.target, err, bf, sizeof(bf)); diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index 9b10cda6b6dc..d25149456a2f 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -1,9 +1,9 @@ -#include "util/util.h" #include "builtin.h" #include "perf.h" +#include <linux/compiler.h> +#include <stdio.h> -int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused, - const char *prefix __maybe_unused) +int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused) { printf("perf version %s\n", perf_version_string); return 0; diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 0bcf68e98ccc..d4d19fe3d050 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -2,44 +2,42 @@ #define BUILTIN_H #include "util/util.h" -#include "util/strbuf.h" extern const char perf_usage_string[]; extern const char perf_more_info_string[]; void list_common_cmds_help(void); const char *help_unknown_cmd(const char *cmd); -void prune_packed_objects(int); -int read_line_with_nul(char *buf, int size, FILE *file); -int check_pager_config(const char *cmd); -int cmd_annotate(int argc, const char **argv, const char *prefix); -int cmd_bench(int argc, const char **argv, const char *prefix); -int cmd_buildid_cache(int argc, const char **argv, const char *prefix); -int cmd_buildid_list(int argc, const char **argv, const char *prefix); -int cmd_config(int argc, const char **argv, const char *prefix); -int cmd_c2c(int argc, const char **argv, const char *prefix); -int cmd_diff(int argc, const char **argv, const char *prefix); -int cmd_evlist(int argc, const char **argv, const char *prefix); -int cmd_help(int argc, const char **argv, const char *prefix); -int cmd_sched(int argc, const char **argv, const char *prefix); -int cmd_list(int argc, const char **argv, const char *prefix); -int cmd_record(int argc, const char **argv, const char *prefix); -int cmd_report(int argc, const char **argv, const char *prefix); -int cmd_stat(int argc, const char **argv, const char *prefix); -int cmd_timechart(int argc, const char **argv, const char *prefix); -int cmd_top(int argc, const char **argv, const char *prefix); -int cmd_script(int argc, const char **argv, const char *prefix); -int cmd_version(int argc, const char **argv, const char *prefix); -int cmd_probe(int argc, const char **argv, const char *prefix); -int cmd_kmem(int argc, const char **argv, const char *prefix); -int cmd_lock(int argc, const char **argv, const char *prefix); -int cmd_kvm(int argc, const char **argv, const char *prefix); -int cmd_test(int argc, const char **argv, const char *prefix); -int cmd_trace(int argc, const char **argv, const char *prefix); -int cmd_inject(int argc, const char **argv, const char *prefix); -int cmd_mem(int argc, const char **argv, const char *prefix); -int cmd_data(int argc, const char **argv, const char *prefix); +int cmd_annotate(int argc, const char **argv); +int cmd_bench(int argc, const char **argv); +int cmd_buildid_cache(int argc, const char **argv); +int cmd_buildid_list(int argc, const char **argv); +int cmd_config(int argc, const char **argv); +int cmd_c2c(int argc, const char **argv); +int cmd_diff(int argc, const char **argv); +int cmd_evlist(int argc, const char **argv); +int cmd_help(int argc, const char **argv); +int cmd_sched(int argc, const char **argv); +int cmd_kallsyms(int argc, const char **argv); +int cmd_list(int argc, const char **argv); +int cmd_record(int argc, const char **argv); +int cmd_report(int argc, const char **argv); +int cmd_stat(int argc, const char **argv); +int cmd_timechart(int argc, const char **argv); +int cmd_top(int argc, const char **argv); +int cmd_script(int argc, const char **argv); +int cmd_version(int argc, const char **argv); +int cmd_probe(int argc, const char **argv); +int cmd_kmem(int argc, const char **argv); +int cmd_lock(int argc, const char **argv); +int cmd_kvm(int argc, const char **argv); +int cmd_test(int argc, const char **argv); +int cmd_trace(int argc, const char **argv); +int cmd_inject(int argc, const char **argv); +int cmd_mem(int argc, const char **argv); +int cmd_data(int argc, const char **argv); +int cmd_ftrace(int argc, const char **argv); int find_scripts(char **scripts_array, char **scripts_path_array); #endif diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index c747bfd7f14d..83fe2202382e 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -1,7 +1,9 @@ #!/bin/sh HEADERS=' +include/uapi/linux/fcntl.h include/uapi/linux/perf_event.h +include/uapi/linux/stat.h include/linux/hash.h include/uapi/linux/hw_breakpoint.h arch/x86/include/asm/disabled-features.h diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index ab5cbaa170d0..2d0caf20ff3a 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -9,9 +9,12 @@ perf-buildid-cache mainporcelain common perf-buildid-list mainporcelain common perf-data mainporcelain common perf-diff mainporcelain common +perf-c2c mainporcelain common perf-config mainporcelain common perf-evlist mainporcelain common +perf-ftrace mainporcelain common perf-inject mainporcelain common +perf-kallsyms mainporcelain common perf-kmem mainporcelain common perf-kvm mainporcelain common perf-list mainporcelain common diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index e9651a9d670e..cf36de7ea255 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -304,7 +304,7 @@ jvmti_close(void *agent) FILE *fp = agent; if (!fp) { - warnx("jvmti: incalid fd in close_agent"); + warnx("jvmti: invalid fd in close_agent"); return -1; } diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h index bedf5d0ba9ff..c53a41f48b63 100644 --- a/tools/perf/jvmti/jvmti_agent.h +++ b/tools/perf/jvmti/jvmti_agent.h @@ -5,8 +5,6 @@ #include <stdint.h> #include <jvmti.h> -#define __unused __attribute__((unused)) - #if defined(__cplusplus) extern "C" { #endif diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c index 5612641c69b4..6d710904c837 100644 --- a/tools/perf/jvmti/libjvmti.c +++ b/tools/perf/jvmti/libjvmti.c @@ -1,3 +1,4 @@ +#include <linux/compiler.h> #include <sys/types.h> #include <stdio.h> #include <string.h> @@ -238,7 +239,7 @@ code_generated_cb(jvmtiEnv *jvmti, } JNIEXPORT jint JNICALL -Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __unused) +Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __maybe_unused) { jvmtiEventCallbacks cb; jvmtiCapabilities caps1; @@ -313,7 +314,7 @@ Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __unused) } JNIEXPORT void JNICALL -Agent_OnUnload(JavaVM *jvm __unused) +Agent_OnUnload(JavaVM *jvm __maybe_unused) { int ret; diff --git a/tools/perf/perf.c b/tools/perf/perf.c index aa23b3347d6b..628a5e412cb1 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -17,11 +17,18 @@ #include <subcmd/parse-options.h> #include "util/bpf-loader.h" #include "util/debug.h" +#include "util/event.h" #include <api/fs/fs.h> #include <api/fs/tracing_path.h> +#include <errno.h> #include <pthread.h> +#include <signal.h> #include <stdlib.h> #include <time.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <linux/kernel.h> const char perf_usage_string[] = "perf [--version] [--help] [OPTIONS] COMMAND [ARGS]"; @@ -29,13 +36,12 @@ const char perf_usage_string[] = const char perf_more_info_string[] = "See 'perf help COMMAND' for more information on a specific command."; -int use_browser = -1; static int use_pager = -1; const char *input_name; struct cmd_struct { const char *cmd; - int (*fn)(int, const char **, const char *); + int (*fn)(int, const char **); int option; }; @@ -47,6 +53,7 @@ static struct cmd_struct commands[] = { { "diff", cmd_diff, 0 }, { "evlist", cmd_evlist, 0 }, { "help", cmd_help, 0 }, + { "kallsyms", cmd_kallsyms, 0 }, { "list", cmd_list, 0 }, { "record", cmd_record, 0 }, { "report", cmd_report, 0 }, @@ -71,6 +78,7 @@ static struct cmd_struct commands[] = { { "inject", cmd_inject, 0 }, { "mem", cmd_mem, 0 }, { "data", cmd_data, 0 }, + { "ftrace", cmd_ftrace, 0 }, }; struct pager_config { @@ -87,13 +95,14 @@ static int pager_command_config(const char *var, const char *value, void *data) } /* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */ -int check_pager_config(const char *cmd) +static int check_pager_config(const char *cmd) { + int err; struct pager_config c; c.cmd = cmd; c.val = -1; - perf_config(pager_command_config, &c); - return c.val; + err = perf_config(pager_command_config, &c); + return err ?: c.val; } static int browser_command_config(const char *var, const char *value, void *data) @@ -112,11 +121,12 @@ static int browser_command_config(const char *var, const char *value, void *data */ static int check_browser_config(const char *cmd) { + int err; struct pager_config c; c.cmd = cmd; c.val = -1; - perf_config(browser_command_config, &c); - return c.val; + err = perf_config(browser_command_config, &c); + return err ?: c.val; } static void commit_pager_choice(void) @@ -264,73 +274,6 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) return handled; } -static int handle_alias(int *argcp, const char ***argv) -{ - int envchanged = 0, ret = 0, saved_errno = errno; - int count, option_count; - const char **new_argv; - const char *alias_command; - char *alias_string; - - alias_command = (*argv)[0]; - alias_string = alias_lookup(alias_command); - if (alias_string) { - if (alias_string[0] == '!') { - if (*argcp > 1) { - struct strbuf buf; - - if (strbuf_init(&buf, PATH_MAX) < 0 || - strbuf_addstr(&buf, alias_string) < 0 || - sq_quote_argv(&buf, (*argv) + 1, - PATH_MAX) < 0) - die("Failed to allocate memory."); - free(alias_string); - alias_string = buf.buf; - } - ret = system(alias_string + 1); - if (ret >= 0 && WIFEXITED(ret) && - WEXITSTATUS(ret) != 127) - exit(WEXITSTATUS(ret)); - die("Failed to run '%s' when expanding alias '%s'", - alias_string + 1, alias_command); - } - count = split_cmdline(alias_string, &new_argv); - if (count < 0) - die("Bad alias.%s string", alias_command); - option_count = handle_options(&new_argv, &count, &envchanged); - if (envchanged) - die("alias '%s' changes environment variables\n" - "You can use '!perf' in the alias to do this.", - alias_command); - memmove(new_argv - option_count, new_argv, - count * sizeof(char *)); - new_argv -= option_count; - - if (count < 1) - die("empty alias for %s", alias_command); - - if (!strcmp(alias_command, new_argv[0])) - die("recursive alias: %s", alias_command); - - new_argv = realloc(new_argv, sizeof(char *) * - (count + *argcp + 1)); - /* insert after command name */ - memcpy(new_argv + count, *argv + 1, sizeof(char *) * *argcp); - new_argv[count + *argcp] = NULL; - - *argv = new_argv; - *argcp += count - 1; - - ret = 1; - } - - errno = saved_errno; - - return ret; -} - -const char perf_version_string[] = PERF_VERSION; - #define RUN_SETUP (1<<0) #define USE_PAGER (1<<1) @@ -338,13 +281,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) { int status; struct stat st; - const char *prefix; char sbuf[STRERR_BUFSIZE]; - prefix = NULL; - if (p->option & RUN_SETUP) - prefix = NULL; /* setup_perf_directory(); */ - if (use_browser == -1) use_browser = check_browser_config(p->cmd); @@ -355,7 +293,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) commit_pager_choice(); perf_env__set_cmdline(&perf_env, argc, argv); - status = p->fn(argc, argv, prefix); + status = p->fn(argc, argv); perf_config__exit(); exit_browser(status); perf_env__exit(&perf_env); @@ -396,16 +334,6 @@ static void handle_internal_command(int argc, const char **argv) { const char *cmd = argv[0]; unsigned int i; - static const char ext[] = STRIP_EXTENSION; - - if (sizeof(ext) > 1) { - i = strlen(argv[0]) - strlen(ext); - if (i > 0 && !strcmp(argv[0] + i, ext)) { - char *argv0 = strdup(argv[0]); - argv[0] = cmd = argv0; - argv0[i] = '\0'; - } - } /* Turn "perf cmd --help" into "perf help cmd" */ if (argc > 1 && !strcmp(argv[1], "--help")) { @@ -447,7 +375,8 @@ static void execv_dashed_external(const char **argv) if (status != -ERR_RUN_COMMAND_EXEC) { if (IS_RUN_COMMAND_ERR(status)) { do_die: - die("unable to run '%s'", argv[0]); + pr_err("FATAL: unable to run '%s'", argv[0]); + status = -128; } exit(-status); } @@ -459,25 +388,12 @@ do_die: static int run_argv(int *argcp, const char ***argv) { - int done_alias = 0; - - while (1) { - /* See if it's an internal command */ - handle_internal_command(*argcp, *argv); + /* See if it's an internal command */ + handle_internal_command(*argcp, *argv); - /* .. then try the external ones */ - execv_dashed_external(*argv); - - /* It could be an alias -- this works around the insanity - * of overriding "perf log" with "perf show" by having - * alias.log = show - */ - if (done_alias || !handle_alias(argcp, argv)) - break; - done_alias = 1; - } - - return done_alias; + /* .. then try the external ones */ + execv_dashed_external(*argv); + return 0; } static void pthread__block_sigwinch(void) @@ -510,6 +426,7 @@ static void cache_line_size(int *cacheline_sizep) int main(int argc, const char **argv) { + int err; const char *cmd; char sbuf[STRERR_BUFSIZE]; int value; @@ -535,7 +452,9 @@ int main(int argc, const char **argv) srandom(time(NULL)); perf_config__init(); - perf_config(perf_default_config, NULL); + err = perf_config(perf_default_config, NULL); + if (err) + return err; set_buildid_dir(NULL); /* get debugfs/tracefs mount point from /proc/mounts */ @@ -562,7 +481,7 @@ int main(int argc, const char **argv) #ifdef HAVE_LIBAUDIT_SUPPORT setup_path(); argv[0] = "trace"; - return cmd_trace(argc, argv, NULL); + return cmd_trace(argc, argv); #else fprintf(stderr, "trace command not available: missing audit-libs devel package at build time.\n"); @@ -607,17 +526,12 @@ int main(int argc, const char **argv) while (1) { static int done_help; - int was_alias = run_argv(&argc, &argv); + + run_argv(&argc, &argv); if (errno != ENOENT) break; - if (was_alias) { - fprintf(stderr, "Expansion of alias '%s' failed; " - "'%s' is not a perf-command\n", - cmd, argv[0]); - goto out; - } if (!done_help) { cmd = argv[0] = help_unknown_cmd(cmd); done_help = 1; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 1c27d947c2fe..806c216a1078 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -50,6 +50,7 @@ struct record_opts { bool running_time; bool full_auxtrace; bool auxtrace_snapshot_mode; + bool record_namespaces; bool record_switch_events; bool all_kernel; bool all_user; diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build index 9213a1273697..999a4e878162 100644 --- a/tools/perf/pmu-events/Build +++ b/tools/perf/pmu-events/Build @@ -2,7 +2,7 @@ hostprogs := jevents jevents-y += json.o jsmn.o jevents.o pmu-events-y += pmu-events.o -JDIR = pmu-events/arch/$(ARCH) +JDIR = pmu-events/arch/$(SRCARCH) JSON = $(shell [ -d $(JDIR) ] && \ find $(JDIR) -name '*.json' -o -name 'mapfile.csv') # @@ -10,4 +10,4 @@ JSON = $(shell [ -d $(JDIR) ] && \ # directory and create tables in pmu-events.c. # $(OUTPUT)pmu-events/pmu-events.c: $(JSON) $(JEVENTS) - $(Q)$(call echo-cmd,gen)$(JEVENTS) $(ARCH) pmu-events/arch $(OUTPUT)pmu-events/pmu-events.c $(V) + $(Q)$(call echo-cmd,gen)$(JEVENTS) $(SRCARCH) pmu-events/arch $(OUTPUT)pmu-events/pmu-events.c $(V) diff --git a/tools/perf/pmu-events/arch/x86/broadwell/uncore.json b/tools/perf/pmu-events/arch/x86/broadwell/uncore.json new file mode 100644 index 000000000000..28e1e159a3cb --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwell/uncore.json @@ -0,0 +1,278 @@ +[ + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x41", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x81", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x44", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x48", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x11", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M", + "BriefDescription": "L3 Lookup read request that access cache and found line in M-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x21", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M", + "BriefDescription": "L3 Lookup write request that access cache and found line in M-state", + "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x81", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M", + "BriefDescription": "L3 Lookup any request that access cache and found line in M-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x18", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I", + "BriefDescription": "L3 Lookup read request that access cache and found line in I-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x88", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I", + "BriefDescription": "L3 Lookup any request that access cache and found line in I-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x1f", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI", + "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x2f", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI", + "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state", + "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x8f", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI", + "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x86", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES", + "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x16", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES", + "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x26", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES", + "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state", + "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "Counter": "0,", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x80", + "UMask": "0x02", + "EventName": "UNC_ARB_TRK_OCCUPANCY.DRD_DIRECT", + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.", + "PublicDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.", + "Counter": "0,", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x02", + "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT", + "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode", + "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x20", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x84", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;", + "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0,", + "CounterMask": "1", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "NCU", + "EventCode": "0x0", + "UMask": "0x01", + "EventName": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles", + "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "FIXED", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json new file mode 100644 index 000000000000..58ed6d33d1f4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json @@ -0,0 +1,317 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory)", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "filter_opc=0x187,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "filter_opc=0x18f,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", + "Filter": "filter_opc=0x190", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x191", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", + "Filter": "filter_opc=0x192", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x180,filter_tid=0x3e", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x181", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache along with writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache with no writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line response from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line forwarded from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json new file mode 100644 index 000000000000..f4b0745cdbbf --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json @@ -0,0 +1,86 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_DCLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_DCLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_DCLOCKTICKS) * 100.", + "MetricName": "power_critical_throttle_cycles %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_DCLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charges due to page misses", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json new file mode 100644 index 000000000000..dd1b95655d1d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json @@ -0,0 +1,92 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c0 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c3 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c6 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "prochot_external_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_limit_thermal_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_os_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_power_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x74", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_trans_cycles %", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json new file mode 100644 index 000000000000..58ed6d33d1f4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json @@ -0,0 +1,317 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory)", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "filter_opc=0x187,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "filter_opc=0x18f,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", + "Filter": "filter_opc=0x190", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x191", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", + "Filter": "filter_opc=0x192", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x180,filter_tid=0x3e", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x181", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache along with writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache with no writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line response from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line forwarded from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json new file mode 100644 index 000000000000..824961318c1e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json @@ -0,0 +1,28 @@ +[ + { + "BriefDescription": "QPI clock ticks", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", + "Counter": "0,1,2,3", + "EventName": "QPI_DATA_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data", + "Counter": "0,1,2,3", + "EventName": "QPI_CTL_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json new file mode 100644 index 000000000000..66eed399724c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json @@ -0,0 +1,86 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_critical_throttle_cycles %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charges due to page misses", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json new file mode 100644 index 000000000000..dd1b95655d1d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json @@ -0,0 +1,92 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c0 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c3 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c6 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "prochot_external_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_limit_thermal_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_os_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_power_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x74", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_trans_cycles %", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/uncore.json b/tools/perf/pmu-events/arch/x86/haswell/uncore.json new file mode 100644 index 000000000000..3ef5c21fef56 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/uncore.json @@ -0,0 +1,374 @@ +[ + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x21", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EXTERNAL", + "BriefDescription": "An external snoop misses in some processor core.", + "PublicDescription": "An external snoop misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x41", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x81", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x24", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EXTERNAL", + "BriefDescription": "An external snoop hits a non-modified line in some processor core.", + "PublicDescription": "An external snoop hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x44", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x84", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EVICTION", + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.", + "PublicDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x28", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EXTERNAL", + "BriefDescription": "An external snoop hits a modified line in some processor core.", + "PublicDescription": "An external snoop hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x48", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x88", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EVICTION", + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.", + "PublicDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x11", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M", + "BriefDescription": "L3 Lookup read request that access cache and found line in M-state.", + "PublicDescription": "L3 Lookup read request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x21", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M", + "BriefDescription": "L3 Lookup write request that access cache and found line in M-state.", + "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x41", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_M", + "BriefDescription": "L3 Lookup external snoop request that access cache and found line in M-state.", + "PublicDescription": "L3 Lookup external snoop request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x81", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M", + "BriefDescription": "L3 Lookup any request that access cache and found line in M-state.", + "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x18", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I", + "BriefDescription": "L3 Lookup read request that access cache and found line in I-state.", + "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x28", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_I", + "BriefDescription": "L3 Lookup write request that access cache and found line in I-state.", + "PublicDescription": "L3 Lookup write request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x48", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_I", + "BriefDescription": "L3 Lookup external snoop request that access cache and found line in I-state.", + "PublicDescription": "L3 Lookup external snoop request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x88", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I", + "BriefDescription": "L3 Lookup any request that access cache and found line in I-state.", + "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x1f", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI", + "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", + "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x2f", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI", + "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state.", + "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x4f", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_MESI", + "BriefDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.", + "PublicDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x8f", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI", + "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state.", + "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x86", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES", + "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state.", + "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x46", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_ES", + "BriefDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.", + "PublicDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x16", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES", + "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state.", + "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x26", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES", + "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state.", + "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x20", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x83", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.All", + "BriefDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory)", + "PublicDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory).", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x84", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "NCU", + "EventCode": "0x0", + "UMask": "0x01", + "EventName": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "FIXED", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json new file mode 100644 index 000000000000..58ed6d33d1f4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json @@ -0,0 +1,317 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory)", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "filter_opc=0x187,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "filter_opc=0x18f,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", + "Filter": "filter_opc=0x190", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x191", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", + "Filter": "filter_opc=0x192", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x180,filter_tid=0x3e", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x181", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache along with writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache with no writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line response from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line forwarded from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json new file mode 100644 index 000000000000..824961318c1e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json @@ -0,0 +1,28 @@ +[ + { + "BriefDescription": "QPI clock ticks", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", + "Counter": "0,1,2,3", + "EventName": "QPI_DATA_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data", + "Counter": "0,1,2,3", + "EventName": "QPI_CTL_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json new file mode 100644 index 000000000000..66eed399724c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json @@ -0,0 +1,86 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_critical_throttle_cycles %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charges due to page misses", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json new file mode 100644 index 000000000000..dd1b95655d1d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json @@ -0,0 +1,92 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c0 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c3 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c6 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "prochot_external_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_limit_thermal_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_os_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_power_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x74", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_trans_cycles %", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/uncore.json b/tools/perf/pmu-events/arch/x86/ivybridge/uncore.json new file mode 100644 index 000000000000..42c70eed05a2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivybridge/uncore.json @@ -0,0 +1,314 @@ +[ + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x01", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS", + "BriefDescription": "A snoop misses in some processor core.", + "PublicDescription": "A snoop misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x02", + "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL", + "BriefDescription": "A snoop invalidates a non-modified line in some processor core.", + "PublicDescription": "A snoop invalidates a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x04", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT", + "BriefDescription": "A snoop hits a non-modified line in some processor core.", + "PublicDescription": "A snoop hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x08", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM", + "BriefDescription": "A snoop hits a modified line in some processor core.", + "PublicDescription": "A snoop hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x10", + "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL_M", + "BriefDescription": "A snoop invalidates a modified line in some processor core.", + "PublicDescription": "A snoop invalidates a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x20", + "EventName": "UNC_CBO_XSNP_RESPONSE.EXTERNAL_FILTER", + "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.", + "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x40", + "EventName": "UNC_CBO_XSNP_RESPONSE.XCORE_FILTER", + "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.", + "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x80", + "EventName": "UNC_CBO_XSNP_RESPONSE.EVICTION_FILTER", + "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.", + "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x01", + "EventName": "UNC_CBO_CACHE_LOOKUP.M", + "BriefDescription": "LLC lookup request that access cache and found line in M-state.", + "PublicDescription": "LLC lookup request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x02", + "EventName": "UNC_CBO_CACHE_LOOKUP.E", + "BriefDescription": "LLC lookup request that access cache and found line in E-state.", + "PublicDescription": "LLC lookup request that access cache and found line in E-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x04", + "EventName": "UNC_CBO_CACHE_LOOKUP.S", + "BriefDescription": "LLC lookup request that access cache and found line in S-state.", + "PublicDescription": "LLC lookup request that access cache and found line in S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x08", + "EventName": "UNC_CBO_CACHE_LOOKUP.I", + "BriefDescription": "LLC lookup request that access cache and found line in I-state.", + "PublicDescription": "LLC lookup request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x10", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_FILTER", + "BriefDescription": "Filter on processor core initiated cacheable read requests.", + "PublicDescription": "Filter on processor core initiated cacheable read requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x20", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_FILTER", + "BriefDescription": "Filter on processor core initiated cacheable write requests.", + "PublicDescription": "Filter on processor core initiated cacheable write requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x40", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_FILTER", + "BriefDescription": "Filter on external snoop requests.", + "PublicDescription": "Filter on external snoop requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x80", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_REQUEST_FILTER", + "BriefDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.", + "PublicDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "BriefDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "PublicDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x81", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "PublicDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x81", + "UMask": "0x20", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "BriefDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.", + "PublicDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x81", + "UMask": "0x80", + "EventName": "UNC_ARB_TRK_REQUESTS.EVICTIONS", + "BriefDescription": "Counts the number of LLC evictions allocated.", + "PublicDescription": "Counts the number of LLC evictions allocated.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x83", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.ALL", + "BriefDescription": "Cycles weighted by number of requests pending in Coherency Tracker.", + "PublicDescription": "Cycles weighted by number of requests pending in Coherency Tracker.", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x84", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "BriefDescription": "Number of requests allocated in Coherency Tracker.", + "PublicDescription": "Number of requests allocated in Coherency Tracker.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0,1", + "CounterMask": "1", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_OVER_HALF_FULL", + "BriefDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "PublicDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0,1", + "CounterMask": "10", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x0", + "UMask": "0x01", + "EventName": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "Fixed", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x06", + "EventName": "UNC_CBO_CACHE_LOOKUP.ES", + "BriefDescription": "LLC lookup request that access cache and found line in E-state or S-state.", + "PublicDescription": "LLC lookup request that access cache and found line in E-state or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json new file mode 100644 index 000000000000..267410594833 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json @@ -0,0 +1,322 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory)", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode.rfo_prefetch", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", + "Filter": "filter_opc=0x190", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode.code", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x191", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode.data_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", + "Filter": "filter_opc=0x192", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe non-snoop reads. Derived from unc_c_tor_inserts.miss_opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_READ", + "Filter": "filter_opc=0x1e4", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.miss_opcode.pcie_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", + "Filter": "filter_opc=0x1e6", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ", + "Filter": "filter_opc=0x195", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_READ", + "Filter": "filter_opc=0x1e4", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x1e5", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_WRITE", + "Filter": "filter_opc=0x1e6", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL", + "PerPkg": "1", + "UMask": "0x2A", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE", + "PerPkg": "1", + "UMask": "0x8A", + "Unit": "CBO" + }, + { + "BriefDescription": "Read requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "Write requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache along with writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache with no writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line response from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line forwarded from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json new file mode 100644 index 000000000000..b798a860bc81 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json @@ -0,0 +1,48 @@ +[ + { + "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where receiving QPI link is in half-width mode", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "MetricName": "rxl0p_power_cycles %", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where transmitting QPI link is in half-width mode", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_Q_TxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "MetricName": "txl0p_power_cycles %", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted ", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted ", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json new file mode 100644 index 000000000000..df4b43294fa0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json @@ -0,0 +1,78 @@ +[ + { + "BriefDescription": "Memory page activates for reads and writes", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT.RD", + "PerPkg": "1", + "UMask": "0x1", + "Umask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "Read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "Write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_critical_throttle_cycles %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory page conflicts", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json new file mode 100644 index 000000000000..d40498f2cb1e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json @@ -0,0 +1,274 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band0_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band1_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band2_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band3_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band0_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band1_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band2_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band3_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c0 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c3 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c6 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip", + "Counter": "0,1,2,3", + "EventCode": "0xa", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "prochot_external_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_limit_thermal_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_os_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_power_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_current_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency", + "Counter": "0,1,2,3", + "EventCode": "0x60", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_trans_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES", + "Filter": "filter_band0=1200", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_1200mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES", + "Filter": "filter_band1=2000", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_2000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES", + "Filter": "filter_band2=3000", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_3000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES", + "Filter": "filter_band3=4000", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_4000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band0=1200", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_1200mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band1=2000", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_2000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band2=4000", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_3000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band3=4000", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_4000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json new file mode 100644 index 000000000000..3fa61d962607 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json @@ -0,0 +1,210 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory)", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ", + "Filter": "filter_opc=0x195", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_READ", + "Filter": "filter_opc=0x1e4", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x1e5", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_WRITE", + "Filter": "filter_opc=0x1e6", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL", + "Filter": "filter_opc=0x182", + "MetricExpr": "(UNC_C_TOR_OCCUPANCY.MISS_ALL / UNC_C_CLOCKTICKS) * 100.", + "MetricName": "tor_occupancy.miss_all %", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json new file mode 100644 index 000000000000..1b53c0e609e3 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json @@ -0,0 +1,48 @@ +[ + { + "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where receiving QPI link is in half-width mode", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "MetricName": "rxl0p_power_cycles %", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where transmitting QPI link is in half-width mode", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_Q_TxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "MetricName": "txl0p_power_cycles %", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted ", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted ", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json new file mode 100644 index 000000000000..8551cebeba23 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json @@ -0,0 +1,82 @@ +[ + { + "BriefDescription": "Memory page activates", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_critical_throttle_cycles %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory page conflicts", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Occupancy counter for memory read queue", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_M_RPQ_OCCUPANCY", + "PerPkg": "1", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json new file mode 100644 index 000000000000..16034bfd06dd --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json @@ -0,0 +1,273 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band0_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band1_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band2_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band3_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band0_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transistioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band1_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band2_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band3_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c0 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c3 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c6 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip", + "Counter": "0,1,2,3", + "EventCode": "0xa", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "prochot_external_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_limit_thermal_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_os_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_power_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_current_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency", + "Counter": "0,1,2,3", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_trans_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES", + "Filter": "filter_band0=1200", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_1200mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES", + "Filter": "filter_band1=2000", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_2000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES", + "Filter": "filter_band2=3000", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_3000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES", + "Filter": "filter_band3=4000", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_4000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band0=1200", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_1200mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band1=2000", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_2000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band2=4000", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_3000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band3=4000", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_4000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json new file mode 100644 index 000000000000..e3bcd86c4f56 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json @@ -0,0 +1,42 @@ +[ + { + "BriefDescription": "ddr bandwidth read (CPU traffic only) (MB/sec). ", + "Counter": "0,1,2,3", + "EventCode": "0x03", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "ScaleUnit": "6.4e-05MiB", + "UMask": "0x01", + "Unit": "imc" + }, + { + "BriefDescription": "ddr bandwidth write (CPU traffic only) (MB/sec). ", + "Counter": "0,1,2,3", + "EventCode": "0x03", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "ScaleUnit": "6.4e-05MiB", + "UMask": "0x02", + "Unit": "imc" + }, + { + "BriefDescription": "mcdram bandwidth read (CPU traffic only) (MB/sec). ", + "Counter": "0,1,2,3", + "EventCode": "0x01", + "EventName": "UNC_E_RPQ_INSERTS", + "PerPkg": "1", + "ScaleUnit": "6.4e-05MiB", + "UMask": "0x01", + "Unit": "edc_eclk" + }, + { + "BriefDescription": "mcdram bandwidth write (CPU traffic only) (MB/sec). ", + "Counter": "0,1,2,3", + "EventCode": "0x02", + "EventName": "UNC_E_WPQ_INSERTS", + "PerPkg": "1", + "ScaleUnit": "6.4e-05MiB", + "UMask": "0x01", + "Unit": "edc_eclk" + } +] diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 12181bb1da2a..d1a12e584c1b 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -17,6 +17,7 @@ GenuineIntel-6-3A,v18,ivybridge,core GenuineIntel-6-3E,v19,ivytown,core GenuineIntel-6-2D,v20,jaketown,core GenuineIntel-6-57,v9,knightslanding,core +GenuineIntel-6-85,v9,knightslanding,core GenuineIntel-6-1E,v2,nehalemep,core GenuineIntel-6-1F,v2,nehalemep,core GenuineIntel-6-1A,v2,nehalemep,core diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/uncore.json b/tools/perf/pmu-events/arch/x86/sandybridge/uncore.json new file mode 100644 index 000000000000..42c70eed05a2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sandybridge/uncore.json @@ -0,0 +1,314 @@ +[ + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x01", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS", + "BriefDescription": "A snoop misses in some processor core.", + "PublicDescription": "A snoop misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x02", + "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL", + "BriefDescription": "A snoop invalidates a non-modified line in some processor core.", + "PublicDescription": "A snoop invalidates a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x04", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT", + "BriefDescription": "A snoop hits a non-modified line in some processor core.", + "PublicDescription": "A snoop hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x08", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM", + "BriefDescription": "A snoop hits a modified line in some processor core.", + "PublicDescription": "A snoop hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x10", + "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL_M", + "BriefDescription": "A snoop invalidates a modified line in some processor core.", + "PublicDescription": "A snoop invalidates a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x20", + "EventName": "UNC_CBO_XSNP_RESPONSE.EXTERNAL_FILTER", + "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.", + "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x40", + "EventName": "UNC_CBO_XSNP_RESPONSE.XCORE_FILTER", + "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.", + "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x80", + "EventName": "UNC_CBO_XSNP_RESPONSE.EVICTION_FILTER", + "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.", + "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x01", + "EventName": "UNC_CBO_CACHE_LOOKUP.M", + "BriefDescription": "LLC lookup request that access cache and found line in M-state.", + "PublicDescription": "LLC lookup request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x02", + "EventName": "UNC_CBO_CACHE_LOOKUP.E", + "BriefDescription": "LLC lookup request that access cache and found line in E-state.", + "PublicDescription": "LLC lookup request that access cache and found line in E-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x04", + "EventName": "UNC_CBO_CACHE_LOOKUP.S", + "BriefDescription": "LLC lookup request that access cache and found line in S-state.", + "PublicDescription": "LLC lookup request that access cache and found line in S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x08", + "EventName": "UNC_CBO_CACHE_LOOKUP.I", + "BriefDescription": "LLC lookup request that access cache and found line in I-state.", + "PublicDescription": "LLC lookup request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x10", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_FILTER", + "BriefDescription": "Filter on processor core initiated cacheable read requests.", + "PublicDescription": "Filter on processor core initiated cacheable read requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x20", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_FILTER", + "BriefDescription": "Filter on processor core initiated cacheable write requests.", + "PublicDescription": "Filter on processor core initiated cacheable write requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x40", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_FILTER", + "BriefDescription": "Filter on external snoop requests.", + "PublicDescription": "Filter on external snoop requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x80", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_REQUEST_FILTER", + "BriefDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.", + "PublicDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "BriefDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "PublicDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x81", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "PublicDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x81", + "UMask": "0x20", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "BriefDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.", + "PublicDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x81", + "UMask": "0x80", + "EventName": "UNC_ARB_TRK_REQUESTS.EVICTIONS", + "BriefDescription": "Counts the number of LLC evictions allocated.", + "PublicDescription": "Counts the number of LLC evictions allocated.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x83", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.ALL", + "BriefDescription": "Cycles weighted by number of requests pending in Coherency Tracker.", + "PublicDescription": "Cycles weighted by number of requests pending in Coherency Tracker.", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x84", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "BriefDescription": "Number of requests allocated in Coherency Tracker.", + "PublicDescription": "Number of requests allocated in Coherency Tracker.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0,1", + "CounterMask": "1", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_OVER_HALF_FULL", + "BriefDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "PublicDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0,1", + "CounterMask": "10", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x0", + "UMask": "0x01", + "EventName": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "Fixed", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x06", + "EventName": "UNC_CBO_CACHE_LOOKUP.ES", + "BriefDescription": "LLC lookup request that access cache and found line in E-state or S-state.", + "PublicDescription": "LLC lookup request that access cache and found line in E-state or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/uncore.json b/tools/perf/pmu-events/arch/x86/skylake/uncore.json new file mode 100644 index 000000000000..dbc193252fb3 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylake/uncore.json @@ -0,0 +1,254 @@ +[ + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x41", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x81", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x44", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x48", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x21", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M", + "BriefDescription": "L3 Lookup write request that access cache and found line in M-state", + "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x81", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M", + "BriefDescription": "L3 Lookup any request that access cache and found line in M-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x18", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I", + "BriefDescription": "L3 Lookup read request that access cache and found line in I-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x88", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I", + "BriefDescription": "L3 Lookup any request that access cache and found line in I-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x1f", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI", + "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x2f", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI", + "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state", + "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x8f", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI", + "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x86", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES", + "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x16", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES", + "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x26", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES", + "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state", + "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x02", + "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT", + "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode", + "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x20", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x84", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;", + "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0", + "CounterMask": "1", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "NCU", + "EventCode": "0x0", + "UMask": "0x01", + "EventName": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles", + "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "FIXED", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 41611d7f9873..bd0aabb2bd0f 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -48,10 +48,6 @@ #include "json.h" #include "jevents.h" -#ifndef __maybe_unused -#define __maybe_unused __attribute__((unused)) -#endif - int verbose; char *prog; @@ -135,7 +131,6 @@ static struct field { const char *field; const char *kernel; } fields[] = { - { "EventCode", "event=" }, { "UMask", "umask=" }, { "CounterMask", "cmask=" }, { "Invert", "inv=" }, @@ -189,6 +184,28 @@ static struct msrmap *lookup_msr(char *map, jsmntok_t *val) return NULL; } +static struct map { + const char *json; + const char *perf; +} unit_to_pmu[] = { + { "CBO", "uncore_cbox" }, + { "QPI LL", "uncore_qpi" }, + { "SBO", "uncore_sbox" }, + { "iMPH-U", "uncore_arb" }, + {} +}; + +static const char *field_to_perf(struct map *table, char *map, jsmntok_t *val) +{ + int i; + + for (i = 0; table[i].json; i++) { + if (json_streq(map, val, table[i].json)) + return table[i].perf; + } + return NULL; +} + #define EXPECT(e, t, m) do { if (!(e)) { \ jsmntok_t *loc = (t); \ if (!(t)->start && (t) > tokens) \ @@ -270,7 +287,10 @@ static void print_events_table_prefix(FILE *fp, const char *tblname) } static int print_events_table_entry(void *data, char *name, char *event, - char *desc, char *long_desc) + char *desc, char *long_desc, + char *pmu, char *unit, char *perpkg, + char *metric_expr, + char *metric_name) { struct perf_entry_data *pd = data; FILE *outfp = pd->outfp; @@ -288,7 +308,16 @@ static int print_events_table_entry(void *data, char *name, char *event, fprintf(outfp, "\t.topic = \"%s\",\n", topic); if (long_desc && long_desc[0]) fprintf(outfp, "\t.long_desc = \"%s\",\n", long_desc); - + if (pmu) + fprintf(outfp, "\t.pmu = \"%s\",\n", pmu); + if (unit) + fprintf(outfp, "\t.unit = \"%s\",\n", unit); + if (perpkg) + fprintf(outfp, "\t.perpkg = \"%s\",\n", perpkg); + if (metric_expr) + fprintf(outfp, "\t.metric_expr = \"%s\",\n", metric_expr); + if (metric_name) + fprintf(outfp, "\t.metric_name = \"%s\",\n", metric_name); fprintf(outfp, "},\n"); return 0; @@ -335,7 +364,10 @@ static char *real_event(const char *name, char *event) /* Call func with each event in the json file */ int json_events(const char *fn, int (*func)(void *data, char *name, char *event, char *desc, - char *long_desc), + char *long_desc, + char *pmu, char *unit, char *perpkg, + char *metric_expr, + char *metric_name), void *data) { int err = -EIO; @@ -343,6 +375,7 @@ int json_events(const char *fn, jsmntok_t *tokens, *tok; int i, j, len; char *map; + char buf[128]; if (!fn) return -ENOENT; @@ -356,6 +389,13 @@ int json_events(const char *fn, char *event = NULL, *desc = NULL, *name = NULL; char *long_desc = NULL; char *extra_desc = NULL; + char *pmu = NULL; + char *filter = NULL; + char *perpkg = NULL; + char *unit = NULL; + char *metric_expr = NULL; + char *metric_name = NULL; + unsigned long long eventcode = 0; struct msrmap *msr = NULL; jsmntok_t *msrval = NULL; jsmntok_t *precise = NULL; @@ -365,6 +405,7 @@ int json_events(const char *fn, for (j = 0; j < obj->size; j += 2) { jsmntok_t *field, *val; int nz; + char *s; field = tok + j; EXPECT(field->type == JSMN_STRING, tok + j, @@ -376,6 +417,16 @@ int json_events(const char *fn, nz = !json_streq(map, val, "0"); if (match_field(map, field, nz, &event, val)) { /* ok */ + } else if (json_streq(map, field, "EventCode")) { + char *code = NULL; + addfield(map, &code, "", "", val); + eventcode |= strtoul(code, NULL, 0); + free(code); + } else if (json_streq(map, field, "ExtSel")) { + char *code = NULL; + addfield(map, &code, "", "", val); + eventcode |= strtoul(code, NULL, 0) << 21; + free(code); } else if (json_streq(map, field, "EventName")) { addfield(map, &name, "", "", val); } else if (json_streq(map, field, "BriefDescription")) { @@ -399,6 +450,34 @@ int json_events(const char *fn, addfield(map, &extra_desc, ". ", " Supports address when precise", NULL); + } else if (json_streq(map, field, "Unit")) { + const char *ppmu; + + ppmu = field_to_perf(unit_to_pmu, map, val); + if (ppmu) { + pmu = strdup(ppmu); + } else { + if (!pmu) + pmu = strdup("uncore_"); + addfield(map, &pmu, "", "", val); + for (s = pmu; *s; s++) + *s = tolower(*s); + } + addfield(map, &desc, ". ", "Unit: ", NULL); + addfield(map, &desc, "", pmu, NULL); + addfield(map, &desc, "", " ", NULL); + } else if (json_streq(map, field, "Filter")) { + addfield(map, &filter, "", "", val); + } else if (json_streq(map, field, "ScaleUnit")) { + addfield(map, &unit, "", "", val); + } else if (json_streq(map, field, "PerPkg")) { + addfield(map, &perpkg, "", "", val); + } else if (json_streq(map, field, "MetricName")) { + addfield(map, &metric_name, "", "", val); + } else if (json_streq(map, field, "MetricExpr")) { + addfield(map, &metric_expr, "", "", val); + for (s = metric_expr; *s; s++) + *s = tolower(*s); } /* ignore unknown fields */ } @@ -410,20 +489,31 @@ int json_events(const char *fn, addfield(map, &extra_desc, " ", "(Precise event)", NULL); } + snprintf(buf, sizeof buf, "event=%#llx", eventcode); + addfield(map, &event, ",", buf, NULL); if (desc && extra_desc) addfield(map, &desc, " ", extra_desc, NULL); if (long_desc && extra_desc) addfield(map, &long_desc, " ", extra_desc, NULL); + if (filter) + addfield(map, &event, ",", filter, NULL); if (msr != NULL) addfield(map, &event, ",", msr->pname, msrval); fixname(name); - err = func(data, name, real_event(name, event), desc, long_desc); + err = func(data, name, real_event(name, event), desc, long_desc, + pmu, unit, perpkg, metric_expr, metric_name); free(event); free(desc); free(name); free(long_desc); free(extra_desc); + free(pmu); + free(filter); + free(perpkg); + free(unit); + free(metric_expr); + free(metric_name); if (err) break; tok += j; diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h index b0eb2744b498..611fac01913d 100644 --- a/tools/perf/pmu-events/jevents.h +++ b/tools/perf/pmu-events/jevents.h @@ -3,7 +3,10 @@ int json_events(const char *fn, int (*func)(void *data, char *name, char *event, char *desc, - char *long_desc), + char *long_desc, + char *pmu, + char *unit, char *perpkg, char *metric_expr, + char *metric_name), void *data); char *get_cpu_str(void); diff --git a/tools/perf/pmu-events/json.c b/tools/perf/pmu-events/json.c index f67bbb0aa36e..0544398d6e2d 100644 --- a/tools/perf/pmu-events/json.c +++ b/tools/perf/pmu-events/json.c @@ -49,7 +49,7 @@ static char *mapfile(const char *fn, size_t *size) int err; int fd = open(fn, O_RDONLY); - if (fd < 0 && verbose && fn) { + if (fd < 0 && verbose > 0 && fn) { pr_err("Error opening events file '%s': %s\n", fn, strerror(errno)); } diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index 2eaef595d8a0..569eab3688dd 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -10,6 +10,11 @@ struct pmu_event { const char *desc; const char *topic; const char *long_desc; + const char *pmu; + const char *unit; + const char *perpkg; + const char *metric_expr; + const char *metric_name; }; /* diff --git a/tools/perf/scripts/python/bin/intel-pt-events-record b/tools/perf/scripts/python/bin/intel-pt-events-record new file mode 100644 index 000000000000..10fe2b6977d4 --- /dev/null +++ b/tools/perf/scripts/python/bin/intel-pt-events-record @@ -0,0 +1,13 @@ +#!/bin/bash + +# +# print Intel PT Power Events and PTWRITE. The intel_pt PMU event needs +# to be specified with appropriate config terms. +# +if ! echo "$@" | grep -q intel_pt ; then + echo "Options must include the Intel PT event e.g. -e intel_pt/pwr_evt,ptw/" + echo "and for power events it probably needs to be system wide i.e. -a option" + echo "For example: -a -e intel_pt/pwr_evt,branch=0/ sleep 1" + exit 1 +fi +perf record $@ diff --git a/tools/perf/scripts/python/bin/intel-pt-events-report b/tools/perf/scripts/python/bin/intel-pt-events-report new file mode 100644 index 000000000000..9a9c92fcd026 --- /dev/null +++ b/tools/perf/scripts/python/bin/intel-pt-events-report @@ -0,0 +1,3 @@ +#!/bin/bash +# description: print Intel PT Power Events and PTWRITE +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/intel-pt-events.py
\ No newline at end of file diff --git a/tools/perf/scripts/python/intel-pt-events.py b/tools/perf/scripts/python/intel-pt-events.py new file mode 100644 index 000000000000..b19172d673af --- /dev/null +++ b/tools/perf/scripts/python/intel-pt-events.py @@ -0,0 +1,128 @@ +# intel-pt-events.py: Print Intel PT Power Events and PTWRITE +# Copyright (c) 2017, Intel Corporation. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms and conditions of the GNU General Public License, +# version 2, as published by the Free Software Foundation. +# +# This program is distributed in the hope it will be useful, but WITHOUT +# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. + +import os +import sys +import struct + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +# These perf imports are not used at present +#from perf_trace_context import * +#from Core import * + +def trace_begin(): + print "Intel PT Power Events and PTWRITE" + +def trace_end(): + print "End" + +def trace_unhandled(event_name, context, event_fields_dict): + print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())]) + +def print_ptwrite(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + flags = data[0] + payload = data[1] + exact_ip = flags & 1 + print "IP: %u payload: %#x" % (exact_ip, payload), + +def print_cbr(raw_buf): + data = struct.unpack_from("<BBBBII", raw_buf) + cbr = data[0] + f = (data[4] + 500) / 1000 + p = ((cbr * 1000 / data[2]) + 5) / 10 + print "%3u freq: %4u MHz (%3u%%)" % (cbr, f, p), + +def print_mwait(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + hints = payload & 0xff + extensions = (payload >> 32) & 0x3 + print "hints: %#x extensions: %#x" % (hints, extensions), + +def print_pwre(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + hw = (payload >> 7) & 1 + cstate = (payload >> 12) & 0xf + subcstate = (payload >> 8) & 0xf + print "hw: %u cstate: %u sub-cstate: %u" % (hw, cstate, subcstate), + +def print_exstop(raw_buf): + data = struct.unpack_from("<I", raw_buf) + flags = data[0] + exact_ip = flags & 1 + print "IP: %u" % (exact_ip), + +def print_pwrx(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + deepest_cstate = payload & 0xf + last_cstate = (payload >> 4) & 0xf + wake_reason = (payload >> 8) & 0xf + print "deepest cstate: %u last cstate: %u wake reason: %#x" % (deepest_cstate, last_cstate, wake_reason), + +def print_common_start(comm, sample, name): + ts = sample["time"] + cpu = sample["cpu"] + pid = sample["pid"] + tid = sample["tid"] + print "%16s %5u/%-5u [%03u] %9u.%09u %7s:" % (comm, pid, tid, cpu, ts / 1000000000, ts %1000000000, name), + +def print_common_ip(sample, symbol, dso): + ip = sample["ip"] + print "%16x %s (%s)" % (ip, symbol, dso) + +def process_event(param_dict): + event_attr = param_dict["attr"] + sample = param_dict["sample"] + raw_buf = param_dict["raw_buf"] + comm = param_dict["comm"] + name = param_dict["ev_name"] + + # Symbol and dso info are not always resolved + if (param_dict.has_key("dso")): + dso = param_dict["dso"] + else: + dso = "[unknown]" + + if (param_dict.has_key("symbol")): + symbol = param_dict["symbol"] + else: + symbol = "[unknown]" + + if name == "ptwrite": + print_common_start(comm, sample, name) + print_ptwrite(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "cbr": + print_common_start(comm, sample, name) + print_cbr(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "mwait": + print_common_start(comm, sample, name) + print_mwait(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "pwre": + print_common_start(comm, sample, name) + print_pwre(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "exstop": + print_common_start(comm, sample, name) + print_exstop(raw_buf) + print_common_ip(sample, symbol, dso) + elif name == "pwrx": + print_common_start(comm, sample, name) + print_pwrx(raw_buf) + print_common_ip(sample, symbol, dso) diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 6676c2dd6dcb..84222bdb8689 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -38,12 +38,14 @@ perf-y += cpumap.o perf-y += stat.o perf-y += event_update.o perf-y += event-times.o +perf-y += expr.o perf-y += backward-ring-buffer.o perf-y += sdt.o perf-y += is_printable_array.o perf-y += bitmap.o perf-y += perf-hooks.o perf-y += clang.o +perf-y += unit_number__scnprintf.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) @@ -73,7 +75,7 @@ $(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/B $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ $(Q)echo ';' >> $@ -ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64 powerpc)) +ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc)) perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o endif diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 28d1605b0338..0e77b2cf61ec 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -18,19 +18,23 @@ * permissions. All the event text files are stored there. */ +#include <debug.h> +#include <errno.h> +#include <inttypes.h> #include <stdlib.h> #include <stdio.h> #include <linux/types.h> #include <linux/kernel.h> +#include <sys/param.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> #include "../perf.h" -#include "util.h" #include <subcmd/exec-cmd.h> #include "tests.h" #define ENV "PERF_TEST_ATTR" -extern int verbose; - static char *dir; void test_attr__init(void) @@ -132,8 +136,10 @@ void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, { int errno_saved = errno; - if (store_event(attr, pid, cpu, fd, group_fd, flags)) - die("test attr FAILED"); + if (store_event(attr, pid, cpu, fd, group_fd, flags)) { + pr_err("test attr FAILED"); + exit(128); + } errno = errno_saved; } @@ -144,7 +150,7 @@ static int run_dir(const char *d, const char *perf) int vcnt = min(verbose, (int) sizeof(v) - 1); char cmd[3*PATH_MAX]; - if (verbose) + if (verbose > 0) vcnt++; snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s", diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index 1091bd47adfd..cdf21a9d0c35 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -16,6 +16,13 @@ class Fail(Exception): def getMsg(self): return '\'%s\' - %s' % (self.test.path, self.msg) +class Notest(Exception): + def __init__(self, test, arch): + self.arch = arch + self.test = test + def getMsg(self): + return '[%s] \'%s\'' % (self.arch, self.test.path) + class Unsup(Exception): def __init__(self, test): self.test = test @@ -112,6 +119,9 @@ class Event(dict): # 'command' - perf command name # 'args' - special command arguments # 'ret' - expected command return value (0 by default) +# 'arch' - architecture specific test (optional) +# comma separated list, ! at the beginning +# negates it. # # [eventX:base] # - one or multiple instances in file @@ -134,6 +144,12 @@ class Test(object): except: self.ret = 0 + try: + self.arch = parser.get('config', 'arch') + log.warning("test limitation '%s'" % self.arch) + except: + self.arch = '' + self.expect = {} self.result = {} log.debug(" loading expected events"); @@ -145,6 +161,31 @@ class Test(object): else: return True + def skip_test(self, myarch): + # If architecture not set always run test + if self.arch == '': + # log.warning("test for arch %s is ok" % myarch) + return False + + # Allow multiple values in assignment separated by ',' + arch_list = self.arch.split(',') + + # Handle negated list such as !s390x,ppc + if arch_list[0][0] == '!': + arch_list[0] = arch_list[0][1:] + log.warning("excluded architecture list %s" % arch_list) + for arch_item in arch_list: + # log.warning("test for %s arch is %s" % (arch_item, myarch)) + if arch_item == myarch: + return True + return False + + for arch_item in arch_list: + # log.warning("test for architecture '%s' current '%s'" % (arch_item, myarch)) + if arch_item == myarch: + return False + return True + def load_events(self, path, events): parser_event = ConfigParser.SafeConfigParser() parser_event.read(path) @@ -168,6 +209,11 @@ class Test(object): events[section] = e def run_cmd(self, tempdir): + junk1, junk2, junk3, junk4, myarch = (os.uname()) + + if self.skip_test(myarch): + raise Notest(self, myarch) + cmd = "PERF_TEST_ATTR=%s %s %s -o %s/perf.data %s" % (tempdir, self.perf, self.command, tempdir, self.args) ret = os.WEXITSTATUS(os.system(cmd)) @@ -265,6 +311,8 @@ def run_tests(options): Test(f, options).run() except Unsup, obj: log.warning("unsupp %s" % obj.getMsg()) + except Notest, obj: + log.warning("skipped %s" % obj.getMsg()) def setup_log(verbose): global log diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 42e892b1e979..50f6d7afee58 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -8,6 +8,7 @@ #include <sys/prctl.h> #include "tests.h" #include "debug.h" +#include <errno.h> #define NR_ITERS 111 diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index e7664fe3bd33..39bbb97cd30a 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -62,8 +62,7 @@ static void __test_function(volatile long *ptr) } #endif -__attribute__ ((noinline)) -static int test_function(void) +static noinline int test_function(void) { __test_function(&the_var); the_var++; @@ -288,3 +287,17 @@ int test__bp_signal(int subtest __maybe_unused) return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ? TEST_OK : TEST_FAIL; } + +bool test__bp_signal_is_supported(void) +{ +/* + * The powerpc so far does not have support to even create + * instruction breakpoint using the perf event interface. + * Once it's there we can release this. + */ +#ifdef __powerpc__ + return false; +#else + return true; +#endif +} diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c index 89f92fa67cc4..3b1ac6f31b15 100644 --- a/tools/perf/tests/bp_signal_overflow.c +++ b/tools/perf/tests/bp_signal_overflow.c @@ -28,8 +28,7 @@ static int overflows; -__attribute__ ((noinline)) -static int test_function(void) +static noinline int test_function(void) { return time(NULL); } diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c index 7230e62c70fc..b4ebc75e25ae 100644 --- a/tools/perf/tests/bpf-script-test-prologue.c +++ b/tools/perf/tests/bpf-script-test-prologue.c @@ -10,6 +10,15 @@ #include <uapi/linux/fs.h> +/* + * If CONFIG_PROFILE_ALL_BRANCHES is selected, + * 'if' is redefined after include kernel header. + * Recover 'if' for BPF object code. + */ +#ifdef if +# undef if +#endif + #define FMODE_READ 0x1 #define FMODE_WRITE 0x2 diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 92343f43e44a..5876da126b58 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -1,15 +1,21 @@ +#include <errno.h> #include <stdio.h> #include <sys/epoll.h> +#include <sys/types.h> +#include <sys/stat.h> #include <util/util.h> #include <util/bpf-loader.h> #include <util/evlist.h> #include <linux/bpf.h> #include <linux/filter.h> +#include <linux/kernel.h> +#include <api/fs/fs.h> #include <bpf/bpf.h> #include "tests.h" #include "llvm.h" #include "debug.h" #define NR_ITERS 111 +#define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test" #ifdef HAVE_LIBBPF_SUPPORT @@ -54,6 +60,7 @@ static struct { const char *msg_load_fail; int (*target_func)(void); int expect_result; + bool pin; } bpf_testcase_table[] = { { LLVM_TESTCASE_BASE, @@ -63,6 +70,17 @@ static struct { "load bpf object failed", &epoll_wait_loop, (NR_ITERS + 1) / 2, + false, + }, + { + LLVM_TESTCASE_BASE, + "BPF pinning", + "[bpf_pinning]", + "fix kbuild first", + "check your vmlinux setting?", + &epoll_wait_loop, + (NR_ITERS + 1) / 2, + true, }, #ifdef HAVE_BPF_PROLOGUE { @@ -73,6 +91,7 @@ static struct { "check your vmlinux setting?", &llseek_loop, (NR_ITERS + 1) / 4, + false, }, #endif { @@ -83,6 +102,7 @@ static struct { "libbpf error when dealing with relocation", NULL, 0, + false, }, }; @@ -226,10 +246,34 @@ static int __test__bpf(int idx) goto out; } - if (obj) + if (obj) { ret = do_test(obj, bpf_testcase_table[idx].target_func, bpf_testcase_table[idx].expect_result); + if (ret != TEST_OK) + goto out; + if (bpf_testcase_table[idx].pin) { + int err; + + if (!bpf_fs__mount()) { + pr_debug("BPF filesystem not mounted\n"); + ret = TEST_FAIL; + goto out; + } + err = mkdir(PERF_TEST_BPF_PATH, 0777); + if (err && errno != EEXIST) { + pr_debug("Failed to make perf_test dir: %s\n", + strerror(errno)); + ret = TEST_FAIL; + goto out; + } + if (bpf_object__pin(obj, PERF_TEST_BPF_PATH)) + ret = TEST_FAIL; + if (rm_rf(PERF_TEST_BPF_PATH)) + ret = TEST_FAIL; + } + } + out: bpf__clear(); return ret; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index a77dcc0d24e3..3ccfd58a8c3c 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -3,8 +3,10 @@ * * Builtin regression testing command: ever growing number of sanity tests */ +#include <errno.h> #include <unistd.h> #include <string.h> +#include <sys/wait.h> #include "builtin.h" #include "hist.h" #include "intlist.h" @@ -13,6 +15,7 @@ #include "color.h" #include <subcmd/parse-options.h> #include "symbol.h" +#include <linux/kernel.h> static bool dont_fork; @@ -44,6 +47,10 @@ static struct test generic_tests[] = { .func = test__parse_events, }, { + .desc = "Simple expression parser", + .func = test__expr, + }, + { .desc = "PERF_RECORD_* events & perf_sample fields", .func = test__PERF_RECORD, }, @@ -90,10 +97,12 @@ static struct test generic_tests[] = { { .desc = "Breakpoint overflow signal handler", .func = test__bp_signal, + .is_supported = test__bp_signal_is_supported, }, { .desc = "Breakpoint overflow sampling", .func = test__bp_signal_overflow, + .is_supported = test__bp_signal_is_supported, }, { .desc = "Number of exit events of a simple workload", @@ -247,6 +256,10 @@ static struct test generic_tests[] = { } }, { + .desc = "unit_number__scnprintf", + .func = test__unit_number__scnprint, + }, + { .func = NULL, }, }; @@ -295,7 +308,7 @@ static int run_test(struct test *test, int subtest) if (!dont_fork) { pr_debug("test child forked, pid %d\n", getpid()); - if (!verbose) { + if (verbose <= 0) { int nullfd = open("/dev/null", O_WRONLY); if (nullfd >= 0) { @@ -390,6 +403,11 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) if (!perf_test__matches(t, curr, argc, argv)) continue; + if (t->is_supported && !t->is_supported()) { + pr_debug("%2d: %-*s: Disabled\n", i, width, t->desc); + continue; + } + pr_info("%2d: %-*s:", i, width, t->desc); if (intlist__find(skiplist, i)) { @@ -456,7 +474,7 @@ static int perf_test__list(int argc, const char **argv) return 0; } -int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_test(int argc, const char **argv) { const char *test_usage[] = { "perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]", diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c index f853e242a86c..c5bb2203f5a9 100644 --- a/tools/perf/tests/clang.c +++ b/tools/perf/tests/clang.c @@ -2,6 +2,7 @@ #include "debug.h" #include "util.h" #include "c++/clang-c.h" +#include <linux/kernel.h> static struct { int (*func)(void); diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index ff5bc6363a79..94b7c7b02bde 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -1,9 +1,12 @@ +#include <errno.h> +#include <linux/kernel.h> #include <linux/types.h> +#include <inttypes.h> #include <stdlib.h> #include <unistd.h> #include <stdio.h> -#include <ctype.h> #include <string.h> +#include <sys/param.h> #include "parse-events.h" #include "evlist.h" @@ -16,6 +19,8 @@ #include "tests.h" +#include "sane_ctype.h" + #define BUFSZ 1024 #define READLEN 128 @@ -224,6 +229,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, unsigned char buf2[BUFSZ]; size_t ret_len; u64 objdump_addr; + const char *objdump_name; + char decomp_name[KMOD_DECOMP_LEN]; int ret; pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr); @@ -284,9 +291,25 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, state->done[state->done_cnt++] = al.map->start; } + objdump_name = al.map->dso->long_name; + if (dso__needs_decompress(al.map->dso)) { + if (dso__decompress_kmodule_path(al.map->dso, objdump_name, + decomp_name, + sizeof(decomp_name)) < 0) { + pr_debug("decompression failed\n"); + return -1; + } + + objdump_name = decomp_name; + } + /* 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); + ret = read_via_objdump(objdump_name, objdump_addr, buf2, len); + + if (dso__needs_decompress(al.map->dso)) + unlink(objdump_name); + if (ret > 0) { /* * The kernel maps are inaccurate - assume objdump is right in @@ -599,7 +622,7 @@ static int do_test_code_reading(bool try_kcore) continue; } - if (verbose) { + if (verbose > 0) { char errbuf[512]; perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf)); pr_debug("perf_evlist__open() failed!\n%s\n", errbuf); diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index f168a85992d0..4478773cdb97 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -66,7 +66,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong nr", map->nr == 2); TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1); TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256); - TEST_ASSERT_VAL("wrong refcnt", atomic_read(&map->refcnt) == 1); + TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1); cpu_map__put(map); return 0; } diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 13725e09ba22..8f08df5861cb 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -1,4 +1,6 @@ +#include <dirent.h> #include <stdlib.h> +#include <linux/kernel.h> #include <linux/types.h> #include <sys/stat.h> #include <fcntl.h> diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 1046491de4b2..3e56d08f7995 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -1,5 +1,6 @@ #include <linux/compiler.h> #include <linux/types.h> +#include <inttypes.h> #include <unistd.h> #include "tests.h" #include "debug.h" @@ -75,8 +76,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return strcmp((const char *) symbol, funcs[idx]); } -__attribute__ ((noinline)) -static int unwind_thread(struct thread *thread) +static noinline int unwind_thread(struct thread *thread) { struct perf_sample sample; unsigned long cnt = 0; @@ -107,8 +107,7 @@ static int unwind_thread(struct thread *thread) static int global_unwind_retval = -INT_MAX; -__attribute__ ((noinline)) -static int compare(void *p1, void *p2) +static noinline int compare(void *p1, void *p2) { /* Any possible value should be 'thread' */ struct thread *thread = *(struct thread **)p1; @@ -127,8 +126,7 @@ static int compare(void *p1, void *p2) return p1 - p2; } -__attribute__ ((noinline)) -static int krava_3(struct thread *thread) +static noinline int krava_3(struct thread *thread) { struct thread *array[2] = {thread, thread}; void *fp = &bsearch; @@ -146,14 +144,12 @@ static int krava_3(struct thread *thread) return global_unwind_retval; } -__attribute__ ((noinline)) -static int krava_2(struct thread *thread) +static noinline int krava_2(struct thread *thread) { return krava_3(thread); } -__attribute__ ((noinline)) -static int krava_1(struct thread *thread) +static noinline int krava_1(struct thread *thread) { return krava_2(thread); } diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c index 19ef77bd6eb4..634f20c631d8 100644 --- a/tools/perf/tests/event-times.c +++ b/tools/perf/tests/event-times.c @@ -1,5 +1,8 @@ #include <linux/compiler.h> +#include <errno.h> +#include <inttypes.h> #include <string.h> +#include <sys/wait.h> #include "tests.h" #include "evlist.h" #include "evsel.h" diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index 60926a1f6fd7..d2bea6f780f8 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -3,6 +3,8 @@ #include "parse-events.h" #include "tests.h" #include "debug.h" +#include <errno.h> +#include <linux/kernel.h> static int perf_evsel__roundtrip_cache_name_test(void) { diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c new file mode 100644 index 000000000000..6c6a3749aaf6 --- /dev/null +++ b/tools/perf/tests/expr.c @@ -0,0 +1,56 @@ +#include "util/debug.h" +#include "util/expr.h" +#include "tests.h" +#include <stdlib.h> + +static int test(struct parse_ctx *ctx, const char *e, double val2) +{ + double val; + + if (expr__parse(&val, ctx, &e)) + TEST_ASSERT_VAL("parse test failed", 0); + TEST_ASSERT_VAL("unexpected value", val == val2); + return 0; +} + +int test__expr(int subtest __maybe_unused) +{ + const char *p; + const char **other; + double val; + int ret; + struct parse_ctx ctx; + int num_other; + + expr__ctx_init(&ctx); + expr__add_id(&ctx, "FOO", 1); + expr__add_id(&ctx, "BAR", 2); + + ret = test(&ctx, "1+1", 2); + ret |= test(&ctx, "FOO+BAR", 3); + ret |= test(&ctx, "(BAR/2)%2", 1); + ret |= test(&ctx, "1 - -4", 5); + ret |= test(&ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5); + + if (ret) + return ret; + + p = "FOO/0"; + ret = expr__parse(&val, &ctx, &p); + TEST_ASSERT_VAL("division by zero", ret == 1); + + p = "BAR/"; + ret = expr__parse(&val, &ctx, &p); + TEST_ASSERT_VAL("missing operand", ret == 1); + + TEST_ASSERT_VAL("find other", + expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", &other, &num_other) == 0); + TEST_ASSERT_VAL("find other", num_other == 3); + TEST_ASSERT_VAL("find other", !strcmp(other[0], "BAR")); + TEST_ASSERT_VAL("find other", !strcmp(other[1], "BAZ")); + TEST_ASSERT_VAL("find other", !strcmp(other[2], "BOZO")); + TEST_ASSERT_VAL("find other", other[3] == NULL); + free((void *)other); + + return 0; +} diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c index a2b5ff9bf83d..bc5982f42dc3 100644 --- a/tools/perf/tests/fdarray.c +++ b/tools/perf/tests/fdarray.c @@ -19,7 +19,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE { int printed = 0; - if (!verbose) + if (verbose <= 0) return 0; printed += fprintf(fp, "\n%s: ", prefix); diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c index 6b21746d6eec..00b8dc50f3db 100644 --- a/tools/perf/tests/hists_common.c +++ b/tools/perf/tests/hists_common.c @@ -1,3 +1,4 @@ +#include <inttypes.h> #include "perf.h" #include "util/debug.h" #include "util/symbol.h" @@ -7,6 +8,7 @@ #include "util/machine.h" #include "util/thread.h" #include "tests/hists_common.h" +#include <linux/kernel.h> static struct { u32 pid; diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 9fd54b79a788..d549a9f2c41b 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -1,5 +1,6 @@ #include "perf.h" #include "util/debug.h" +#include "util/event.h" #include "util/symbol.h" #include "util/sort.h" #include "util/evsel.h" @@ -9,6 +10,7 @@ #include "util/parse-events.h" #include "tests/tests.h" #include "tests/hists_common.h" +#include <linux/kernel.h> struct sample { u32 pid; diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 62efb14f3a5a..df9c91f49af1 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -3,12 +3,14 @@ #include "util/symbol.h" #include "util/sort.h" #include "util/evsel.h" +#include "util/event.h" #include "util/evlist.h" #include "util/machine.h" #include "util/thread.h" #include "util/parse-events.h" #include "tests/tests.h" #include "tests/hists_common.h" +#include <linux/kernel.h> struct sample { u32 pid; diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index eddc7407ff8a..a26cbb79e988 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -9,6 +9,8 @@ #include "thread.h" #include "parse-events.h" #include "hists_common.h" +#include <errno.h> +#include <linux/kernel.h> struct sample { u32 pid; diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 63c5efaba1b5..06e5080182d3 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -1,5 +1,6 @@ #include "perf.h" #include "util/debug.h" +#include "util/event.h" #include "util/symbol.h" #include "util/sort.h" #include "util/evsel.h" @@ -9,6 +10,7 @@ #include "util/parse-events.h" #include "tests/tests.h" #include "tests/hists_common.h" +#include <linux/kernel.h> struct sample { u32 cpu; diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c index 42e13393e502..a5192f6a20d7 100644 --- a/tools/perf/tests/is_printable_array.c +++ b/tools/perf/tests/is_printable_array.c @@ -1,7 +1,8 @@ #include <linux/compiler.h> +#include <linux/kernel.h> #include "tests.h" #include "debug.h" -#include "util.h" +#include "print_binary.h" int test__is_printable_array(int subtest __maybe_unused) { diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index 76f41f249944..6cd9e5107f77 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -61,6 +61,7 @@ int test__kmod_path__parse(int subtest __maybe_unused) M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_KERNEL, true); M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_USER, false); +#ifdef HAVE_ZLIB_SUPPORT /* path alloc_name alloc_ext kmod comp name ext */ T("/xxxx/xxxx/x.ko.gz", true , true , true, true, "[x]", "gz"); T("/xxxx/xxxx/x.ko.gz", false , true , true, true, NULL , "gz"); @@ -96,6 +97,7 @@ int test__kmod_path__parse(int subtest __maybe_unused) M("x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("x.ko.gz", PERF_RECORD_MISC_KERNEL, true); M("x.ko.gz", PERF_RECORD_MISC_USER, false); +#endif /* path alloc_name alloc_ext kmod comp name ext */ T("[test_module]", true , true , true, false, "[test_module]", NULL); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 02a33ebcd992..482b5365e68d 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -13,7 +13,7 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz) struct bpf_object *obj; obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL); - if (IS_ERR(obj)) + if (libbpf_get_error(obj)) return TEST_FAIL; bpf_object__close(obj); return TEST_OK; @@ -76,7 +76,7 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf, * Skip this test if user's .perfconfig doesn't set [llvm] section * and clang is not found in $PATH, and this is not perf test -v */ - if (!force && (verbose == 0 && + if (!force && (verbose <= 0 && !llvm_param.user_set_param && llvm__search_clang())) { pr_debug("No clang and no verbosive, skip this test\n"); diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 634bce9caebd..15c770856aac 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> /* For the CLR_() macros */ #include <pthread.h> @@ -7,6 +9,7 @@ #include "cpumap.h" #include "tests.h" #include <linux/err.h> +#include <linux/kernel.h> /* * This test will generate random numbers of calls to some getpid syscalls, diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 0c5ce44f723f..6ea4d8a5d26b 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -1,3 +1,4 @@ +#include <inttypes.h> #include <unistd.h> #include <sys/syscall.h> #include <sys/types.h> @@ -11,6 +12,7 @@ #include "thread_map.h" #include "symbol.h" #include "thread.h" +#include "util.h" #define THREADS 4 diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index c8d9592eb142..1a74dd9fd067 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -1,8 +1,14 @@ +#include <errno.h> +#include <inttypes.h> /* For the CPU_* macros */ #include <pthread.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> #include <api/fs/fs.h> #include <linux/err.h> +#include <api/fs/tracing_path.h> #include "evsel.h" #include "tests.h" #include "thread_map.h" diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index f52239fed361..9788fac91095 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -5,6 +5,7 @@ #include "thread_map.h" #include "tests.h" #include "debug.h" +#include <errno.h> #ifndef O_DIRECTORY #define O_DIRECTORY 00200000 diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c index d7414128d7fe..e44506e21ee7 100644 --- a/tools/perf/tests/openat-syscall.c +++ b/tools/perf/tests/openat-syscall.c @@ -1,5 +1,10 @@ +#include <errno.h> +#include <inttypes.h> #include <api/fs/tracing_path.h> #include <linux/err.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> #include "thread_map.h" #include "evsel.h" #include "debug.h" diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 20c2e641c422..812a053d1941 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1,4 +1,3 @@ - #include "parse-events.h" #include "evsel.h" #include "evlist.h" @@ -6,8 +5,15 @@ #include "tests.h" #include "debug.h" #include "util.h" +#include <dirent.h> +#include <errno.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <linux/kernel.h> #include <linux/hw_breakpoint.h> #include <api/fs/fs.h> +#include <api/fs/tracing_path.h> #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \ PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD) @@ -1779,15 +1785,14 @@ static int test_pmu_events(void) } while (!ret && (ent = readdir(dir))) { -#define MAX_NAME 100 struct evlist_test e; - char name[MAX_NAME]; + char name[2 * NAME_MAX + 1 + 12 + 3]; /* Names containing . are special and cannot be used directly */ if (strchr(ent->d_name, '.')) continue; - snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name); + snprintf(name, sizeof(name), "cpu/event=%s/u", ent->d_name); e.name = name; e.check = test__checkevent_pmu_events; @@ -1795,28 +1800,16 @@ static int test_pmu_events(void) ret = test_event(&e); if (ret) break; - snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name); + snprintf(name, sizeof(name), "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name); e.name = name; e.check = test__checkevent_pmu_events_mix; ret = test_event(&e); -#undef MAX_NAME } closedir(dir); return ret; } -static void debug_warn(const char *warn, va_list params) -{ - char msg[1024]; - - if (!verbose) - return; - - vsnprintf(msg, sizeof(msg), warn, params); - fprintf(stderr, " Warning: %s\n", msg); -} - int test__parse_events(int subtest __maybe_unused) { int ret1, ret2 = 0; @@ -1828,8 +1821,6 @@ do { \ ret2 = ret1; \ } while (0) - set_warning_routine(debug_warn); - TEST_EVENTS(test__events); if (test_pmu()) diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index 81c6eeaca0f5..c6207db09f12 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -1,3 +1,4 @@ +#include <linux/kernel.h> #include <linux/types.h> #include <stddef.h> @@ -50,7 +51,8 @@ static int process_events(union perf_event **events, size_t count) } struct test_attr_event { - struct attr_event attr; + struct perf_event_header header; + struct perf_event_attr attr; u64 id; }; @@ -71,20 +73,16 @@ int test__parse_no_sample_id_all(int subtest __maybe_unused) int err; struct test_attr_event event1 = { - .attr = { - .header = { - .type = PERF_RECORD_HEADER_ATTR, - .size = sizeof(struct test_attr_event), - }, + .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), - }, + .header = { + .type = PERF_RECORD_HEADER_ATTR, + .size = sizeof(struct test_attr_event), }, .id = 2, }; diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 8f2e1de6d0ea..d37cd9588cc0 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> /* For the CLR_() macros */ #include <pthread.h> @@ -66,7 +68,7 @@ int test__PERF_RECORD(int subtest __maybe_unused) if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */ evlist = perf_evlist__new_default(); - if (evlist == NULL || argv == NULL) { + if (evlist == NULL) { pr_debug("Not enough memory to create evlist\n"); goto out; } @@ -172,13 +174,13 @@ int test__PERF_RECORD(int subtest __maybe_unused) err = perf_evlist__parse_sample(evlist, event, &sample); if (err < 0) { - if (verbose) + if (verbose > 0) perf_event__fprintf(event, stderr); pr_debug("Couldn't parse sample\n"); goto out_delete_evlist; } - if (verbose) { + if (verbose > 0) { pr_info("%" PRIu64" %d ", sample.time, sample.cpu); perf_event__fprintf(event, stderr); } diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 1e2ba2602930..a6d7aef30030 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -2,6 +2,8 @@ #include "pmu.h" #include "util.h" #include "tests.h" +#include <errno.h> +#include <linux/kernel.h> /* Simulated format definitions. */ static struct test_format { diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c index 7a52834ee0d0..fa79509da535 100644 --- a/tools/perf/tests/python-use.c +++ b/tools/perf/tests/python-use.c @@ -15,7 +15,7 @@ int test__python_use(int subtest __maybe_unused) int ret; if (asprintf(&cmd, "echo \"import sys ; sys.path.append('%s'); import perf\" | %s %s", - PYTHONPATH, PYTHON, verbose ? "" : "2> /dev/null") < 0) + PYTHONPATH, PYTHON, verbose > 0 ? "" : "2> /dev/null") < 0) return -1; ret = system(cmd) ? -1 : 0; diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 5f23710b9fee..bac5c3885b3b 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -1,4 +1,6 @@ #include <stdbool.h> +#include <inttypes.h> +#include <linux/kernel.h> #include <linux/types.h> #include "util.h" diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c index f59d210e1baf..06eda675ae2c 100644 --- a/tools/perf/tests/sdt.c +++ b/tools/perf/tests/sdt.c @@ -1,6 +1,6 @@ +#include <errno.h> #include <stdio.h> #include <sys/epoll.h> -#include <util/util.h> #include <util/evlist.h> #include <linux/filter.h> #include "tests.h" @@ -43,7 +43,7 @@ static char *get_self_path(void) { char *buf = calloc(PATH_MAX, sizeof(char)); - if (buf && readlink("/proc/self/exe", buf, PATH_MAX) < 0) { + if (buf && readlink("/proc/self/exe", buf, PATH_MAX - 1) < 0) { pr_debug("Failed to get correct path of perf\n"); free(buf); return NULL; diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 4c9fd046d57b..828494db4a19 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> #include <unistd.h> #include <stdlib.h> #include <signal.h> diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 7ddbe267d0ac..65474fd80da7 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -1,5 +1,6 @@ #include <sys/time.h> #include <sys/prctl.h> +#include <errno.h> #include <time.h> #include <stdlib.h> diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 01a5ba2788c6..cf00ebad2ef5 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -4,6 +4,7 @@ #include "cpumap.h" #include "tests.h" +#include <errno.h> #include <signal.h> static int exited; @@ -82,7 +83,7 @@ int test__task_exit(int subtest __maybe_unused) evsel = perf_evlist__first(evlist); evsel->attr.task = 1; - evsel->attr.sample_freq = 0; + evsel->attr.sample_freq = 1; evsel->attr.inherit = 0; evsel->attr.watermark = 0; evsel->attr.wakeup_events = 1; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index a512f0c8ff5b..577363809c9b 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -34,6 +34,7 @@ struct test { int (*get_nr)(void); const char *(*get_desc)(int subtest); } subtest; + bool (*is_supported)(void); }; /* Tests */ @@ -62,6 +63,7 @@ int test__sample_parsing(int subtest); int test__keep_tracking(int subtest); int test__parse_no_sample_id_all(int subtest); int test__dwarf_unwind(int subtest); +int test__expr(int subtest); int test__hists_filter(int subtest); int test__mmap_thread_lookup(int subtest); int test__thread_mg_share(int subtest); @@ -96,6 +98,9 @@ int test__perf_hooks(int subtest); int test__clang(int subtest); const char *test__clang_subtest_get_desc(int subtest); int test__clang_subtest_get_nr(void); +int test__unit_number__scnprint(int subtest); + +bool test__bp_signal_is_supported(void); #if defined(__arm__) || defined(__aarch64__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c index a4a4b4625ac3..a63d6945807b 100644 --- a/tools/perf/tests/thread-map.c +++ b/tools/perf/tests/thread-map.c @@ -29,7 +29,7 @@ int test__thread_map(int subtest __maybe_unused) thread_map__comm(map, 0) && !strcmp(thread_map__comm(map, 0), NAME)); TEST_ASSERT_VAL("wrong refcnt", - atomic_read(&map->refcnt) == 1); + refcount_read(&map->refcnt) == 1); thread_map__put(map); /* test dummy pid */ @@ -44,7 +44,7 @@ int test__thread_map(int subtest __maybe_unused) thread_map__comm(map, 0) && !strcmp(thread_map__comm(map, 0), "dummy")); TEST_ASSERT_VAL("wrong refcnt", - atomic_read(&map->refcnt) == 1); + refcount_read(&map->refcnt) == 1); thread_map__put(map); return 0; } @@ -71,7 +71,7 @@ static int process_event(struct perf_tool *tool __maybe_unused, thread_map__comm(threads, 0) && !strcmp(thread_map__comm(threads, 0), NAME)); TEST_ASSERT_VAL("wrong refcnt", - atomic_read(&threads->refcnt) == 1); + refcount_read(&threads->refcnt) == 1); thread_map__put(threads); return 0; } @@ -109,7 +109,7 @@ int test__thread_map_remove(int subtest __maybe_unused) TEST_ASSERT_VAL("failed to allocate thread_map", threads); - if (verbose) + if (verbose > 0) thread_map__fprintf(threads, stderr); TEST_ASSERT_VAL("failed to remove thread", @@ -117,7 +117,7 @@ int test__thread_map_remove(int subtest __maybe_unused) TEST_ASSERT_VAL("thread_map count != 1", threads->nr == 1); - if (verbose) + if (verbose > 0) thread_map__fprintf(threads, stderr); TEST_ASSERT_VAL("failed to remove thread", @@ -125,7 +125,7 @@ int test__thread_map_remove(int subtest __maybe_unused) TEST_ASSERT_VAL("thread_map count != 0", threads->nr == 0); - if (verbose) + if (verbose > 0) thread_map__fprintf(threads, stderr); TEST_ASSERT_VAL("failed to not remove thread", diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c index 188b63140fc8..76686dd6f5ec 100644 --- a/tools/perf/tests/thread-mg-share.c +++ b/tools/perf/tests/thread-mg-share.c @@ -43,7 +43,7 @@ int test__thread_mg_share(int subtest __maybe_unused) leader && t1 && t2 && t3 && other); mg = leader->mg; - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 4); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 4); /* test the map groups pointer is shared */ TEST_ASSERT_VAL("map groups don't match", mg == t1->mg); @@ -71,25 +71,25 @@ int test__thread_mg_share(int subtest __maybe_unused) machine__remove_thread(machine, other_leader); other_mg = other->mg; - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 2); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 2); TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg); /* release thread group */ thread__put(leader); - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 3); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 3); thread__put(t1); - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 2); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 2); thread__put(t2); - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 1); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 1); thread__put(t3); /* release other group */ thread__put(other_leader); - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 1); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 1); thread__put(other); diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index 98fe69ac553c..803f893550d6 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -65,7 +65,9 @@ static int check_cpu_topology(char *path, struct cpu_map *map) session = perf_session__new(&file, false, NULL); TEST_ASSERT_VAL("can't get session", session); - for (i = 0; i < session->header.env.nr_cpus_online; i++) { + for (i = 0; i < session->header.env.nr_cpus_avail; i++) { + if (!cpu_map__has(map, i)) + continue; pr_debug("CPU %d, core %d, socket %d\n", i, session->header.env.cpu[i].core_id, session->header.env.cpu[i].socket_id); diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c new file mode 100644 index 000000000000..44589de084b8 --- /dev/null +++ b/tools/perf/tests/unit_number__scnprintf.c @@ -0,0 +1,38 @@ +#include <inttypes.h> +#include <linux/compiler.h> +#include <linux/types.h> +#include "tests.h" +#include "units.h" +#include "debug.h" + +int test__unit_number__scnprint(int subtest __maybe_unused) +{ + struct { + u64 n; + const char *str; + } test[] = { + { 1, "1B" }, + { 10*1024, "10K" }, + { 20*1024*1024, "20M" }, + { 30*1024*1024*1024ULL, "30G" }, + { 0, "0B" }, + { 0, NULL }, + }; + unsigned i = 0; + + while (test[i].str) { + char buf[100]; + + unit_number__scnprintf(buf, sizeof(buf), test[i].n); + + pr_debug("n %" PRIu64 ", str '%s', buf '%s'\n", + test[i].n, test[i].str, buf); + + if (strcmp(test[i].str, buf)) + return TEST_FAIL; + + i++; + } + + return TEST_OK; +} diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index a5082331f246..8456175fc234 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -1,5 +1,6 @@ #include <linux/compiler.h> #include <linux/rbtree.h> +#include <inttypes.h> #include <string.h> #include "map.h" #include "symbol.h" @@ -168,7 +169,7 @@ next_pair: err = -1; } - if (!verbose) + if (verbose <= 0) goto out; header_printed = false; diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build new file mode 100644 index 000000000000..be95ac6ce845 --- /dev/null +++ b/tools/perf/trace/beauty/Build @@ -0,0 +1 @@ +libperf-y += statx.o diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h new file mode 100644 index 000000000000..cf50be3f17a4 --- /dev/null +++ b/tools/perf/trace/beauty/beauty.h @@ -0,0 +1,24 @@ +#ifndef _PERF_TRACE_BEAUTY_H +#define _PERF_TRACE_BEAUTY_H + +#include <linux/types.h> + +struct trace; +struct thread; + +struct syscall_arg { + unsigned long val; + struct thread *thread; + struct trace *trace; + void *parm; + u8 idx; + u8 mask; +}; + +size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags + +size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_STATX_MASK syscall_arg__scnprintf_statx_mask + +#endif /* _PERF_TRACE_BEAUTY_H */ diff --git a/tools/perf/trace/beauty/signum.c b/tools/perf/trace/beauty/signum.c index d3b0b1fab077..fde8f2fc6558 100644 --- a/tools/perf/trace/beauty/signum.c +++ b/tools/perf/trace/beauty/signum.c @@ -1,3 +1,4 @@ +#include <signal.h> static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg) { diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c new file mode 100644 index 000000000000..5643b692af4c --- /dev/null +++ b/tools/perf/trace/beauty/statx.c @@ -0,0 +1,72 @@ +/* + * trace/beauty/statx.c + * + * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include "trace/beauty/beauty.h" +#include <linux/kernel.h> +#include <sys/types.h> +#include <uapi/linux/fcntl.h> +#include <uapi/linux/stat.h> + +size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + + if (flags == 0) + return scnprintf(bf, size, "SYNC_AS_STAT"); +#define P_FLAG(n) \ + if (flags & AT_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~AT_##n; \ + } + + P_FLAG(SYMLINK_NOFOLLOW); + P_FLAG(REMOVEDIR); + P_FLAG(SYMLINK_FOLLOW); + P_FLAG(NO_AUTOMOUNT); + P_FLAG(EMPTY_PATH); + P_FLAG(STATX_FORCE_SYNC); + P_FLAG(STATX_DONT_SYNC); + +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_FLAG(n) \ + if (flags & STATX_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~STATX_##n; \ + } + + P_FLAG(TYPE); + P_FLAG(MODE); + P_FLAG(NLINK); + P_FLAG(UID); + P_FLAG(GID); + P_FLAG(ATIME); + P_FLAG(MTIME); + P_FLAG(CTIME); + P_FLAG(INO); + P_FLAG(SIZE); + P_FLAG(BLOCKS); + P_FLAG(BTIME); + +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 3eb3edb307a4..83874b0e266c 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -1,4 +1,5 @@ #include "../util.h" +#include "../string2.h" #include "../config.h" #include "../../perf.h" #include "libslang.h" @@ -13,6 +14,7 @@ #include "helpline.h" #include "keysyms.h" #include "../color.h" +#include "sane_ctype.h" static int ui_browser__percent_color(struct ui_browser *browser, double percent, bool current) @@ -579,7 +581,7 @@ static int ui_browser__color_config(const char *var, const char *value, break; *bg = '\0'; - while (isspace(*++bg)); + bg = ltrim(++bg); ui_browser__colorsets[i].bg = bg; ui_browser__colorsets[i].fg = fg; return 0; @@ -702,7 +704,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser, ui_browser__gotorc(browser, row, column + 1); SLsmg_draw_hline(2); - if (row++ == 0) + if (++row == 0) goto out; } else row = 0; diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ba36aac340bc..27f41f28dcb4 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -9,7 +9,10 @@ #include "../../util/symbol.h" #include "../../util/evsel.h" #include "../../util/config.h" +#include <inttypes.h> #include <pthread.h> +#include <linux/kernel.h> +#include <sys/ttydefaults.h> struct disasm_line_samples { double percent; @@ -43,12 +46,15 @@ static struct annotate_browser_opt { .jump_arrows = true, }; +struct arch; + struct annotate_browser { struct ui_browser b; struct rb_root entries; struct rb_node *curr_hot; struct disasm_line *selection; struct disasm_line **offsets; + struct arch *arch; int nr_events; u64 start; int nr_asm_entries; @@ -122,43 +128,57 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int int i, pcnt_width = annotate_browser__pcnt_width(ab); double percent_max = 0.0; char bf[256]; + bool show_title = false; for (i = 0; i < ab->nr_events; i++) { if (bdl->samples[i].percent > percent_max) percent_max = bdl->samples[i].percent; } + if ((row == 0) && (dl->offset == -1 || percent_max == 0.0)) { + if (ab->have_cycles) { + if (dl->ipc == 0.0 && dl->cycles == 0) + show_title = true; + } else + show_title = true; + } + if (dl->offset != -1 && percent_max != 0.0) { - if (percent_max != 0.0) { - for (i = 0; i < ab->nr_events; i++) { - ui_browser__set_percent_color(browser, - bdl->samples[i].percent, - current_entry); - if (annotate_browser__opts.show_total_period) { - ui_browser__printf(browser, "%6" PRIu64 " ", - bdl->samples[i].nr); - } else { - ui_browser__printf(browser, "%6.2f ", - bdl->samples[i].percent); - } + for (i = 0; i < ab->nr_events; i++) { + ui_browser__set_percent_color(browser, + bdl->samples[i].percent, + current_entry); + if (annotate_browser__opts.show_total_period) { + ui_browser__printf(browser, "%6" PRIu64 " ", + bdl->samples[i].nr); + } else { + ui_browser__printf(browser, "%6.2f ", + bdl->samples[i].percent); } - } else { - ui_browser__write_nstring(browser, " ", 7 * ab->nr_events); } } else { ui_browser__set_percent_color(browser, 0, current_entry); - ui_browser__write_nstring(browser, " ", 7 * ab->nr_events); + + if (!show_title) + ui_browser__write_nstring(browser, " ", 7 * ab->nr_events); + else + ui_browser__printf(browser, "%*s", 7, "Percent"); } if (ab->have_cycles) { if (dl->ipc) ui_browser__printf(browser, "%*.2f ", IPC_WIDTH - 1, dl->ipc); - else + else if (!show_title) ui_browser__write_nstring(browser, " ", IPC_WIDTH); + else + ui_browser__printf(browser, "%*s ", IPC_WIDTH - 1, "IPC"); + if (dl->cycles) ui_browser__printf(browser, "%*" PRIu64 " ", CYCLES_WIDTH - 1, dl->cycles); - else + else if (!show_title) ui_browser__write_nstring(browser, " ", CYCLES_WIDTH); + else + ui_browser__printf(browser, "%*s ", CYCLES_WIDTH - 1, "Cycle"); } SLsmg_write_char(' '); @@ -1053,7 +1073,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, (nr_pcnt - 1); } - err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), sizeof_bdl); + err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), + sizeof_bdl, &browser.arch); if (err) { char msg[BUFSIZ]; symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c index edbeaaf31ace..e2c9390ff4c5 100644 --- a/tools/perf/ui/browsers/header.c +++ b/tools/perf/ui/browsers/header.c @@ -8,6 +8,8 @@ #include "util/header.h" #include "util/session.h" +#include <sys/ttydefaults.h> + static void ui_browser__argv_write(struct ui_browser *browser, void *entry, int row) { diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 641b40234a9d..69f4570bd4f9 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1,7 +1,11 @@ +#include <dirent.h> +#include <errno.h> +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <linux/rbtree.h> +#include <sys/ttydefaults.h> #include "../../util/evsel.h" #include "../../util/evlist.h" @@ -10,6 +14,7 @@ #include "../../util/sort.h" #include "../../util/util.h" #include "../../util/top.h" +#include "../../util/thread.h" #include "../../arch/common.h" #include "../browsers/hists.h" @@ -18,6 +23,11 @@ #include "../ui.h" #include "map.h" #include "annotate.h" +#include "srcline.h" +#include "string2.h" +#include "units.h" + +#include "sane_ctype.h" extern void hist_browser__init_hpp(void); @@ -144,9 +154,60 @@ static void callchain_list__set_folding(struct callchain_list *cl, bool unfold) cl->unfolded = unfold ? cl->has_children : false; } +static struct inline_node *inline_node__create(struct map *map, u64 ip) +{ + struct dso *dso; + struct inline_node *node; + + if (map == NULL) + return NULL; + + dso = map->dso; + if (dso == NULL) + return NULL; + + if (dso->kernel != DSO_TYPE_USER) + return NULL; + + node = dso__parse_addr_inlines(dso, + map__rip_2objdump(map, ip)); + + return node; +} + +static int inline__count_rows(struct inline_node *node) +{ + struct inline_list *ilist; + int i = 0; + + if (node == NULL) + return 0; + + list_for_each_entry(ilist, &node->val, list) { + if ((ilist->filename != NULL) || (ilist->funcname != NULL)) + i++; + } + + return i; +} + +static int callchain_list__inline_rows(struct callchain_list *chain) +{ + struct inline_node *node; + int rows; + + node = inline_node__create(chain->ms.map, chain->ip); + if (node == NULL) + return 0; + + rows = inline__count_rows(node); + inline_node__delete(node); + return rows; +} + static int callchain_node__count_rows_rb_tree(struct callchain_node *node) { - int n = 0; + int n = 0, inline_rows; struct rb_node *nd; for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) { @@ -156,6 +217,13 @@ static int callchain_node__count_rows_rb_tree(struct callchain_node *node) list_for_each_entry(chain, &child->val, list) { ++n; + + if (symbol_conf.inline_name) { + inline_rows = + callchain_list__inline_rows(chain); + n += inline_rows; + } + /* We need this because we may not have children */ folded_sign = callchain_list__folded(chain); if (folded_sign == '+') @@ -207,7 +275,7 @@ static int callchain_node__count_rows(struct callchain_node *node) { struct callchain_list *chain; bool unfolded = false; - int n = 0; + int n = 0, inline_rows; if (callchain_param.mode == CHAIN_FLAT) return callchain_node__count_flat_rows(node); @@ -216,6 +284,11 @@ static int callchain_node__count_rows(struct callchain_node *node) list_for_each_entry(chain, &node->val, list) { ++n; + if (symbol_conf.inline_name) { + inline_rows = callchain_list__inline_rows(chain); + n += inline_rows; + } + unfolded = chain->unfolded; } @@ -362,6 +435,19 @@ static void hist_entry__init_have_children(struct hist_entry *he) he->init_have_children = true; } +static void hist_entry_init_inline_node(struct hist_entry *he) +{ + if (he->inline_node) + return; + + he->inline_node = inline_node__create(he->ms.map, he->ip); + + if (he->inline_node == NULL) + return; + + he->has_children = true; +} + static bool hist_browser__toggle_fold(struct hist_browser *browser) { struct hist_entry *he = browser->he_selection; @@ -393,7 +479,12 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser) if (he->unfolded) { if (he->leaf) - he->nr_rows = callchain__count_rows(&he->sorted_chain); + if (he->inline_node) + he->nr_rows = inline__count_rows( + he->inline_node); + else + he->nr_rows = callchain__count_rows( + &he->sorted_chain); else he->nr_rows = hierarchy_count_rows(browser, he, false); @@ -501,8 +592,8 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he, return n; } -static void hist_entry__set_folding(struct hist_entry *he, - struct hist_browser *hb, bool unfold) +static void __hist_entry__set_folding(struct hist_entry *he, + struct hist_browser *hb, bool unfold) { hist_entry__init_have_children(he); he->unfolded = unfold ? he->has_children : false; @@ -520,12 +611,34 @@ static void hist_entry__set_folding(struct hist_entry *he, he->nr_rows = 0; } +static void hist_entry__set_folding(struct hist_entry *he, + struct hist_browser *browser, bool unfold) +{ + double percent; + + percent = hist_entry__get_percent_limit(he); + if (he->filtered || percent < browser->min_pcnt) + return; + + __hist_entry__set_folding(he, browser, unfold); + + if (!he->depth || unfold) + browser->nr_hierarchy_entries++; + if (he->leaf) + browser->nr_callchain_rows += he->nr_rows; + else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) { + browser->nr_hierarchy_entries++; + he->has_no_entry = true; + he->nr_rows = 1; + } else + he->has_no_entry = false; +} + static void __hist_browser__set_folding(struct hist_browser *browser, bool unfold) { struct rb_node *nd; struct hist_entry *he; - double percent; nd = rb_first(&browser->hists->entries); while (nd) { @@ -535,21 +648,6 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold) nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD); hist_entry__set_folding(he, browser, unfold); - - percent = hist_entry__get_percent_limit(he); - if (he->filtered || percent < browser->min_pcnt) - continue; - - if (!he->depth || unfold) - browser->nr_hierarchy_entries++; - if (he->leaf) - browser->nr_callchain_rows += he->nr_rows; - else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) { - browser->nr_hierarchy_entries++; - he->has_no_entry = true; - he->nr_rows = 1; - } else - he->has_no_entry = false; } } @@ -564,6 +662,15 @@ static void hist_browser__set_folding(struct hist_browser *browser, bool unfold) ui_browser__reset_index(&browser->b); } +static void hist_browser__set_folding_selected(struct hist_browser *browser, bool unfold) +{ + if (!browser->he_selection) + return; + + hist_entry__set_folding(browser->he_selection, browser, unfold); + browser->b.nr_entries = hist_browser__nr_entries(browser); +} + static void ui_browser__warn_lost_events(struct ui_browser *browser) { ui_browser__warning(browser, 4, @@ -637,10 +744,18 @@ int hist_browser__run(struct hist_browser *browser, const char *help) /* Collapse the whole world. */ hist_browser__set_folding(browser, false); break; + case 'c': + /* Collapse the selected entry. */ + hist_browser__set_folding_selected(browser, false); + break; case 'E': /* Expand the whole world. */ hist_browser__set_folding(browser, true); break; + case 'e': + /* Expand the selected entry. */ + hist_browser__set_folding_selected(browser, true); + break; case 'H': browser->show_headers = !browser->show_headers; hist_browser__update_rows(browser); @@ -729,6 +844,71 @@ static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_u #define LEVEL_OFFSET_STEP 3 +static int hist_browser__show_inline(struct hist_browser *browser, + struct inline_node *node, + unsigned short row, + int offset) +{ + struct inline_list *ilist; + char buf[1024]; + int color, width, first_row; + + first_row = row; + width = browser->b.width - (LEVEL_OFFSET_STEP + 2); + list_for_each_entry(ilist, &node->val, list) { + if ((ilist->filename != NULL) || (ilist->funcname != NULL)) { + color = HE_COLORSET_NORMAL; + if (ui_browser__is_current_entry(&browser->b, row)) + color = HE_COLORSET_SELECTED; + + if (callchain_param.key == CCKEY_ADDRESS || + callchain_param.key == CCKEY_SRCLINE) { + if (ilist->filename != NULL) + scnprintf(buf, sizeof(buf), + "%s:%d (inline)", + ilist->filename, + ilist->line_nr); + else + scnprintf(buf, sizeof(buf), "??"); + } else if (ilist->funcname != NULL) + scnprintf(buf, sizeof(buf), "%s (inline)", + ilist->funcname); + else if (ilist->filename != NULL) + scnprintf(buf, sizeof(buf), + "%s:%d (inline)", + ilist->filename, + ilist->line_nr); + else + scnprintf(buf, sizeof(buf), "??"); + + ui_browser__set_color(&browser->b, color); + hist_browser__gotorc(browser, row, 0); + ui_browser__write_nstring(&browser->b, " ", + LEVEL_OFFSET_STEP + offset); + ui_browser__write_nstring(&browser->b, buf, width); + row++; + } + } + + return row - first_row; +} + +static size_t show_inline_list(struct hist_browser *browser, struct map *map, + u64 ip, int row, int offset) +{ + struct inline_node *node; + int ret; + + node = inline_node__create(map, ip); + if (node == NULL) + return 0; + + ret = hist_browser__show_inline(browser, node, row, offset); + + inline_node__delete(node); + return ret; +} + static int hist_browser__show_callchain_list(struct hist_browser *browser, struct callchain_node *node, struct callchain_list *chain, @@ -740,6 +920,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser, char bf[1024], *alloc_str; char buf[64], *alloc_str2; const char *str; + int inline_rows = 0, ret = 1; if (arg->row_offset != 0) { arg->row_offset--; @@ -777,10 +958,15 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser, } print(browser, chain, str, offset, row, arg); - free(alloc_str); free(alloc_str2); - return 1; + + if (symbol_conf.inline_name) { + inline_rows = show_inline_list(browser, chain->ms.map, + chain->ip, row + 1, offset); + } + + return ret + inline_rows; } static bool check_percent_display(struct rb_node *node, u64 parent_total) @@ -1204,6 +1390,12 @@ static int hist_browser__show_entry(struct hist_browser *browser, folded_sign = hist_entry__folded(entry); } + if (symbol_conf.inline_name && + (!entry->has_children)) { + hist_entry_init_inline_node(entry); + folded_sign = hist_entry__folded(entry); + } + if (row_offset == 0) { struct hpp_arg arg = { .b = &browser->b, @@ -1235,7 +1427,8 @@ static int hist_browser__show_entry(struct hist_browser *browser, } if (first) { - if (symbol_conf.use_callchain) { + if (symbol_conf.use_callchain || + symbol_conf.inline_name) { ui_browser__printf(&browser->b, "%c ", folded_sign); width -= 2; } @@ -1277,8 +1470,14 @@ static int hist_browser__show_entry(struct hist_browser *browser, .is_current_entry = current_entry, }; - printed += hist_browser__show_callchain(browser, entry, 1, row, - hist_browser__show_callchain_entry, &arg, + if (entry->inline_node) + printed += hist_browser__show_inline(browser, + entry->inline_node, row, 0); + else + printed += hist_browser__show_callchain(browser, + entry, 1, row, + hist_browser__show_callchain_entry, + &arg, hist_browser__check_output_full); } @@ -2284,7 +2483,7 @@ static int switch_data_file(void) return ret; memset(options, 0, sizeof(options)); - memset(options, 0, sizeof(abs_path)); + memset(abs_path, 0, sizeof(abs_path)); while ((dent = readdir(pwd_dir))) { char path[PATH_MAX]; diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c index 98a34664bb7e..ffa5addf631d 100644 --- a/tools/perf/ui/browsers/map.c +++ b/tools/perf/ui/browsers/map.c @@ -11,6 +11,8 @@ #include "../keysyms.h" #include "map.h" +#include "sane_ctype.h" + struct map_browser { struct ui_browser b; struct map *map; @@ -73,7 +75,7 @@ static int map_browser__run(struct map_browser *browser) if (ui_browser__show(&browser->b, browser->map->dso->long_name, "Press ESC to exit, %s / to search", - verbose ? "" : "restart with -v to use") < 0) + verbose > 0 ? "" : "restart with -v to use") < 0) return -1; while (1) { @@ -81,7 +83,7 @@ static int map_browser__run(struct map_browser *browser) switch (key) { case '/': - if (verbose) + if (verbose > 0) map_browser__search(browser); default: break; @@ -117,7 +119,7 @@ int map__browse(struct map *map) if (maxaddr < pos->end) maxaddr = pos->end; - if (verbose) { + if (verbose > 0) { u32 *idx = symbol__browser_index(pos); *idx = mb.b.nr_entries; } diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index 8c9308ac30b7..d903fd493416 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -3,7 +3,8 @@ #include "util/annotate.h" #include "util/evsel.h" #include "ui/helpline.h" - +#include <inttypes.h> +#include <signal.h> enum { ANN_COL__PERCENT, @@ -167,7 +168,8 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map, if (map->dso->annotate_warned) return -1; - err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), 0); + err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), + 0, NULL); if (err) { char msg[BUFSIZ]; symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg)); diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index a4f02de7c1b5..e24f83957705 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -4,7 +4,9 @@ #include "../sort.h" #include "../hist.h" #include "../helpline.h" +#include "../string2.h" #include "gtk.h" +#include <signal.h> #define MAX_COLUMNS 32 diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 37388397b5bc..ddb2c6fbdf91 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -1,3 +1,4 @@ +#include <inttypes.h> #include <math.h> #include <linux/compiler.h> @@ -209,6 +210,8 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b, return 0; ret = b->callchain->max_depth - a->callchain->max_depth; + if (callchain_param.order == ORDER_CALLER) + ret = -ret; } return ret; } @@ -521,6 +524,12 @@ void perf_hpp_list__register_sort_field(struct perf_hpp_list *list, list_add_tail(&format->sort_list, &list->sorts); } +void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list, + struct perf_hpp_fmt *format) +{ + list_add(&format->sort_list, &list->sorts); +} + void perf_hpp__column_unregister(struct perf_hpp_fmt *format) { list_del(&format->list); @@ -560,6 +569,10 @@ void perf_hpp__setup_output_field(struct perf_hpp_list *list) perf_hpp_list__for_each_sort_list(list, fmt) { struct perf_hpp_fmt *pos; + /* skip sort-only fields ("sort_compute" in perf diff) */ + if (!fmt->entry && !fmt->color) + continue; + perf_hpp_list__for_each_format(list, pos) { if (fmt_equal(fmt, pos)) goto next; @@ -638,7 +651,7 @@ unsigned int hists__sort_list_width(struct hists *hists) ret += fmt->width(fmt, &dummy_hpp, hists); } - if (verbose && hists__has(hists, sym)) /* Addr + origin */ + if (verbose > 0 && hists__has(hists, sym)) /* Addr + origin */ ret += 3 + BITS_PER_LONG / 4; return ret; diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index 1f6b0994f4f4..caf1ce6f5152 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -4,11 +4,16 @@ #include "../util/cache.h" #include "../util/debug.h" #include "../util/hist.h" +#include "../util/util.h" pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; void *perf_gtk_handle; +int use_browser = -1; + +#define PERF_GTK_DSO "libperf-gtk.so" #ifdef HAVE_GTK2_SUPPORT + static int setup_gtk_browser(void) { int (*perf_ui_init)(void); diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 668f4aecf2e6..42e432bd2eb4 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -4,7 +4,10 @@ #include "../../util/hist.h" #include "../../util/sort.h" #include "../../util/evsel.h" - +#include "../../util/srcline.h" +#include "../../util/string2.h" +#include "../../util/thread.h" +#include "../../util/sane_ctype.h" static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin) { @@ -17,6 +20,67 @@ static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin) return ret; } +static size_t inline__fprintf(struct map *map, u64 ip, int left_margin, + int depth, int depth_mask, FILE *fp) +{ + struct dso *dso; + struct inline_node *node; + struct inline_list *ilist; + int ret = 0, i; + + if (map == NULL) + return 0; + + dso = map->dso; + if (dso == NULL) + return 0; + + if (dso->kernel != DSO_TYPE_USER) + return 0; + + node = dso__parse_addr_inlines(dso, + map__rip_2objdump(map, ip)); + if (node == NULL) + return 0; + + list_for_each_entry(ilist, &node->val, list) { + if ((ilist->filename != NULL) || (ilist->funcname != NULL)) { + ret += callchain__fprintf_left_margin(fp, left_margin); + + for (i = 0; i < depth; i++) { + if (depth_mask & (1 << i)) + ret += fprintf(fp, "|"); + else + ret += fprintf(fp, " "); + ret += fprintf(fp, " "); + } + + if (callchain_param.key == CCKEY_ADDRESS || + callchain_param.key == CCKEY_SRCLINE) { + if (ilist->filename != NULL) + ret += fprintf(fp, "%s:%d (inline)", + ilist->filename, + ilist->line_nr); + else + ret += fprintf(fp, "??"); + } else if (ilist->funcname != NULL) + ret += fprintf(fp, "%s (inline)", + ilist->funcname); + else if (ilist->filename != NULL) + ret += fprintf(fp, "%s:%d (inline)", + ilist->filename, + ilist->line_nr); + else + ret += fprintf(fp, "??"); + + ret += fprintf(fp, "\n"); + } + } + + inline_node__delete(node); + return ret; +} + static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask, int left_margin) { @@ -78,6 +142,10 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node, fputs(str, fp); fputc('\n', fp); free(alloc_str); + + if (symbol_conf.inline_name) + ret += inline__fprintf(chain->ms.map, chain->ip, + left_margin, depth, depth_mask, fp); return ret; } @@ -229,6 +297,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, if (!i++ && field_order == NULL && sort_order && !prefixcmp(sort_order, "sym")) continue; + if (!printed) { ret += callchain__fprintf_left_margin(fp, left_margin); ret += fprintf(fp, "|\n"); @@ -251,6 +320,13 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, if (++entries_printed == callchain_param.print_limit) break; + + if (symbol_conf.inline_name) + ret += inline__fprintf(chain->ms.map, + chain->ip, + left_margin, + 0, 0, + fp); } root = &cnode->rb_root; } @@ -529,6 +605,8 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, bool use_callchain) { int ret; + int callchain_ret = 0; + int inline_ret = 0; struct perf_hpp hpp = { .buf = bf, .size = size, @@ -547,7 +625,16 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, ret = fprintf(fp, "%s\n", bf); if (use_callchain) - ret += hist_entry_callchain__fprintf(he, total_period, 0, fp); + callchain_ret = hist_entry_callchain__fprintf(he, total_period, + 0, fp); + + if (callchain_ret == 0 && symbol_conf.inline_name) { + inline_ret = inline__fprintf(he->ms.map, he->ip, 0, 0, 0, fp); + ret += inline_ret; + if (inline_ret > 0) + ret += fprintf(fp, "\n"); + } else + ret += callchain_ret; return ret; } diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index 4ea2ba861fc2..d9350a1da48b 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -1,6 +1,7 @@ #include <errno.h> #include <signal.h> #include <stdbool.h> +#include <linux/kernel.h> #ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> #endif diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 3840e3a87057..79dea95a7f68 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -1,4 +1,3 @@ -libperf-y += alias.o libperf-y += annotate.o libperf-y += block-range.o libperf-y += build-id.o @@ -14,9 +13,11 @@ libperf-y += find_bit.o libperf-y += kallsyms.o libperf-y += levenshtein.o libperf-y += llvm-utils.o +libperf-y += memswap.o libperf-y += parse-events.o libperf-y += perf_regs.o libperf-y += path.o +libperf-y += print_binary.o libperf-y += rbtree.o libperf-y += libstring.o libperf-y += bitmap.o @@ -42,6 +43,7 @@ libperf-y += pstack.o libperf-y += session.o libperf-$(CONFIG_AUDIT) += syscalltbl.o libperf-y += ordered-events.o +libperf-y += namespaces.o libperf-y += comm.o libperf-y += thread.o libperf-y += thread_map.o @@ -81,13 +83,16 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/ libperf-$(CONFIG_AUXTRACE) += intel-pt.o libperf-$(CONFIG_AUXTRACE) += intel-bts.o libperf-y += parse-branch-options.o +libperf-y += dump-insn.o libperf-y += parse-regs-options.o libperf-y += term.o libperf-y += help-unknown-cmd.o libperf-y += mem-events.o libperf-y += vsprintf.o libperf-y += drv_configs.o +libperf-y += units.o libperf-y += time-utils.o +libperf-y += expr-bison.o libperf-$(CONFIG_LIBBPF) += bpf-loader.o libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o @@ -140,6 +145,10 @@ $(OUTPUT)util/parse-events-bison.c: util/parse-events.y $(call rule_mkdir) $(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_ +$(OUTPUT)util/expr-bison.c: util/expr.y + $(call rule_mkdir) + $(Q)$(call echo-cmd,bison)$(BISON) -v util/expr.y -d $(PARSER_DEBUG_BISON) -o $@ -p expr__ + $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c $(call rule_mkdir) $(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l @@ -152,6 +161,7 @@ CFLAGS_parse-events-flex.o += -w CFLAGS_pmu-flex.o += -w CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w +CFLAGS_expr-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $(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 $(OUTPUT)util/pmu-bison.c @@ -162,6 +172,7 @@ CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_parse-events.o += -Wno-redundant-decls +CFLAGS_header.o += -include $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE $(call rule_mkdir) diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c deleted file mode 100644 index 6455471d9cd1..000000000000 --- a/tools/perf/util/alias.c +++ /dev/null @@ -1,78 +0,0 @@ -#include "cache.h" -#include "util.h" -#include "config.h" - -static const char *alias_key; -static char *alias_val; - -static int alias_lookup_cb(const char *k, const char *v, - void *cb __maybe_unused) -{ - if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) { - if (!v) - return config_error_nonbool(k); - alias_val = strdup(v); - return 0; - } - return 0; -} - -char *alias_lookup(const char *alias) -{ - alias_key = alias; - alias_val = NULL; - perf_config(alias_lookup_cb, NULL); - return alias_val; -} - -int split_cmdline(char *cmdline, const char ***argv) -{ - int src, dst, count = 0, size = 16; - char quoted = 0; - - *argv = malloc(sizeof(char*) * size); - - /* split alias_string */ - (*argv)[count++] = cmdline; - for (src = dst = 0; cmdline[src];) { - char c = cmdline[src]; - if (!quoted && isspace(c)) { - cmdline[dst++] = 0; - while (cmdline[++src] - && isspace(cmdline[src])) - ; /* skip */ - if (count >= size) { - size += 16; - *argv = realloc(*argv, sizeof(char*) * size); - } - (*argv)[count++] = cmdline + dst; - } else if (!quoted && (c == '\'' || c == '"')) { - quoted = c; - src++; - } else if (c == quoted) { - quoted = 0; - src++; - } else { - if (c == '\\' && quoted != '\'') { - src++; - c = cmdline[src]; - if (!c) { - zfree(argv); - return error("cmdline ends with \\"); - } - } - cmdline[dst++] = c; - src++; - } - } - - cmdline[dst] = 0; - - if (quoted) { - zfree(argv); - return error("unclosed quote"); - } - - return count; -} - diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 06cc04e5806a..be1caabb9290 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -7,6 +7,8 @@ * Released under the GPL v2. (and only v2, not any later version) */ +#include <errno.h> +#include <inttypes.h> #include "util.h" #include "ui/ui.h" #include "sort.h" @@ -18,12 +20,16 @@ #include "annotate.h" #include "evsel.h" #include "block-range.h" +#include "string2.h" #include "arch/common.h" #include <regex.h> #include <pthread.h> #include <linux/bitops.h> +#include <linux/kernel.h> #include <sys/utsname.h> +#include "sane_ctype.h" + const char *disassembler_style; const char *objdump_path; static regex_t file_lineno; @@ -108,6 +114,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i #include "arch/arm64/annotate/instructions.c" #include "arch/x86/annotate/instructions.c" #include "arch/powerpc/annotate/instructions.c" +#include "arch/s390/annotate/instructions.c" static struct arch architectures[] = { { @@ -130,6 +137,13 @@ static struct arch architectures[] = { .name = "powerpc", .init = powerpc__annotate_init, }, + { + .name = "s390", + .init = s390__annotate_init, + .objdump = { + .comment_char = '#', + }, + }, }; static void ins__delete(struct ins_operands *ops) @@ -225,10 +239,20 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op const char *s = strchr(ops->raw, '+'); const char *c = strchr(ops->raw, ','); - if (c++ != NULL) + /* + * skip over possible up to 2 operands to get to address, e.g.: + * tbnz w0, #26, ffff0000083cd190 <security_file_permission+0xd0> + */ + if (c++ != NULL) { ops->target.addr = strtoull(c, NULL, 16); - else + if (!ops->target.addr) { + c = strchr(c, ','); + if (c++ != NULL) + ops->target.addr = strtoull(c, NULL, 16); + } + } else { ops->target.addr = strtoull(ops->raw, NULL, 16); + } if (s++ != NULL) { ops->target.offset = strtoull(s, NULL, 16); @@ -243,10 +267,27 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op static int jump__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops) { + const char *c = strchr(ops->raw, ','); + if (!ops->target.addr || ops->target.offset < 0) return ins__raw_scnprintf(ins, bf, size, ops); - return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset); + if (c != NULL) { + const char *c2 = strchr(c + 1, ','); + + /* check for 3-op insn */ + if (c2 != NULL) + c = c2; + c++; + + /* mirror arch objdump's space-after-comma style */ + if (*c == ' ') + c++; + } + + return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64, + ins->name, c ? c - ops->raw : 0, ops->raw, + ops->target.offset); } static struct ins_ops jump_ops = { @@ -379,9 +420,7 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *m if (comment == NULL) return 0; - while (comment[0] != '\0' && isspace(comment[0])) - ++comment; - + comment = ltrim(comment); comment__symbol(ops->source.raw, comment, &ops->source.addr, &ops->source.name); comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name); @@ -426,9 +465,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops if (comment == NULL) return 0; - while (comment[0] != '\0' && isspace(comment[0])) - ++comment; - + comment = ltrim(comment); comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name); return 0; @@ -777,10 +814,7 @@ static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, str static int disasm_line__parse(char *line, const char **namep, char **rawp) { - char *name = line, tmp; - - while (isspace(name[0])) - ++name; + char tmp, *name = ltrim(line); if (name[0] == '\0') return -1; @@ -798,12 +832,7 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp) goto out_free_name; (*rawp)[0] = tmp; - - if ((*rawp)[0] != '\0') { - (*rawp)++; - while (isspace((*rawp)[0])) - ++(*rawp); - } + *rawp = ltrim(*rawp); return 0; @@ -1148,7 +1177,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, { struct annotation *notes = symbol__annotation(sym); struct disasm_line *dl; - char *line = NULL, *parsed_line, *tmp, *tmp2, *c; + char *line = NULL, *parsed_line, *tmp, *tmp2; size_t line_len; s64 line_ip, offset = -1; regmatch_t match[2]; @@ -1159,32 +1188,16 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, if (!line) return -1; - while (line_len != 0 && isspace(line[line_len - 1])) - line[--line_len] = '\0'; - - c = strchr(line, '\n'); - if (c) - *c = 0; - line_ip = -1; - parsed_line = line; + parsed_line = rtrim(line); /* /filename:linenr ? Save line number and ignore. */ - if (regexec(&file_lineno, line, 2, match, 0) == 0) { - *line_nr = atoi(line + match[1].rm_so); + if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) { + *line_nr = atoi(parsed_line + match[1].rm_so); return 0; } - /* - * Strip leading spaces: - */ - tmp = line; - while (*tmp) { - if (*tmp != ' ') - break; - tmp++; - } - + tmp = ltrim(parsed_line); if (*tmp) { /* * Parse hexa addresses followed by ':' @@ -1307,6 +1320,8 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil { char linkname[PATH_MAX]; char *build_id_filename; + char *build_id_path = NULL; + char *pos; if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && !dso__is_kcore(dso)) @@ -1322,8 +1337,21 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil goto fallback; } + build_id_path = strdup(filename); + if (!build_id_path) + return -1; + + /* + * old style build-id cache has name of XX/XXXXXXX.. while + * new style has XX/XXXXXXX../{elf,kallsyms,vdso}. + * extract the build-id part of dirname in the new style only. + */ + pos = strrchr(build_id_path, '/'); + if (pos && strlen(pos) < SBUILD_ID_SIZE - 2) + dirname(build_id_path); + if (dso__is_kcore(dso) || - readlink(filename, linkname, sizeof(linkname)) < 0 || + readlink(build_id_path, linkname, sizeof(linkname)) < 0 || strstr(linkname, DSO__NAME_KALLSYMS) || access(filename, R_OK)) { fallback: @@ -1335,6 +1363,7 @@ fallback: __symbol__join_symfs(filename, filename_size, dso->long_name); } + free(build_id_path); return 0; } @@ -1350,7 +1379,9 @@ static const char *annotate__norm_arch(const char *arch_name) return normalize_arch((char *)arch_name); } -int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize) +int symbol__disassemble(struct symbol *sym, struct map *map, + const char *arch_name, size_t privsize, + struct arch **parch) { struct dso *dso = map->dso; char command[PATH_MAX * 2]; @@ -1376,6 +1407,9 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na if (arch == NULL) return -ENOTSUP; + if (parch) + *parch = arch; + if (arch->init) { err = arch->init(arch); if (err) { @@ -1402,31 +1436,10 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na sizeof(symfs_filename)); } } else if (dso__needs_decompress(dso)) { - char tmp[PATH_MAX]; - struct kmod_path m; - int fd; - bool ret; + char tmp[KMOD_DECOMP_LEN]; - if (kmod_path__parse_ext(&m, symfs_filename)) - goto out; - - snprintf(tmp, PATH_MAX, "/tmp/perf-kmod-XXXXXX"); - - fd = mkstemp(tmp); - if (fd < 0) { - free(m.ext); - goto out; - } - - ret = decompress_to_file(m.ext, symfs_filename, fd); - - if (ret) - pr_err("Cannot decompress %s %s\n", m.ext, symfs_filename); - - free(m.ext); - close(fd); - - if (!ret) + if (dso__decompress_kmodule_path(dso, symfs_filename, + tmp, sizeof(tmp)) < 0) goto out; strcpy(symfs_filename, tmp); @@ -1435,7 +1448,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na snprintf(command, sizeof(command), "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -l -d %s %s -C %s 2>/dev/null|grep -v %s|expand", + " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand", objdump_path ? objdump_path : "objdump", disassembler_style ? "-M " : "", disassembler_style ? disassembler_style : "", @@ -1482,6 +1495,12 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na nline = 0; while (!feof(file)) { + /* + * The source code line number (lineno) needs to be kept in + * accross calls to symbol__parse_objdump_line(), so that it + * can associate it with the instructions till the next one. + * See disasm_line__new() and struct disasm_line::line_nr. + */ if (symbol__parse_objdump_line(sym, map, arch, file, privsize, &lineno) < 0) break; @@ -1651,24 +1670,31 @@ 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++) { - u64 offset; + u64 offset, nr_samples; double percent_max = 0.0; src_line->nr_pcnt = nr_pcnt; for (k = 0; k < nr_pcnt; k++) { + double percent = 0.0; + h = annotation__histogram(notes, evidx + k); - src_line->samples[k].percent = 100.0 * h->addr[i] / h->sum; + nr_samples = h->addr[i]; + if (h->sum) + percent = 100.0 * nr_samples / h->sum; - if (src_line->samples[k].percent > percent_max) - percent_max = src_line->samples[k].percent; + if (percent > percent_max) + percent_max = percent; + src_line->samples[k].percent = percent; + src_line->samples[k].nr = nr_samples; } if (percent_max <= 0.5) goto next; offset = start + i; - src_line->path = get_srcline(map->dso, offset, NULL, false); + src_line->path = get_srcline(map->dso, offset, NULL, + false, true); insert_source_line(&tmp_root, src_line); next: @@ -1768,7 +1794,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, printf("%-*.*s----\n", graph_dotted_len, graph_dotted_len, graph_dotted_line); - if (verbose) + if (verbose > 0) symbol__annotate_hits(sym, evsel); list_for_each_entry(pos, ¬es->src->source, node) { @@ -1880,7 +1906,8 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, struct rb_root source_line = RB_ROOT; u64 len; - if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), 0) < 0) + if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), + 0, NULL) < 0) return -1; len = symbol__size(sym); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 09776b5af991..21055034aedd 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -98,7 +98,7 @@ struct cyc_hist { struct source_line_samples { double percent; double percent_sum; - double nr; + u64 nr; }; struct source_line { @@ -158,7 +158,9 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr); int symbol__alloc_hist(struct symbol *sym); void symbol__annotate_zero_histograms(struct symbol *sym); -int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize); +int symbol__disassemble(struct symbol *sym, struct map *map, + const char *arch_name, size_t privsize, + struct arch **parch); enum symbol_disassemble_errno { SYMBOL_ANNOTATE_ERRNO__SUCCESS = 0, diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index c5a6e0b12452..5547457566a7 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -13,10 +13,10 @@ * */ +#include <inttypes.h> #include <sys/types.h> #include <sys/mman.h> #include <stdbool.h> -#include <ctype.h> #include <string.h> #include <limits.h> #include <errno.h> @@ -46,7 +46,6 @@ #include "cpumap.h" #include "thread_map.h" #include "asm/bug.h" -#include "symbol/kallsyms.h" #include "auxtrace.h" #include <linux/hash.h> @@ -59,6 +58,9 @@ #include "intel-pt.h" #include "intel-bts.h" +#include "sane_ctype.h" +#include "symbol/kallsyms.h" + int auxtrace_mmap__mmap(struct auxtrace_mmap *mm, struct auxtrace_mmap_params *mp, void *userpg, int fd) @@ -320,6 +322,13 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues, return auxtrace_queues__add_buffer(queues, idx, buffer); } +static bool filter_cpu(struct perf_session *session, int cpu) +{ + unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap; + + return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap); +} + int auxtrace_queues__add_event(struct auxtrace_queues *queues, struct perf_session *session, union perf_event *event, off_t data_offset, @@ -329,6 +338,9 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues, unsigned int idx; int err; + if (filter_cpu(session, event->auxtrace.cpu)) + return 0; + buffer = zalloc(sizeof(struct auxtrace_buffer)); if (!buffer) return -ENOMEM; @@ -945,6 +957,8 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts) synth_opts->instructions = true; synth_opts->branches = true; synth_opts->transactions = true; + synth_opts->ptwrites = true; + synth_opts->pwr_events = true; synth_opts->errors = true; synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE; synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD; @@ -1028,6 +1042,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, case 'x': synth_opts->transactions = true; break; + case 'w': + synth_opts->ptwrites = true; + break; + case 'p': + synth_opts->pwr_events = true; + break; case 'e': synth_opts->errors = true; break; @@ -1826,7 +1846,7 @@ static int addr_filter__resolve_kernel_syms(struct addr_filter *filt) filt->addr = start; if (filt->range && !filt->size && !filt->sym_to) { filt->size = size; - no_size = !!size; + no_size = !size; } } @@ -1840,7 +1860,7 @@ static int addr_filter__resolve_kernel_syms(struct addr_filter *filt) if (err) return err; filt->size = start + size - filt->addr; - no_size = !!size; + no_size = !size; } /* The very last symbol in kallsyms does not imply a particular size */ diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 26fb1ee5746a..33b5e6cdf38c 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -17,6 +17,7 @@ #define __PERF_AUXTRACE_H #include <sys/types.h> +#include <errno.h> #include <stdbool.h> #include <stddef.h> #include <linux/list.h> @@ -58,6 +59,8 @@ enum itrace_period_type { * @instructions: whether to synthesize 'instructions' events * @branches: whether to synthesize 'branches' events * @transactions: whether to synthesize events for transactions + * @ptwrites: whether to synthesize events for ptwrites + * @pwr_events: whether to synthesize power events * @errors: whether to synthesize decoder error events * @dont_decode: whether to skip decoding entirely * @log: write a decoding log @@ -71,6 +74,7 @@ enum itrace_period_type { * @period: 'instructions' events period * @period_type: 'instructions' events period type * @initial_skip: skip N events at the beginning. + * @cpu_bitmap: CPUs for which to synthesize events, or NULL for all */ struct itrace_synth_opts { bool set; @@ -78,6 +82,8 @@ struct itrace_synth_opts { bool instructions; bool branches; bool transactions; + bool ptwrites; + bool pwr_events; bool errors; bool dont_decode; bool log; @@ -91,6 +97,7 @@ struct itrace_synth_opts { unsigned long long period; enum itrace_period_type period_type; unsigned long initial_skip; + unsigned long *cpu_bitmap; }; /** diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 36c861103291..4bd2d1d882af 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -9,7 +9,9 @@ #include <bpf/libbpf.h> #include <bpf/bpf.h> #include <linux/err.h> +#include <linux/kernel.h> #include <linux/string.h> +#include <errno.h> #include "perf.h" #include "debug.h" #include "bpf-loader.h" @@ -17,6 +19,7 @@ #include "probe-event.h" #include "probe-finder.h" // for MAX_PROBES #include "parse-events.h" +#include "strfilter.h" #include "llvm-utils.h" #include "c++/clang-c.h" @@ -670,13 +673,13 @@ int bpf__probe(struct bpf_object *obj) err = convert_perf_probe_events(pev, 1); if (err < 0) { - pr_debug("bpf_probe: failed to convert perf probe events"); + pr_debug("bpf_probe: failed to convert perf probe events\n"); goto out; } err = apply_perf_probe_events(pev, 1); if (err < 0) { - pr_debug("bpf_probe: failed to apply perf probe events"); + pr_debug("bpf_probe: failed to apply perf probe events\n"); goto out; } diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index f2b737b225f2..48863867878b 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -85,6 +85,8 @@ int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err, char *buf, size_t size); #else +#include <errno.h> + static inline struct bpf_object * bpf__prepare_load(const char *filename __maybe_unused, bool source __maybe_unused) diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c index 6cdbee119ceb..1356220a9f1b 100644 --- a/tools/perf/util/bpf-prologue.c +++ b/tools/perf/util/bpf-prologue.c @@ -12,6 +12,7 @@ #include "bpf-loader.h" #include "bpf-prologue.h" #include "probe-finder.h" +#include <errno.h> #include <dwarf-regs.h> #include <linux/filter.h> diff --git a/tools/perf/util/bpf-prologue.h b/tools/perf/util/bpf-prologue.h index d94cbea12899..ba564838375f 100644 --- a/tools/perf/util/bpf-prologue.h +++ b/tools/perf/util/bpf-prologue.h @@ -18,6 +18,8 @@ int bpf__gen_prologue(struct probe_trace_arg *args, int nargs, struct bpf_insn *new_prog, size_t *new_cnt, size_t cnt_space); #else +#include <errno.h> + static inline int bpf__gen_prologue(struct probe_trace_arg *args __maybe_unused, int nargs __maybe_unused, diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index e528c40739cc..e0148b081bdf 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -7,18 +7,26 @@ * Copyright (C) 2009, 2010 Arnaldo Carvalho de Melo <acme@redhat.com> */ #include "util.h" +#include <dirent.h> +#include <errno.h> #include <stdio.h> +#include <sys/stat.h> +#include <sys/types.h> #include "build-id.h" #include "event.h" #include "symbol.h" +#include "thread.h" #include <linux/kernel.h> #include "debug.h" #include "session.h" #include "tool.h" #include "header.h" #include "vdso.h" +#include "path.h" #include "probe-file.h" +#include "strlist.h" +#include "sane_ctype.h" static bool no_buildid_cache; @@ -182,13 +190,17 @@ char *build_id_cache__origname(const char *sbuild_id) char buf[PATH_MAX]; char *ret = NULL, *p; size_t offs = 5; /* == strlen("../..") */ + ssize_t len; linkname = build_id_cache__linkname(sbuild_id, NULL, 0); if (!linkname) return NULL; - if (readlink(linkname, buf, PATH_MAX) < 0) + len = readlink(linkname, buf, sizeof(buf) - 1); + if (len <= 0) goto out; + buf[len] = '\0'; + /* The link should be "../..<origpath>/<sbuild_id>" */ p = strrchr(buf, '/'); /* Cut off the "/<sbuild_id>" */ if (p && (p > buf + offs)) { @@ -266,51 +278,6 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) return bf; } -bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size) -{ - char *id_name = NULL, *ch; - struct stat sb; - char sbuild_id[SBUILD_ID_SIZE]; - - if (!dso->has_build_id) - goto err; - - build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); - id_name = build_id_cache__linkname(sbuild_id, NULL, 0); - if (!id_name) - goto err; - if (access(id_name, F_OK)) - goto err; - if (lstat(id_name, &sb) == -1) - goto err; - if ((size_t)sb.st_size > size - 1) - goto err; - if (readlink(id_name, bf, size - 1) < 0) - goto err; - - bf[sb.st_size] = '\0'; - - /* - * link should be: - * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92 - */ - ch = strrchr(bf, '/'); - if (!ch) - goto err; - if (ch - 3 < bf) - goto err; - - free(id_name); - return strncmp(".ko", ch - 3, 3) == 0; -err: - pr_err("Invalid build id: %s\n", id_name ? : - dso->long_name ? : - dso->short_name ? : - "[unknown]"); - free(id_name); - return false; -} - #define dsos__for_each_with_build_id(pos, head) \ list_for_each_entry(pos, head, node) \ if (!pos->has_build_id) \ @@ -443,14 +410,14 @@ void disable_buildid_cache(void) } static bool lsdir_bid_head_filter(const char *name __maybe_unused, - struct dirent *d __maybe_unused) + struct dirent *d) { return (strlen(d->d_name) == 2) && isxdigit(d->d_name[0]) && isxdigit(d->d_name[1]); } static bool lsdir_bid_tail_filter(const char *name __maybe_unused, - struct dirent *d __maybe_unused) + struct dirent *d) { int i = 0; while (isxdigit(d->d_name[i]) && i < SBUILD_ID_SIZE - 3) @@ -690,7 +657,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, err = 0; /* Update SDT cache : error is just warned */ - if (build_id_cache__add_sdt_cache(sbuild_id, realname) < 0) + if (realname && build_id_cache__add_sdt_cache(sbuild_id, realname) < 0) pr_debug4("Failed to update/scan SDT cache for %s\n", realname); out_free: diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index d27990610f9f..96690a55c62c 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -5,7 +5,6 @@ #define SBUILD_ID_SIZE (BUILD_ID_SIZE * 2 + 1) #include "tool.h" -#include "strlist.h" #include <linux/types.h> extern struct perf_tool build_id__mark_dso_hit_ops; @@ -18,7 +17,6 @@ char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf, size_t size); char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size); -bool dso__build_id_is_kmod(const 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, @@ -34,6 +32,9 @@ char *build_id_cache__origname(const char *sbuild_id); char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size); char *build_id_cache__cachedir(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso); + +struct strlist; + struct strlist *build_id_cache__list_all(bool validonly); char *build_id_cache__complement(const char *incomplete_sbuild_id); int build_id_cache__list_build_ids(const char *pathname, @@ -42,6 +43,10 @@ bool build_id_cache__cached(const char *sbuild_id); int build_id_cache__add_s(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso); int build_id_cache__remove_s(const char *sbuild_id); + +extern char buildid_dir[]; + +void set_buildid_dir(const char *dir); void disable_buildid_cache(void); #endif diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h index 0eadd792ab1f..ccafcf72b37a 100644 --- a/tools/perf/util/c++/clang-c.h +++ b/tools/perf/util/c++/clang-c.h @@ -20,6 +20,7 @@ extern int perf_clang__compile_bpf(const char *filename, size_t *p_obj_buf_sz); #else +#include <errno.h> static inline void perf_clang__init(void) { } static inline void perf_clang__cleanup(void) { } diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 512c0c83fbc6..0175765c05b9 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -5,6 +5,7 @@ #include <subcmd/pager.h> #include "../ui/ui.h" +#include <linux/compiler.h> #include <linux/string.h> #define CMD_EXEC_PATH "--exec-path" @@ -15,7 +16,6 @@ #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR" #define PERF_PAGER_ENVIRONMENT "PERF_PAGER" -char *alias_lookup(const char *alias); int split_cmdline(char *cmdline, const char ***argv); #define alloc_nr(x) (((x)+16)*3/2) @@ -25,6 +25,6 @@ static inline int is_absolute_path(const char *path) return path[0] == '/'; } -char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2))); +char *mkpath(const char *fmt, ...) __printf(1, 2); #endif /* __PERF_CACHE_H */ diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 42922512c1c6..b4204b43ed58 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -9,6 +9,7 @@ * */ +#include <inttypes.h> #include <stdlib.h> #include <stdio.h> #include <stdbool.h> @@ -23,6 +24,21 @@ #include "machine.h" #include "callchain.h" +#define CALLCHAIN_PARAM_DEFAULT \ + .mode = CHAIN_GRAPH_ABS, \ + .min_percent = 0.5, \ + .order = ORDER_CALLEE, \ + .key = CCKEY_FUNCTION, \ + .value = CCVAL_PERCENT, \ + +struct callchain_param callchain_param = { + CALLCHAIN_PARAM_DEFAULT +}; + +struct callchain_param callchain_param_default = { + CALLCHAIN_PARAM_DEFAULT +}; + __thread struct callchain_cursor callchain_cursor; int parse_callchain_record_opt(const char *arg, struct callchain_param *param) @@ -48,6 +64,8 @@ static int parse_callchain_mode(const char *value) callchain_param.mode = CHAIN_FOLDED; return 0; } + + pr_err("Invalid callchain mode: %s\n", value); return -1; } @@ -63,6 +81,8 @@ static int parse_callchain_order(const char *value) callchain_param.order_set = true; return 0; } + + pr_err("Invalid callchain order: %s\n", value); return -1; } @@ -76,10 +96,16 @@ static int parse_callchain_sort_key(const char *value) callchain_param.key = CCKEY_ADDRESS; return 0; } + if (!strncmp(value, "srcline", strlen(value))) { + callchain_param.key = CCKEY_SRCLINE; + return 0; + } if (!strncmp(value, "branch", strlen(value))) { callchain_param.branch_callstack = 1; return 0; } + + pr_err("Invalid callchain sort key: %s\n", value); return -1; } @@ -97,6 +123,34 @@ static int parse_callchain_value(const char *value) callchain_param.value = CCVAL_COUNT; return 0; } + + pr_err("Invalid callchain config key: %s\n", value); + return -1; +} + +static int get_stack_size(const char *str, unsigned long *_size) +{ + char *endptr; + unsigned long size; + unsigned long max_size = round_down(USHRT_MAX, sizeof(u64)); + + size = strtoul(str, &endptr, 0); + + do { + if (*endptr) + break; + + size = round_up(size, sizeof(u64)); + if (!size || size > max_size) + break; + + *_size = size; + return 0; + + } while (0); + + pr_err("callchain: Incorrect stack dump size (max %ld): %s\n", + max_size, str); return -1; } @@ -104,7 +158,7 @@ static int __parse_callchain_report_opt(const char *arg, bool allow_record_opt) { char *tok; - char *endptr; + char *endptr, *saveptr = NULL; bool minpcnt_set = false; bool record_opt_set = false; bool try_stack_size = false; @@ -115,7 +169,7 @@ __parse_callchain_report_opt(const char *arg, bool allow_record_opt) if (!arg) return 0; - while ((tok = strtok((char *)arg, ",")) != NULL) { + while ((tok = strtok_r((char *)arg, ",", &saveptr)) != NULL) { if (!strncmp(tok, "none", strlen(tok))) { callchain_param.mode = CHAIN_NONE; callchain_param.enabled = false; @@ -183,6 +237,68 @@ int parse_callchain_top_opt(const char *arg) return __parse_callchain_report_opt(arg, true); } +int parse_callchain_record(const char *arg, struct callchain_param *param) +{ + char *tok, *name, *saveptr = NULL; + char *buf; + int ret = -1; + + /* We need buffer that we know we can write to. */ + buf = malloc(strlen(arg) + 1); + if (!buf) + return -ENOMEM; + + strcpy(buf, arg); + + tok = strtok_r((char *)buf, ",", &saveptr); + name = tok ? : (char *)buf; + + do { + /* Framepointer style */ + if (!strncmp(name, "fp", sizeof("fp"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + param->record_mode = CALLCHAIN_FP; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for --call-graph fp\n"); + break; + + /* Dwarf style */ + } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { + const unsigned long default_stack_dump_size = 8192; + + ret = 0; + param->record_mode = CALLCHAIN_DWARF; + param->dump_size = default_stack_dump_size; + + tok = strtok_r(NULL, ",", &saveptr); + if (tok) { + unsigned long size = 0; + + ret = get_stack_size(tok, &size); + param->dump_size = size; + } + } else if (!strncmp(name, "lbr", sizeof("lbr"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + param->record_mode = CALLCHAIN_LBR; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for --call-graph lbr\n"); + break; + } else { + pr_err("callchain: Unknown --call-graph option " + "value: %s\n", arg); + break; + } + + } while (0); + + free(buf); + return ret; +} + int perf_callchain_config(const char *var, const char *value) { char *endptr; @@ -210,13 +326,17 @@ int perf_callchain_config(const char *var, const char *value) return parse_callchain_sort_key(value); if (!strcmp(var, "threshold")) { callchain_param.min_percent = strtod(value, &endptr); - if (value == endptr) + if (value == endptr) { + pr_err("Invalid callchain threshold: %s\n", value); return -1; + } } if (!strcmp(var, "print-limit")) { callchain_param.print_limit = strtod(value, &endptr); - if (value == endptr) + if (value == endptr) { + pr_err("Invalid callchain print limit: %s\n", value); return -1; + } } return 0; @@ -437,7 +557,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) } call->ip = cursor_node->ip; call->ms.sym = cursor_node->sym; - call->ms.map = cursor_node->map; + call->ms.map = map__get(cursor_node->map); if (cursor_node->branch) { call->branch_count = 1; @@ -477,6 +597,7 @@ add_child(struct callchain_node *parent, list_for_each_entry_safe(call, tmp, &new->val, list) { list_del(&call->list); + map__zput(call->ms.map); free(call); } free(new); @@ -497,14 +618,56 @@ enum match_result { MATCH_GT, }; +static enum match_result match_chain_srcline(struct callchain_cursor_node *node, + struct callchain_list *cnode) +{ + char *left = NULL; + char *right = NULL; + enum match_result ret = MATCH_EQ; + int cmp; + + if (cnode->ms.map) + left = get_srcline(cnode->ms.map->dso, + map__rip_2objdump(cnode->ms.map, cnode->ip), + cnode->ms.sym, true, false); + if (node->map) + right = get_srcline(node->map->dso, + map__rip_2objdump(node->map, node->ip), + node->sym, true, false); + + if (left && right) + cmp = strcmp(left, right); + else if (!left && right) + cmp = 1; + else if (left && !right) + cmp = -1; + else if (cnode->ip == node->ip) + cmp = 0; + else + cmp = (cnode->ip < node->ip) ? -1 : 1; + + if (cmp != 0) + ret = cmp < 0 ? MATCH_LT : MATCH_GT; + + free_srcline(left); + free_srcline(right); + return ret; +} + static enum match_result match_chain(struct callchain_cursor_node *node, struct callchain_list *cnode) { struct symbol *sym = node->sym; u64 left, right; - if (cnode->ms.sym && sym && - callchain_param.key == CCKEY_FUNCTION) { + if (callchain_param.key == CCKEY_SRCLINE) { + enum match_result match = match_chain_srcline(node, cnode); + + if (match != MATCH_ERROR) + return match; + } + + if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) { left = cnode->ms.sym->start; right = sym->start; } else { @@ -761,6 +924,7 @@ merge_chain_branch(struct callchain_cursor *cursor, list->ms.map, list->ms.sym, false, NULL, 0, 0); list_del(&list->list); + map__zput(list->ms.map); free(list); } @@ -811,7 +975,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor, } node->ip = ip; - node->map = map; + map__zput(node->map); + node->map = map__get(map); node->sym = sym; node->branch = branch; node->nr_loop_iter = nr_loop_iter; @@ -896,15 +1061,16 @@ out: char *callchain_list__sym_name(struct callchain_list *cl, char *bf, size_t bfsize, bool show_dso) { + bool show_addr = callchain_param.key == CCKEY_ADDRESS; + bool show_srcline = show_addr || callchain_param.key == CCKEY_SRCLINE; int printed; if (cl->ms.sym) { - if (callchain_param.key == CCKEY_ADDRESS && - cl->ms.map && !cl->srcline) + if (show_srcline && cl->ms.map && !cl->srcline) cl->srcline = get_srcline(cl->ms.map->dso, map__rip_2objdump(cl->ms.map, cl->ip), - cl->ms.sym, false); + cl->ms.sym, false, show_addr); if (cl->srcline) printed = scnprintf(bf, bfsize, "%s %s", cl->ms.sym->name, cl->srcline); @@ -1048,63 +1214,100 @@ int callchain_branch_counts(struct callchain_root *root, cycles_count); } -static int callchain_counts_printf(FILE *fp, char *bf, int bfsize, - u64 branch_count, u64 predicted_count, - u64 abort_count, u64 cycles_count, - u64 iter_count, u64 samples_count) +static int counts_str_build(char *bf, int bfsize, + u64 branch_count, u64 predicted_count, + u64 abort_count, u64 cycles_count, + u64 iter_count, u64 samples_count) { double predicted_percent = 0.0; const char *null_str = ""; char iter_str[32]; - char *str; - u64 cycles = 0; - - if (branch_count == 0) { - if (fp) - return fprintf(fp, " (calltrace)"); + char cycle_str[32]; + char *istr, *cstr; + u64 cycles; + if (branch_count == 0) return scnprintf(bf, bfsize, " (calltrace)"); - } + + cycles = cycles_count / branch_count; if (iter_count && samples_count) { - scnprintf(iter_str, sizeof(iter_str), - ", iterations:%" PRId64 "", - iter_count / samples_count); - str = iter_str; + if (cycles > 0) + scnprintf(iter_str, sizeof(iter_str), + " iterations:%" PRId64 "", + iter_count / samples_count); + else + scnprintf(iter_str, sizeof(iter_str), + "iterations:%" PRId64 "", + iter_count / samples_count); + istr = iter_str; } else - str = (char *)null_str; + istr = (char *)null_str; + + if (cycles > 0) { + scnprintf(cycle_str, sizeof(cycle_str), + "cycles:%" PRId64 "", cycles); + cstr = cycle_str; + } else + cstr = (char *)null_str; predicted_percent = predicted_count * 100.0 / branch_count; - cycles = cycles_count / branch_count; - if ((predicted_percent >= 100.0) && (abort_count == 0)) { - if (fp) - return fprintf(fp, " (cycles:%" PRId64 "%s)", - cycles, str); + if ((predicted_count == branch_count) && (abort_count == 0)) { + if ((cycles > 0) || (istr != (char *)null_str)) + return scnprintf(bf, bfsize, " (%s%s)", cstr, istr); + else + return scnprintf(bf, bfsize, "%s", (char *)null_str); + } - return scnprintf(bf, bfsize, " (cycles:%" PRId64 "%s)", - cycles, str); + if ((predicted_count < branch_count) && (abort_count == 0)) { + if ((cycles > 0) || (istr != (char *)null_str)) + return scnprintf(bf, bfsize, + " (predicted:%.1f%% %s%s)", + predicted_percent, cstr, istr); + else { + return scnprintf(bf, bfsize, + " (predicted:%.1f%%)", + predicted_percent); + } } - if ((predicted_percent < 100.0) && (abort_count == 0)) { - if (fp) - return fprintf(fp, - " (predicted:%.1f%%, cycles:%" PRId64 "%s)", - predicted_percent, cycles, str); + if ((predicted_count == branch_count) && (abort_count > 0)) { + if ((cycles > 0) || (istr != (char *)null_str)) + return scnprintf(bf, bfsize, + " (abort:%" PRId64 " %s%s)", + abort_count, cstr, istr); + else + return scnprintf(bf, bfsize, + " (abort:%" PRId64 ")", + abort_count); + } + if ((cycles > 0) || (istr != (char *)null_str)) return scnprintf(bf, bfsize, - " (predicted:%.1f%%, cycles:%" PRId64 "%s)", - predicted_percent, cycles, str); - } + " (predicted:%.1f%% abort:%" PRId64 " %s%s)", + predicted_percent, abort_count, cstr, istr); + + return scnprintf(bf, bfsize, + " (predicted:%.1f%% abort:%" PRId64 ")", + predicted_percent, abort_count); +} + +static int callchain_counts_printf(FILE *fp, char *bf, int bfsize, + u64 branch_count, u64 predicted_count, + u64 abort_count, u64 cycles_count, + u64 iter_count, u64 samples_count) +{ + char str[128]; + + counts_str_build(str, sizeof(str), branch_count, + predicted_count, abort_count, cycles_count, + iter_count, samples_count); if (fp) - return fprintf(fp, - " (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)", - predicted_percent, abort_count, cycles, str); + return fprintf(fp, "%s", str); - return scnprintf(bf, bfsize, - " (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)", - predicted_percent, abort_count, cycles, str); + return scnprintf(bf, bfsize, "%s", str); } int callchain_list_counts__printf_value(struct callchain_node *node, @@ -1142,11 +1345,13 @@ static void free_callchain_node(struct callchain_node *node) list_for_each_entry_safe(list, tmp, &node->parent_val, list) { list_del(&list->list); + map__zput(list->ms.map); free(list); } list_for_each_entry_safe(list, tmp, &node->val, list) { list_del(&list->list); + map__zput(list->ms.map); free(list); } @@ -1210,6 +1415,7 @@ int callchain_node__make_parent_list(struct callchain_node *node) goto out; *new = *chain; new->has_children = false; + map__get(new->ms.map); list_add_tail(&new->list, &head); } parent = parent->parent; @@ -1230,6 +1436,7 @@ int callchain_node__make_parent_list(struct callchain_node *node) out: list_for_each_entry_safe(chain, new, &head, list) { list_del(&chain->list); + map__zput(chain->ms.map); free(chain); } return -ENOMEM; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 35c8e379530f..c56c23dbbf72 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -5,6 +5,7 @@ #include <linux/list.h> #include <linux/rbtree.h> #include "event.h" +#include "map.h" #include "symbol.h" #define HELP_PAD "\t\t\t\t" @@ -76,7 +77,8 @@ typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *, enum chain_key { CCKEY_FUNCTION, - CCKEY_ADDRESS + CCKEY_ADDRESS, + CCKEY_SRCLINE }; enum chain_value { @@ -184,8 +186,13 @@ int callchain_merge(struct callchain_cursor *cursor, */ static inline void callchain_cursor_reset(struct callchain_cursor *cursor) { + struct callchain_cursor_node *node; + cursor->nr = 0; cursor->last = &cursor->first; + + for (node = cursor->first; node != NULL; node = node->next) + map__zput(node->map); } int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip, diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 8fdee24725a7..03347748f3fa 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -4,6 +4,7 @@ #include "evsel.h" #include "cgroup.h" #include "evlist.h" +#include <linux/stringify.h> int nr_cgroups; @@ -12,8 +13,8 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen) { FILE *fp; char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1]; + char path_v1[PATH_MAX + 1], path_v2[PATH_MAX + 2], *path; char *token, *saved_ptr = NULL; - int found = 0; fp = fopen("/proc/mounts", "r"); if (!fp) @@ -24,31 +25,43 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen) * and inspect every cgroupfs mount point to find one that has * perf_event subsystem */ - while (fscanf(fp, "%*s %"STR(PATH_MAX)"s %"STR(PATH_MAX)"s %" - STR(PATH_MAX)"s %*d %*d\n", + path_v1[0] = '\0'; + path_v2[0] = '\0'; + + while (fscanf(fp, "%*s %"__stringify(PATH_MAX)"s %"__stringify(PATH_MAX)"s %" + __stringify(PATH_MAX)"s %*d %*d\n", mountpoint, type, tokens) == 3) { - if (!strcmp(type, "cgroup")) { + if (!path_v1[0] && !strcmp(type, "cgroup")) { token = strtok_r(tokens, ",", &saved_ptr); while (token != NULL) { if (!strcmp(token, "perf_event")) { - found = 1; + strcpy(path_v1, mountpoint); break; } token = strtok_r(NULL, ",", &saved_ptr); } } - if (found) + + if (!path_v2[0] && !strcmp(type, "cgroup2")) + strcpy(path_v2, mountpoint); + + if (path_v1[0] && path_v2[0]) break; } fclose(fp); - if (!found) + + if (path_v1[0]) + path = path_v1; + else if (path_v2[0]) + path = path_v2; + else return -1; - if (strlen(mountpoint) < maxlen) { - strcpy(buf, mountpoint); + if (strlen(path) < maxlen) { + strcpy(buf, path); return 0; } return -1; @@ -115,19 +128,19 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) goto found; n++; } - if (atomic_read(&cgrp->refcnt) == 0) + if (refcount_read(&cgrp->refcnt) == 0) free(cgrp); return -1; found: - atomic_inc(&cgrp->refcnt); + refcount_inc(&cgrp->refcnt); counter->cgrp = cgrp; return 0; } void close_cgroup(struct cgroup_sel *cgrp) { - if (cgrp && atomic_dec_and_test(&cgrp->refcnt)) { + if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) { close(cgrp->fd); zfree(&cgrp->name); free(cgrp); diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h index 31f8dcdbd7ef..d91966b97cbd 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -1,14 +1,14 @@ #ifndef __CGROUP_H__ #define __CGROUP_H__ -#include <linux/atomic.h> +#include <linux/refcount.h> struct option; struct cgroup_sel { char *name; int fd; - atomic_t refcnt; + refcount_t refcnt; }; diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index f0dcd0ee0afa..4b4f00df58a8 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -1,3 +1,4 @@ +#include <errno.h> #include <sched.h> #include "util.h" #include "../perf.h" diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h index d0d465953d36..94a5a7d829d5 100644 --- a/tools/perf/util/cloexec.h +++ b/tools/perf/util/cloexec.h @@ -3,10 +3,4 @@ unsigned long perf_event_open_cloexec_flag(void); -#ifdef __GLIBC_PREREQ -#if !__GLIBC_PREREQ(2, 6) && !defined(__UCLIBC__) -int sched_getcpu(void) __THROW; -#endif -#endif - #endif /* __PERF_CLOEXEC_H */ diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index a93997f16dec..52122bcc3170 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -1,6 +1,8 @@ #ifndef __PERF_COLOR_H #define __PERF_COLOR_H +#include <stdio.h> + /* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */ #define COLOR_MAXLEN 24 diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 21b7ff382c3f..7bc981b6bf29 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -1,13 +1,15 @@ #include "comm.h" #include "util.h" +#include <errno.h> #include <stdlib.h> #include <stdio.h> -#include <linux/atomic.h> +#include <string.h> +#include <linux/refcount.h> struct comm_str { char *str; struct rb_node rb_node; - atomic_t refcnt; + refcount_t refcnt; }; /* Should perhaps be moved to struct machine */ @@ -16,13 +18,13 @@ static struct rb_root comm_str_root; static struct comm_str *comm_str__get(struct comm_str *cs) { if (cs) - atomic_inc(&cs->refcnt); + refcount_inc(&cs->refcnt); return cs; } static void comm_str__put(struct comm_str *cs) { - if (cs && atomic_dec_and_test(&cs->refcnt)) { + if (cs && refcount_dec_and_test(&cs->refcnt)) { rb_erase(&cs->rb_node, &comm_str_root); zfree(&cs->str); free(cs); @@ -43,7 +45,7 @@ static struct comm_str *comm_str__alloc(const char *str) return NULL; } - atomic_set(&cs->refcnt, 0); + refcount_set(&cs->refcnt, 1); return cs; } @@ -61,7 +63,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) cmp = strcmp(str, iter->str); if (!cmp) - return iter; + return comm_str__get(iter); if (cmp < 0) p = &(*p)->rb_left; @@ -95,8 +97,6 @@ struct comm *comm__new(const char *str, u64 timestamp, bool exec) return NULL; } - comm_str__get(comm->comm_str); - return comm; } @@ -108,7 +108,6 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec) if (!new) return -ENOMEM; - comm_str__get(new); comm_str__put(old); comm->comm_str = new; comm->start = timestamp; diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h new file mode 100644 index 000000000000..67fd1bb7c2b7 --- /dev/null +++ b/tools/perf/util/compress.h @@ -0,0 +1,12 @@ +#ifndef PERF_COMPRESS_H +#define PERF_COMPRESS_H + +#ifdef HAVE_ZLIB_SUPPORT +int gzip_decompress_to_file(const char *input, int output_fd); +#endif + +#ifdef HAVE_LZMA_SUPPORT +int lzma_decompress_to_file(const char *input, int output_fd); +#endif + +#endif /* PERF_COMPRESS_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 3d906dbbef74..31a7dea248d0 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -8,12 +8,19 @@ * Copyright (C) Johannes Schindelin, 2005 * */ +#include <errno.h> +#include <sys/param.h> #include "util.h" #include "cache.h" #include <subcmd/exec-cmd.h> #include "util/hist.h" /* perf_hist_config */ #include "util/llvm-utils.h" /* perf_llvm_config */ #include "config.h" +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +#include "sane_ctype.h" #define MAXNAME (256) @@ -328,32 +335,42 @@ static int perf_parse_long(const char *value, long *ret) return 0; } -static void die_bad_config(const char *name) +static void bad_config(const char *name) { if (config_file_name) - die("bad config value for '%s' in %s", name, config_file_name); - die("bad config value for '%s'", name); + pr_warning("bad config value for '%s' in %s, ignoring...\n", name, config_file_name); + else + pr_warning("bad config value for '%s', ignoring...\n", name); } -u64 perf_config_u64(const char *name, const char *value) +int perf_config_u64(u64 *dest, const char *name, const char *value) { long long ret = 0; - if (!perf_parse_llong(value, &ret)) - die_bad_config(name); - return (u64) ret; + if (!perf_parse_llong(value, &ret)) { + bad_config(name); + return -1; + } + + *dest = ret; + return 0; } -int perf_config_int(const char *name, const char *value) +int perf_config_int(int *dest, const char *name, const char *value) { long ret = 0; - if (!perf_parse_long(value, &ret)) - die_bad_config(name); - return ret; + if (!perf_parse_long(value, &ret)) { + bad_config(name); + return -1; + } + *dest = ret; + return 0; } static int perf_config_bool_or_int(const char *name, const char *value, int *is_bool) { + int ret; + *is_bool = 1; if (!value) return 1; @@ -364,7 +381,7 @@ static int perf_config_bool_or_int(const char *name, const char *value, int *is_ if (!strcasecmp(value, "false") || !strcasecmp(value, "no") || !strcasecmp(value, "off")) return 0; *is_bool = 0; - return perf_config_int(name, value); + return perf_config_int(&ret, name, value) < 0 ? -1 : ret; } int perf_config_bool(const char *name, const char *value) @@ -386,8 +403,10 @@ static int perf_buildid_config(const char *var, const char *value) if (!strcmp(var, "buildid.dir")) { const char *dir = perf_config_dirname(var, value); - if (!dir) + if (!dir) { + pr_err("Invalid buildid directory!\n"); return -1; + } strncpy(buildid_dir, dir, MAXPATHLEN-1); buildid_dir[MAXPATHLEN-1] = '\0'; } @@ -405,10 +424,9 @@ static int perf_default_core_config(const char *var __maybe_unused, static int perf_ui_config(const char *var, const char *value) { /* Add other config variables here. */ - if (!strcmp(var, "ui.show-headers")) { + if (!strcmp(var, "ui.show-headers")) symbol_conf.show_hist_headers = perf_config_bool(var, value); - return 0; - } + return 0; } @@ -626,6 +644,8 @@ static int perf_config_set__init(struct perf_config_set *set) { int ret = -1; const char *home = NULL; + char *user_config; + struct stat st; /* Setting $PERF_CONFIG makes perf read _only_ the given config file. */ if (config_exclusive_filename) @@ -636,33 +656,39 @@ static int perf_config_set__init(struct perf_config_set *set) } home = getenv("HOME"); - if (perf_config_global() && home) { - char *user_config = strdup(mkpath("%s/.perfconfig", home)); - struct stat st; - if (user_config == NULL) { - warning("Not enough memory to process %s/.perfconfig, " - "ignoring it.", home); - goto out; - } + /* + * Skip reading user config if: + * - there is no place to read it from (HOME) + * - we are asked not to (PERF_CONFIG_NOGLOBAL=1) + */ + if (!home || !*home || !perf_config_global()) + return 0; - if (stat(user_config, &st) < 0) - goto out_free; + user_config = strdup(mkpath("%s/.perfconfig", home)); + if (user_config == NULL) { + pr_warning("Not enough memory to process %s/.perfconfig, ignoring it.", home); + goto out; + } - if (st.st_uid && (st.st_uid != geteuid())) { - warning("File %s not owned by current user or root, " - "ignoring it.", user_config); - goto out_free; - } + if (stat(user_config, &st) < 0) { + if (errno == ENOENT) + ret = 0; + goto out_free; + } - if (!st.st_size) - goto out_free; + ret = 0; + if (st.st_uid && (st.st_uid != geteuid())) { + pr_warning("File %s not owned by current user or root, ignoring it.", user_config); + goto out_free; + } + + if (st.st_size) ret = perf_config_from_file(collect_config, user_config, set); out_free: - free(user_config); - } + free(user_config); out: return ret; } @@ -777,7 +803,8 @@ void perf_config_set__delete(struct perf_config_set *set) */ int config_error_nonbool(const char *var) { - return error("Missing value for '%s'", var); + pr_err("Missing value for '%s'", var); + return -1; } void set_buildid_dir(const char *dir) diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index 1a59a6b43f8b..b6bb11f3f165 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -27,8 +27,8 @@ extern const char *config_exclusive_filename; typedef int (*config_fn_t)(const char *, const char *, void *); int perf_default_config(const char *, const char *, void *); int perf_config(config_fn_t fn, void *); -int perf_config_int(const char *, const char *); -u64 perf_config_u64(const char *, const char *); +int perf_config_int(int *dest, const char *, const char *); +int perf_config_u64(u64 *dest, const char *, const char *); int perf_config_bool(const char *, const char *); int config_error_nonbool(const char *); const char *perf_etc_perfconfig(void); diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c index e3fde313deb2..c4af82ab7808 100644 --- a/tools/perf/util/counts.c +++ b/tools/perf/util/counts.c @@ -1,6 +1,8 @@ +#include <errno.h> #include <stdlib.h> #include "evsel.h" #include "counts.h" +#include "util.h" struct perf_counts *perf_counts__new(int ncpus, int nthreads) { diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 2c0b52264a46..37b3bb79ee08 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -3,12 +3,16 @@ #include "../perf.h" #include "cpumap.h" #include <assert.h> +#include <dirent.h> #include <stdio.h> #include <stdlib.h> #include <linux/bitmap.h> #include "asm/bug.h" +#include "sane_ctype.h" + static int max_cpu_num; +static int max_present_cpu_num; static int max_node_num; static int *cpunode_map; @@ -28,7 +32,7 @@ static struct cpu_map *cpu_map__default_new(void) cpus->map[i] = i; cpus->nr = nr_cpus; - atomic_set(&cpus->refcnt, 1); + refcount_set(&cpus->refcnt, 1); } return cpus; @@ -42,7 +46,7 @@ static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) if (cpus != NULL) { cpus->nr = nr_cpus; memcpy(cpus->map, tmp_cpus, payload_size); - atomic_set(&cpus->refcnt, 1); + refcount_set(&cpus->refcnt, 1); } return cpus; @@ -251,7 +255,7 @@ struct cpu_map *cpu_map__dummy_new(void) if (cpus != NULL) { cpus->nr = 1; cpus->map[0] = -1; - atomic_set(&cpus->refcnt, 1); + refcount_set(&cpus->refcnt, 1); } return cpus; @@ -268,7 +272,7 @@ struct cpu_map *cpu_map__empty_new(int nr) for (i = 0; i < nr; i++) cpus->map[i] = -1; - atomic_set(&cpus->refcnt, 1); + refcount_set(&cpus->refcnt, 1); } return cpus; @@ -277,7 +281,7 @@ struct cpu_map *cpu_map__empty_new(int nr) static void cpu_map__delete(struct cpu_map *map) { if (map) { - WARN_ONCE(atomic_read(&map->refcnt) != 0, + WARN_ONCE(refcount_read(&map->refcnt) != 0, "cpu_map refcnt unbalanced\n"); free(map); } @@ -286,13 +290,13 @@ static void cpu_map__delete(struct cpu_map *map) struct cpu_map *cpu_map__get(struct cpu_map *map) { if (map) - atomic_inc(&map->refcnt); + refcount_inc(&map->refcnt); return map; } void cpu_map__put(struct cpu_map *map) { - if (map && atomic_dec_and_test(&map->refcnt)) + if (map && refcount_dec_and_test(&map->refcnt)) cpu_map__delete(map); } @@ -356,7 +360,7 @@ int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, /* ensure we process id in increasing order */ qsort(c->map, c->nr, sizeof(int), cmp_ids); - atomic_set(&c->refcnt, 1); + refcount_set(&c->refcnt, 1); *res = c; return 0; } @@ -442,6 +446,7 @@ static void set_max_cpu_num(void) /* set up default */ max_cpu_num = 4096; + max_present_cpu_num = 4096; mnt = sysfs__mountpoint(); if (!mnt) @@ -455,6 +460,17 @@ static void set_max_cpu_num(void) } ret = get_max_num(path, &max_cpu_num); + if (ret) + goto out; + + /* get the highest present cpu number for a sparse allocation */ + ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt); + if (ret == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + goto out; + } + + ret = get_max_num(path, &max_present_cpu_num); out: if (ret) @@ -505,6 +521,15 @@ int cpu__max_cpu(void) return max_cpu_num; } +int cpu__max_present_cpu(void) +{ + if (unlikely(!max_present_cpu_num)) + set_max_cpu_num(); + + return max_present_cpu_num; +} + + int cpu__get_node(int cpu) { if (unlikely(cpunode_map == NULL)) { @@ -651,3 +676,49 @@ size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size) pr_debug("cpumask list: %s\n", buf); return ret; } + +static char hex_char(unsigned char val) +{ + if (val < 10) + return val + '0'; + if (val < 16) + return val - 10 + 'a'; + return '?'; +} + +size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size) +{ + int i, cpu; + char *ptr = buf; + unsigned char *bitmap; + int last_cpu = cpu_map__cpu(map, map->nr - 1); + + bitmap = zalloc((last_cpu + 7) / 8); + if (bitmap == NULL) { + buf[0] = '\0'; + return 0; + } + + for (i = 0; i < map->nr; i++) { + cpu = cpu_map__cpu(map, i); + bitmap[cpu / 8] |= 1 << (cpu % 8); + } + + for (cpu = last_cpu / 4 * 4; cpu >= 0; cpu -= 4) { + unsigned char bits = bitmap[cpu / 8]; + + if (cpu % 8) + bits >>= 4; + else + bits &= 0xf; + + *ptr++ = hex_char(bits); + if ((cpu % 32) == 0 && cpu > 0) + *ptr++ = ','; + } + *ptr = '\0'; + free(bitmap); + + buf[size - 1] = '\0'; + return ptr - buf; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 06bd689f5989..6b8bff87481d 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -3,13 +3,13 @@ #include <stdio.h> #include <stdbool.h> -#include <linux/atomic.h> +#include <linux/refcount.h> #include "perf.h" #include "util/debug.h" struct cpu_map { - atomic_t refcnt; + refcount_t refcnt; int nr; int map[]; }; @@ -20,6 +20,7 @@ struct cpu_map *cpu_map__dummy_new(void); struct cpu_map *cpu_map__new_data(struct cpu_map_data *data); struct cpu_map *cpu_map__read(FILE *file); size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size); +size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size); size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); int cpu_map__get_socket_id(int cpu); int cpu_map__get_socket(struct cpu_map *map, int idx, void *data); @@ -62,6 +63,7 @@ int cpu__setup_cpunode_map(void); int cpu__max_node(void); int cpu__max_cpu(void); +int cpu__max_present_cpu(void); int cpu__get_node(int cpu); int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c index d4a5a21c2a7e..4b261c2ec0f1 100644 --- a/tools/perf/util/ctype.c +++ b/tools/perf/util/ctype.c @@ -3,7 +3,7 @@ * * No surprises, and works with signed and unsigned chars. */ -#include "util.h" +#include "sane_ctype.h" enum { S = GIT_SPACE, diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 7123f4de32cc..3149b70799fd 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -7,7 +7,10 @@ * Released under the GPL v2. (and only v2, not any later version) */ +#include <errno.h> +#include <inttypes.h> #include <linux/compiler.h> +#include <linux/kernel.h> #include <babeltrace/ctf-writer/writer.h> #include <babeltrace/ctf-writer/clock.h> #include <babeltrace/ctf-writer/stream.h> @@ -27,6 +30,7 @@ #include "evsel.h" #include "machine.h" #include "config.h" +#include "sane_ctype.h" #define pr_N(n, fmt, ...) \ eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__) @@ -1440,10 +1444,8 @@ static int convert__config(const char *var, const char *value, void *cb) { struct convert *c = cb; - if (!strcmp(var, "convert.queue-size")) { - c->queue_size = perf_config_u64(var, value); - return 0; - } + if (!strcmp(var, "convert.queue-size")) + return perf_config_u64(&c->queue_size, var, value); return 0; } @@ -1468,12 +1470,13 @@ int bt_convert__perf2ctf(const char *input, const char *path, .lost = perf_event__process_lost, .tracing_data = perf_event__process_tracing_data, .build_id = perf_event__process_build_id, + .namespaces = perf_event__process_namespaces, .ordered_events = true, .ordering_requires_timestamps = true, }, }; struct ctf_writer *cw = &c.writer; - int err = -1; + int err; if (opts->all) { c.tool.comm = process_comm_event; @@ -1481,12 +1484,15 @@ int bt_convert__perf2ctf(const char *input, const char *path, c.tool.fork = process_fork_event; } - perf_config(convert__config, &c); + err = perf_config(convert__config, &c); + if (err) + return err; /* CTF writer */ if (ctf_writer__init(cw, path)) return -1; + err = -1; /* perf.data session */ session = perf_session__new(&file, 0, &c.tool); if (!session) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 60bfc9ca1e22..e84bbc8ec058 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -2,6 +2,7 @@ #include <linux/kernel.h> #include <sys/types.h> #include <sys/stat.h> +#include <errno.h> #include <unistd.h> #include <string.h> diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index c1838b643108..a5b3777ffee6 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -2,19 +2,26 @@ #include "../perf.h" +#include <inttypes.h> #include <string.h> #include <stdarg.h> #include <stdio.h> +#include <sys/wait.h> #include <api/debug.h> #include <linux/time64.h> - +#ifdef HAVE_BACKTRACE_SUPPORT +#include <execinfo.h> +#endif #include "cache.h" #include "color.h" #include "event.h" #include "debug.h" +#include "print_binary.h" #include "util.h" #include "target.h" +#include "sane_ctype.h" + int verbose; bool dump_trace = false, quiet = false; int debug_ordered_events; @@ -203,11 +210,28 @@ int perf_debug_option(const char *str) v = (v < 0) || (v > 10) ? 0 : v; } + if (quiet) + v = -1; + *var->ptr = v; free(s); return 0; } +int perf_quiet_option(void) +{ + struct debug_variable *var = &debug_variables[0]; + + /* disable all debug messages */ + while (var->name) { + *var->ptr = -1; + var++; + } + + quiet = true; + return 0; +} + #define DEBUG_WRAPPER(__n, __l) \ static int pr_ ## __n ## _wrapper(const char *fmt, ...) \ { \ @@ -227,3 +251,31 @@ void perf_debug_setup(void) { libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper); } + +/* Obtain a backtrace and print it to stdout. */ +#ifdef HAVE_BACKTRACE_SUPPORT +void dump_stack(void) +{ + void *array[16]; + size_t size = backtrace(array, ARRAY_SIZE(array)); + char **strings = backtrace_symbols(array, size); + size_t i; + + printf("Obtained %zd stack frames.\n", size); + + for (i = 0; i < size; i++) + printf("%s\n", strings[i]); + + free(strings); +} +#else +void dump_stack(void) {} +#endif + +void sighandler_dump_stack(int sig) +{ + psignal(sig, "perf"); + dump_stack(); + signal(sig, SIG_DFL); + raise(sig); +} diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index d242adc3d5a2..c818bdb1c1ab 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -4,6 +4,7 @@ #include <stdbool.h> #include <string.h> +#include <linux/compiler.h> #include "event.h" #include "../ui/helpline.h" #include "../ui/progress.h" @@ -40,19 +41,23 @@ extern int debug_data_convert; #define STRERR_BUFSIZE 128 /* For the buffer size of str_error_r */ -int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); +int dump_printf(const char *fmt, ...) __printf(1, 2); void trace_event(union perf_event *event); -int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); -int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); +int ui__error(const char *format, ...) __printf(1, 2); +int ui__warning(const char *format, ...) __printf(1, 2); void pr_stat(const char *fmt, ...); -int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4))); -int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5))); +int eprintf(int level, int var, const char *fmt, ...) __printf(3, 4); +int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5); int veprintf(int level, int var, const char *fmt, va_list args); int perf_debug_option(const char *str); void perf_debug_setup(void); +int perf_quiet_option(void); + +void dump_stack(void); +void sighandler_dump_stack(int sig); #endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c index 3e6062ab2cdd..cb66d334f532 100644 --- a/tools/perf/util/demangle-java.c +++ b/tools/perf/util/demangle-java.c @@ -7,6 +7,8 @@ #include "demangle-java.h" +#include "sane_ctype.h" + enum { MODE_PREFIX = 0, MODE_CLASS = 1, diff --git a/tools/perf/util/drv_configs.c b/tools/perf/util/drv_configs.c index 1647f285c629..eec754243f4d 100644 --- a/tools/perf/util/drv_configs.c +++ b/tools/perf/util/drv_configs.c @@ -17,6 +17,7 @@ #include "evlist.h" #include "evsel.h" #include "pmu.h" +#include <errno.h> static int perf_evsel__apply_drv_configs(struct perf_evsel *evsel, diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index d2c6cdd9d42b..4e7ab611377a 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1,14 +1,29 @@ #include <asm/bug.h> +#include <linux/kernel.h> #include <sys/time.h> #include <sys/resource.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <errno.h> +#include "compress.h" +#include "path.h" #include "symbol.h" #include "dso.h" #include "machine.h" #include "auxtrace.h" #include "util.h" #include "debug.h" +#include "string2.h" #include "vdso.h" +static const char * const debuglink_paths[] = { + "%.0s%s", + "%s/%s", + "%s/.debug/%s", + "/usr/lib/debug%s/%s" +}; + char dso__symtab_origin(const struct dso *dso) { static const char origin[] = { @@ -44,24 +59,43 @@ int dso__read_binary_type_filename(const struct dso *dso, size_t len; switch (type) { - case DSO_BINARY_TYPE__DEBUGLINK: { - char *debuglink; + case DSO_BINARY_TYPE__DEBUGLINK: + { + const char *last_slash; + char dso_dir[PATH_MAX]; + char symfile[PATH_MAX]; + unsigned int i; len = __symbol__join_symfs(filename, size, dso->long_name); - debuglink = filename + len; - while (debuglink != filename && *debuglink != '/') - debuglink--; - if (*debuglink == '/') - debuglink++; + last_slash = filename + len; + while (last_slash != filename && *last_slash != '/') + last_slash--; - ret = -1; - if (!is_regular_file(filename)) + strncpy(dso_dir, filename, last_slash - filename); + dso_dir[last_slash-filename] = '\0'; + + if (!is_regular_file(filename)) { + ret = -1; break; + } - ret = filename__read_debuglink(filename, debuglink, - size - (debuglink - filename)); + ret = filename__read_debuglink(filename, symfile, PATH_MAX); + if (ret) + break; + + /* Check predefined locations where debug file might reside */ + ret = -1; + for (i = 0; i < ARRAY_SIZE(debuglink_paths); i++) { + snprintf(filename, size, + debuglink_paths[i], dso_dir, symfile); + if (is_regular_file(filename)) { + ret = 0; + break; + } } + break; + } case DSO_BINARY_TYPE__BUILD_ID_CACHE: if (dso__build_id_filename(dso, filename, size) == NULL) ret = -1; @@ -214,6 +248,64 @@ bool dso__needs_decompress(struct dso *dso) dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; } +static int decompress_kmodule(struct dso *dso, const char *name, char *tmpbuf) +{ + int fd = -1; + struct kmod_path m; + + if (!dso__needs_decompress(dso)) + return -1; + + if (kmod_path__parse_ext(&m, dso->long_name)) + return -1; + + if (!m.comp) + goto out; + + fd = mkstemp(tmpbuf); + if (fd < 0) { + dso->load_errno = errno; + goto out; + } + + if (!decompress_to_file(m.ext, name, fd)) { + dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE; + close(fd); + fd = -1; + } + +out: + free(m.ext); + return fd; +} + +int dso__decompress_kmodule_fd(struct dso *dso, const char *name) +{ + char tmpbuf[] = KMOD_DECOMP_NAME; + int fd; + + fd = decompress_kmodule(dso, name, tmpbuf); + unlink(tmpbuf); + return fd; +} + +int dso__decompress_kmodule_path(struct dso *dso, const char *name, + char *pathname, size_t len) +{ + char tmpbuf[] = KMOD_DECOMP_NAME; + int fd; + + fd = decompress_kmodule(dso, name, tmpbuf); + if (fd < 0) { + unlink(tmpbuf); + return -1; + } + + strncpy(pathname, tmpbuf, len); + close(fd); + return 0; +} + /* * Parses kernel module specified in @path and updates * @m argument like: @@ -301,6 +393,21 @@ int __kmod_path__parse(struct kmod_path *m, const char *path, return 0; } +void dso__set_module_info(struct dso *dso, struct kmod_path *m, + struct machine *machine) +{ + if (machine__is_host(machine)) + dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; + else + dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; + + /* _KMODULE_COMP should be next to _KMODULE */ + if (m->kmod && m->comp) + dso->symtab_type++; + + dso__set_short_name(dso, strdup(m->name), true); +} + /* * Global list of open DSOs and the counter. */ @@ -347,7 +454,7 @@ static int do_open(char *name) static int __open_dso(struct dso *dso, struct machine *machine) { - int fd; + int fd = -EINVAL; char *root_dir = (char *)""; char *name = malloc(PATH_MAX); @@ -358,15 +465,30 @@ static int __open_dso(struct dso *dso, struct machine *machine) root_dir = machine->root_dir; if (dso__read_binary_type_filename(dso, dso->binary_type, - root_dir, name, PATH_MAX)) { - free(name); - return -EINVAL; - } + root_dir, name, PATH_MAX)) + goto out; if (!is_regular_file(name)) - return -EINVAL; + goto out; + + if (dso__needs_decompress(dso)) { + char newpath[KMOD_DECOMP_LEN]; + size_t len = sizeof(newpath); + + if (dso__decompress_kmodule_path(dso, name, newpath, len) < 0) { + fd = -dso->load_errno; + goto out; + } + + strcpy(name, newpath); + } fd = do_open(name); + + if (dso__needs_decompress(dso)) + unlink(name); + +out: free(name); return fd; } @@ -925,7 +1047,7 @@ static struct dso *__dso__findlink_by_longname(struct rb_root *root, if (rc == 0) { /* * In case the new DSO is a duplicate of an existing - * one, print an one-time warning & put the new entry + * one, print a one-time warning & put the new entry * at the end of the list of duplicates. */ if (!dso || (dso == this)) @@ -1032,7 +1154,7 @@ int dso__name_len(const struct dso *dso) { if (!dso) return strlen("[unknown]"); - if (verbose) + if (verbose > 0) return dso->long_name_len; return dso->short_name_len; @@ -1083,7 +1205,7 @@ struct dso *dso__new(const char *name) INIT_LIST_HEAD(&dso->node); INIT_LIST_HEAD(&dso->data.open_entry); pthread_mutex_init(&dso->lock, NULL); - atomic_set(&dso->refcnt, 1); + refcount_set(&dso->refcnt, 1); } return dso; @@ -1121,13 +1243,13 @@ void dso__delete(struct dso *dso) struct dso *dso__get(struct dso *dso) { if (dso) - atomic_inc(&dso->refcnt); + refcount_inc(&dso->refcnt); return dso; } void dso__put(struct dso *dso) { - if (dso && atomic_dec_and_test(&dso->refcnt)) + if (dso && refcount_dec_and_test(&dso->refcnt)) dso__delete(dso); } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index ecc4bbd3f82e..bd061ba7b47c 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -1,7 +1,7 @@ #ifndef __PERF_DSO #define __PERF_DSO -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/types.h> #include <linux/rbtree.h> #include <sys/types.h> @@ -187,7 +187,7 @@ struct dso { void *priv; u64 db_id; }; - atomic_t refcnt; + refcount_t refcnt; char name[0]; }; @@ -244,6 +244,12 @@ bool is_supported_compression(const char *ext); bool is_kernel_module(const char *pathname, int cpumode); bool decompress_to_file(const char *ext, const char *filename, int output_fd); bool dso__needs_decompress(struct dso *dso); +int dso__decompress_kmodule_fd(struct dso *dso, const char *name); +int dso__decompress_kmodule_path(struct dso *dso, const char *name, + char *pathname, size_t len); + +#define KMOD_DECOMP_NAME "/tmp/perf-kmod-XXXXXX" +#define KMOD_DECOMP_LEN sizeof(KMOD_DECOMP_NAME) struct kmod_path { char *name; @@ -259,6 +265,9 @@ int __kmod_path__parse(struct kmod_path *m, const char *path, #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) #define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) +void dso__set_module_info(struct dso *dso, struct kmod_path *m, + struct machine *machine); + /* * The dso__data_* external interface provides following functions: * dso__data_get_fd diff --git a/tools/perf/util/dump-insn.c b/tools/perf/util/dump-insn.c new file mode 100644 index 000000000000..ffbdb19f05d0 --- /dev/null +++ b/tools/perf/util/dump-insn.c @@ -0,0 +1,14 @@ +#include <linux/compiler.h> +#include "dump-insn.h" + +/* Fallback code */ + +__weak +const char *dump_insn(struct perf_insn *x __maybe_unused, + u64 ip __maybe_unused, u8 *inbuf __maybe_unused, + int inlen __maybe_unused, int *lenp) +{ + if (lenp) + *lenp = 0; + return "?"; +} diff --git a/tools/perf/util/dump-insn.h b/tools/perf/util/dump-insn.h new file mode 100644 index 000000000000..90fb115981cf --- /dev/null +++ b/tools/perf/util/dump-insn.h @@ -0,0 +1,22 @@ +#ifndef __PERF_DUMP_INSN_H +#define __PERF_DUMP_INSN_H 1 + +#define MAXINSN 15 + +#include <linux/types.h> + +struct thread; + +struct perf_insn { + /* Initialized by callers: */ + struct thread *thread; + u8 cpumode; + bool is64bit; + int cpu; + /* Temporary */ + char out[256]; +}; + +const char *dump_insn(struct perf_insn *x, u64 ip, + u8 *inbuf, int inlen, int *lenp); +#endif diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 41e068e94349..f5acda13dcfa 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -17,10 +17,13 @@ * */ +#include <errno.h> +#include <inttypes.h> #include <stdbool.h> #include "util.h" #include "debug.h" #include "dwarf-aux.h" +#include "string2.h" /** * cu_find_realpath - Find the realpath of the target file diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c index 62bc4a86a970..c708395b3cb6 100644 --- a/tools/perf/util/dwarf-regs.c +++ b/tools/perf/util/dwarf-regs.c @@ -8,6 +8,7 @@ #include <debug.h> #include <dwarf-regs.h> #include <elf.h> +#include <linux/kernel.h> #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index bb964e86b09d..9e21538c42ae 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -1,6 +1,7 @@ #include "cpumap.h" #include "env.h" #include "util.h" +#include <errno.h> struct perf_env perf_env; @@ -66,7 +67,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env) return 0; if (env->nr_cpus_avail == 0) - env->nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF); + env->nr_cpus_avail = cpu__max_present_cpu(); nr_cpus = env->nr_cpus_avail; if (nr_cpus == -1) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 8ab0d7da956b..dc5c3bb69d73 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,15 +1,24 @@ +#include <dirent.h> +#include <errno.h> +#include <inttypes.h> +#include <linux/kernel.h> #include <linux/types.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ #include <api/fs/fs.h> +#include <linux/perf_event.h> #include "event.h" #include "debug.h" #include "hist.h" #include "machine.h" #include "sort.h" -#include "string.h" +#include "string2.h" #include "strlist.h" #include "thread.h" #include "thread_map.h" +#include "sane_ctype.h" #include "symbol/kallsyms.h" #include "asm/bug.h" #include "stat.h" @@ -31,6 +40,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_LOST_SAMPLES] = "LOST_SAMPLES", [PERF_RECORD_SWITCH] = "SWITCH", [PERF_RECORD_SWITCH_CPU_WIDE] = "SWITCH_CPU_WIDE", + [PERF_RECORD_NAMESPACES] = "NAMESPACES", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", @@ -49,6 +59,16 @@ static const char *perf_event__names[] = { [PERF_RECORD_TIME_CONV] = "TIME_CONV", }; +static const char *perf_ns__names[] = { + [NET_NS_INDEX] = "net", + [UTS_NS_INDEX] = "uts", + [IPC_NS_INDEX] = "ipc", + [PID_NS_INDEX] = "pid", + [USER_NS_INDEX] = "user", + [MNT_NS_INDEX] = "mnt", + [CGROUP_NS_INDEX] = "cgroup", +}; + const char *perf_event__name(unsigned int id) { if (id >= ARRAY_SIZE(perf_event__names)) @@ -58,6 +78,13 @@ const char *perf_event__name(unsigned int id) return perf_event__names[id]; } +static const char *perf_ns__name(unsigned int id) +{ + if (id >= ARRAY_SIZE(perf_ns__names)) + return "UNKNOWN"; + return perf_ns__names[id]; +} + static int perf_tool__process_synth_event(struct perf_tool *tool, union perf_event *event, struct machine *machine, @@ -88,7 +115,7 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len, int fd; size_t size = 0; ssize_t n; - char *nl, *name, *tgids, *ppids; + char *name, *tgids, *ppids; *tgid = -1; *ppid = -1; @@ -115,10 +142,10 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len, ppids = strstr(bf, "PPid:"); if (name) { - name += 5; /* strlen("Name:") */ + char *nl; - while (*name && isspace(*name)) - ++name; + name += 5; /* strlen("Name:") */ + name = ltrim(name); nl = strchr(name, '\n'); if (nl) @@ -203,6 +230,58 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool, return tgid; } +static void perf_event__get_ns_link_info(pid_t pid, const char *ns, + struct perf_ns_link_info *ns_link_info) +{ + struct stat64 st; + char proc_ns[128]; + + sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns); + if (stat64(proc_ns, &st) == 0) { + ns_link_info->dev = st.st_dev; + ns_link_info->ino = st.st_ino; + } +} + +int perf_event__synthesize_namespaces(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct machine *machine) +{ + u32 idx; + struct perf_ns_link_info *ns_link_info; + + if (!tool || !tool->namespace_events) + return 0; + + memset(&event->namespaces, 0, (sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size)); + + event->namespaces.pid = tgid; + event->namespaces.tid = pid; + + event->namespaces.nr_namespaces = NR_NAMESPACES; + + ns_link_info = event->namespaces.link_info; + + for (idx = 0; idx < event->namespaces.nr_namespaces; idx++) + perf_event__get_ns_link_info(pid, perf_ns__name(idx), + &ns_link_info[idx]); + + event->namespaces.header.type = PERF_RECORD_NAMESPACES; + + event->namespaces.header.size = (sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) + return -1; + + return 0; +} + static int perf_event__synthesize_fork(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, pid_t ppid, @@ -255,8 +334,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, if (machine__is_default_guest(machine)) return 0; - snprintf(filename, sizeof(filename), "%s/proc/%d/maps", - machine->root_dir, pid); + snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps", + machine->root_dir, pid, pid); fp = fopen(filename, "r"); if (fp == NULL) { @@ -434,8 +513,9 @@ int perf_event__synthesize_modules(struct perf_tool *tool, static int __event__synthesize_thread(union perf_event *comm_event, union perf_event *mmap_event, union perf_event *fork_event, + union perf_event *namespaces_event, pid_t pid, int full, - perf_event__handler_t process, + perf_event__handler_t process, struct perf_tool *tool, struct machine *machine, bool mmap_data, @@ -455,6 +535,11 @@ static int __event__synthesize_thread(union perf_event *comm_event, if (tgid == -1) return -1; + if (perf_event__synthesize_namespaces(tool, namespaces_event, pid, + tgid, process, machine) < 0) + return -1; + + return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data, proc_map_timeout); @@ -488,6 +573,11 @@ static int __event__synthesize_thread(union perf_event *comm_event, if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, ppid, process, machine) < 0) break; + + if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid, + tgid, process, machine) < 0) + break; + /* * Send the prepared comm event */ @@ -516,6 +606,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, unsigned int proc_map_timeout) { union perf_event *comm_event, *mmap_event, *fork_event; + union perf_event *namespaces_event; int err = -1, thread, j; comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); @@ -530,10 +621,16 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, if (fork_event == NULL) goto out_free_mmap; + namespaces_event = malloc(sizeof(namespaces_event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (namespaces_event == NULL) + goto out_free_fork; + err = 0; for (thread = 0; thread < threads->nr; ++thread) { if (__event__synthesize_thread(comm_event, mmap_event, - fork_event, + fork_event, namespaces_event, thread_map__pid(threads, thread), 0, process, tool, machine, mmap_data, proc_map_timeout)) { @@ -559,7 +656,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, /* if not, generate events for it */ if (need_leader && __event__synthesize_thread(comm_event, mmap_event, - fork_event, + fork_event, namespaces_event, comm_event->comm.pid, 0, process, tool, machine, mmap_data, proc_map_timeout)) { @@ -568,6 +665,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, } } } + free(namespaces_event); +out_free_fork: free(fork_event); out_free_mmap: free(mmap_event); @@ -587,6 +686,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, char proc_path[PATH_MAX]; struct dirent *dirent; union perf_event *comm_event, *mmap_event, *fork_event; + union perf_event *namespaces_event; int err = -1; if (machine__is_default_guest(machine)) @@ -604,11 +704,17 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (fork_event == NULL) goto out_free_mmap; + namespaces_event = malloc(sizeof(namespaces_event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (namespaces_event == NULL) + goto out_free_fork; + snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); proc = opendir(proc_path); if (proc == NULL) - goto out_free_fork; + goto out_free_namespaces; while ((dirent = readdir(proc)) != NULL) { char *end; @@ -620,13 +726,16 @@ int perf_event__synthesize_threads(struct perf_tool *tool, * We may race with exiting thread, so don't stop just because * one thread couldn't be synthesized. */ - __event__synthesize_thread(comm_event, mmap_event, fork_event, pid, - 1, process, tool, machine, mmap_data, + __event__synthesize_thread(comm_event, mmap_event, fork_event, + namespaces_event, pid, 1, process, + tool, machine, mmap_data, proc_map_timeout); } err = 0; closedir(proc); +out_free_namespaces: + free(namespaces_event); out_free_fork: free(fork_event); out_free_mmap: @@ -659,15 +768,16 @@ static int find_symbol_cb(void *arg, const char *name, char type, return 1; } -u64 kallsyms__get_function_start(const char *kallsyms_filename, - const char *symbol_name) +int kallsyms__get_function_start(const char *kallsyms_filename, + const char *symbol_name, u64 *addr) { struct process_symbol_args args = { .name = symbol_name, }; if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0) - return 0; + return -1; - return args.start; + *addr = args.start; + return 0; } int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, @@ -1008,6 +1118,33 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid); } +size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp) +{ + size_t ret = 0; + struct perf_ns_link_info *ns_link_info; + u32 nr_namespaces, idx; + + ns_link_info = event->namespaces.link_info; + nr_namespaces = event->namespaces.nr_namespaces; + + ret += fprintf(fp, " %d/%d - nr_namespaces: %u\n\t\t[", + event->namespaces.pid, + event->namespaces.tid, + nr_namespaces); + + for (idx = 0; idx < nr_namespaces; idx++) { + if (idx && (idx % 4 == 0)) + ret += fprintf(fp, "\n\t\t "); + + ret += fprintf(fp, "%u/%s: %" PRIu64 "/%#" PRIx64 "%s", idx, + perf_ns__name(idx), (u64)ns_link_info[idx].dev, + (u64)ns_link_info[idx].ino, + ((idx + 1) != nr_namespaces) ? ", " : "]\n"); + } + + return ret; +} + int perf_event__process_comm(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -1016,6 +1153,14 @@ int perf_event__process_comm(struct perf_tool *tool __maybe_unused, return machine__process_comm_event(machine, event, sample); } +int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + return machine__process_namespaces_event(machine, event, sample); +} + int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -1153,11 +1298,12 @@ int perf_event__process_exit(struct perf_tool *tool __maybe_unused, size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp) { - return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n", + return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s%s]\n", event->aux.aux_offset, event->aux.aux_size, event->aux.flags, event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "", - event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : ""); + event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "", + event->aux.flags & PERF_AUX_FLAG_PARTIAL ? "P" : ""); } size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp) @@ -1196,6 +1342,9 @@ 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_NAMESPACES: + ret += perf_event__fprintf_namespaces(event, fp); + break; case PERF_RECORD_MMAP2: ret += perf_event__fprintf_mmap2(event, fp); break; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index c735c53a26f8..9967c87af7a6 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -3,9 +3,9 @@ #include <limits.h> #include <stdio.h> +#include <linux/kernel.h> #include "../perf.h" -#include "map.h" #include "build-id.h" #include "perf_regs.h" @@ -39,6 +39,13 @@ struct comm_event { char comm[16]; }; +struct namespaces_event { + struct perf_event_header header; + u32 pid, tid; + u64 nr_namespaces; + struct perf_ns_link_info link_info[]; +}; + struct fork_event { struct perf_event_header header; u32 pid, ppid; @@ -222,7 +229,7 @@ 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, /* depreceated */ + PERF_RECORD_HEADER_EVENT_TYPE = 65, /* deprecated */ PERF_RECORD_HEADER_TRACING_DATA = 66, PERF_RECORD_HEADER_BUILD_ID = 67, PERF_RECORD_FINISHED_ROUND = 68, @@ -245,6 +252,127 @@ enum auxtrace_error_type { PERF_AUXTRACE_ERROR_MAX }; +/* Attribute type for custom synthesized events */ +#define PERF_TYPE_SYNTH (INT_MAX + 1U) + +/* Attribute config for custom synthesized events */ +enum perf_synth_id { + PERF_SYNTH_INTEL_PTWRITE, + PERF_SYNTH_INTEL_MWAIT, + PERF_SYNTH_INTEL_PWRE, + PERF_SYNTH_INTEL_EXSTOP, + PERF_SYNTH_INTEL_PWRX, + PERF_SYNTH_INTEL_CBR, +}; + +/* + * Raw data formats for synthesized events. Note that 4 bytes of padding are + * present to match the 'size' member of PERF_SAMPLE_RAW data which is always + * 8-byte aligned. That means we must dereference raw_data with an offset of 4. + * Refer perf_sample__synth_ptr() and perf_synth__raw_data(). It also means the + * structure sizes are 4 bytes bigger than the raw_size, refer + * perf_synth__raw_size(). + */ + +struct perf_synth_intel_ptwrite { + u32 padding; + union { + struct { + u32 ip : 1, + reserved : 31; + }; + u32 flags; + }; + u64 payload; +}; + +struct perf_synth_intel_mwait { + u32 padding; + u32 reserved; + union { + struct { + u64 hints : 8, + reserved1 : 24, + extensions : 2, + reserved2 : 30; + }; + u64 payload; + }; +}; + +struct perf_synth_intel_pwre { + u32 padding; + u32 reserved; + union { + struct { + u64 reserved1 : 7, + hw : 1, + subcstate : 4, + cstate : 4, + reserved2 : 48; + }; + u64 payload; + }; +}; + +struct perf_synth_intel_exstop { + u32 padding; + union { + struct { + u32 ip : 1, + reserved : 31; + }; + u32 flags; + }; +}; + +struct perf_synth_intel_pwrx { + u32 padding; + u32 reserved; + union { + struct { + u64 deepest_cstate : 4, + last_cstate : 4, + wake_reason : 4, + reserved1 : 52; + }; + u64 payload; + }; +}; + +struct perf_synth_intel_cbr { + u32 padding; + union { + struct { + u32 cbr : 8, + reserved1 : 8, + max_nonturbo : 8, + reserved2 : 8; + }; + u32 flags; + }; + u32 freq; + u32 reserved3; +}; + +/* + * raw_data is always 4 bytes from an 8-byte boundary, so subtract 4 to get + * 8-byte alignment. + */ +static inline void *perf_sample__synth_ptr(struct perf_sample *sample) +{ + return sample->raw_data - 4; +} + +static inline void *perf_synth__raw_data(void *p) +{ + return p + 4; +} + +#define perf_synth__raw_size(d) (sizeof(d) - 4) + +#define perf_sample__bad_synth_size(s, d) ((s)->raw_size < sizeof(d) - 4) + /* * The kernel collects the number of events it couldn't send in a stretch and * when possible sends this number in a PERF_RECORD_LOST event. The number of @@ -269,6 +397,7 @@ struct events_stats { u64 total_lost; u64 total_lost_samples; u64 total_aux_lost; + u64 total_aux_partial; u64 total_invalid_chains; u32 nr_events[PERF_RECORD_HEADER_MAX]; u32 nr_non_filtered_samples; @@ -485,6 +614,7 @@ union perf_event { struct mmap_event mmap; struct mmap2_event mmap2; struct comm_event comm; + struct namespaces_event namespaces; struct fork_event fork; struct lost_event lost; struct lost_samples_event lost_samples; @@ -587,6 +717,10 @@ int perf_event__process_switch(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_namespaces(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -636,6 +770,12 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_namespaces(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct machine *machine); + int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, @@ -653,12 +793,21 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp); size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp); size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp); size_t perf_event__fprintf(union perf_event *event, FILE *fp); -u64 kallsyms__get_function_start(const char *kallsyms_filename, - const char *symbol_name); +int kallsyms__get_function_start(const char *kallsyms_filename, + const char *symbol_name, u64 *addr); void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max); void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map, u16 type, int max); + +void event_attr_init(struct perf_event_attr *attr); + +int perf_event_paranoid(void); + +extern int sysctl_perf_event_max_stack; +extern int sysctl_perf_event_max_contexts_per_stack; + #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index d92e02006fb8..46c0faf6c502 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -8,6 +8,8 @@ */ #include "util.h" #include <api/fs/fs.h> +#include <errno.h> +#include <inttypes.h> #include <poll.h> #include "cpumap.h" #include "thread_map.h" @@ -15,12 +17,15 @@ #include "evlist.h" #include "evsel.h" #include "debug.h" +#include "units.h" #include "asm/bug.h" +#include <signal.h> #include <unistd.h> #include "parse-events.h" #include <subcmd/parse-options.h> +#include <sys/ioctl.h> #include <sys/mman.h> #include <linux/bitops.h> @@ -777,7 +782,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messu /* * Check if event was unmapped due to a POLLHUP/POLLERR. */ - if (!atomic_read(&md->refcnt)) + if (!refcount_read(&md->refcnt)) return NULL; head = perf_mmap__read_head(md); @@ -794,7 +799,7 @@ perf_mmap__read_backward(struct perf_mmap *md) /* * Check if event was unmapped due to a POLLHUP/POLLERR. */ - if (!atomic_read(&md->refcnt)) + if (!refcount_read(&md->refcnt)) return NULL; head = perf_mmap__read_head(md); @@ -856,7 +861,7 @@ void perf_mmap__read_catchup(struct perf_mmap *md) { u64 head; - if (!atomic_read(&md->refcnt)) + if (!refcount_read(&md->refcnt)) return; head = perf_mmap__read_head(md); @@ -875,14 +880,14 @@ static bool perf_mmap__empty(struct perf_mmap *md) static void perf_mmap__get(struct perf_mmap *map) { - atomic_inc(&map->refcnt); + refcount_inc(&map->refcnt); } static void perf_mmap__put(struct perf_mmap *md) { - BUG_ON(md->base && atomic_read(&md->refcnt) == 0); + BUG_ON(md->base && refcount_read(&md->refcnt) == 0); - if (atomic_dec_and_test(&md->refcnt)) + if (refcount_dec_and_test(&md->refcnt)) perf_mmap__munmap(md); } @@ -894,7 +899,7 @@ void perf_mmap__consume(struct perf_mmap *md, bool overwrite) perf_mmap__write_tail(md, old); } - if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md)) + if (refcount_read(&md->refcnt) == 1 && perf_mmap__empty(md)) perf_mmap__put(md); } @@ -937,7 +942,7 @@ static void perf_mmap__munmap(struct perf_mmap *map) munmap(map->base, perf_mmap__mmap_len(map)); map->base = NULL; map->fd = -1; - atomic_set(&map->refcnt, 0); + refcount_set(&map->refcnt, 0); } auxtrace_mmap__munmap(&map->auxtrace_mmap); } @@ -974,8 +979,19 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist) if (!map) return NULL; - for (i = 0; i < evlist->nr_mmaps; i++) + for (i = 0; i < evlist->nr_mmaps; i++) { map[i].fd = -1; + /* + * When the perf_mmap() call is made we grab one refcount, plus + * one extra to let perf_evlist__mmap_consume() get the last + * events after all real references (perf_mmap__get()) are + * dropped. + * + * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and + * thus does perf_mmap__get() on it. + */ + refcount_set(&map[i].refcnt, 0); + } return map; } @@ -1001,7 +1017,7 @@ static int perf_mmap__mmap(struct perf_mmap *map, * evlist layer can't just drop it when filtering events in * perf_evlist__filter_pollfd(). */ - atomic_set(&map->refcnt, 2); + refcount_set(&map->refcnt, 2); map->prev = 0; map->mask = mp->mask; map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot, @@ -1184,7 +1200,7 @@ unsigned long perf_event_mlock_kb_in_pages(void) return pages; } -static size_t perf_evlist__mmap_size(unsigned long pages) +size_t perf_evlist__mmap_size(unsigned long pages) { if (pages == UINT_MAX) pages = perf_event_mlock_kb_in_pages(); @@ -1224,12 +1240,16 @@ static long parse_pages_arg(const char *str, unsigned long min, if (pages == 0 && min == 0) { /* leave number of pages at 0 */ } else if (!is_power_of_2(pages)) { + char buf[100]; + /* round pages up to next power of 2 */ pages = roundup_pow_of_two(pages); if (!pages) return -EINVAL; - pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n", - pages * page_size, pages); + + unit_number__scnprintf(buf, sizeof(buf), pages * page_size); + pr_info("rounding mmap pages size to %s (%lu pages)\n", + buf, pages); } if (pages > max) @@ -1797,7 +1817,7 @@ int perf_evlist__start_workload(struct perf_evlist *evlist) */ ret = write(evlist->workload.cork_fd, &bf, 1); if (ret < 0) - perror("enable to write to pipe"); + perror("unable to write to pipe"); close(evlist->workload.cork_fd); return ret; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 4fd034f22d2f..8d601fbdd8d6 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -1,7 +1,9 @@ #ifndef __PERF_EVLIST_H #define __PERF_EVLIST_H 1 -#include <linux/atomic.h> +#include <linux/compiler.h> +#include <linux/kernel.h> +#include <linux/refcount.h> #include <linux/list.h> #include <api/fd/array.h> #include <stdio.h> @@ -10,6 +12,7 @@ #include "evsel.h" #include "util.h" #include "auxtrace.h" +#include <signal.h> #include <unistd.h> struct pollfd; @@ -29,10 +32,10 @@ struct perf_mmap { void *base; int mask; int fd; - atomic_t refcnt; + refcount_t refcnt; u64 prev; struct auxtrace_mmap auxtrace_mmap; - char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8))); + char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8); }; static inline size_t @@ -218,6 +221,8 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, bool overwrite); void perf_evlist__munmap(struct perf_evlist *evlist); +size_t perf_evlist__mmap_size(unsigned long pages); + void perf_evlist__disable(struct perf_evlist *evlist); void perf_evlist__enable(struct perf_evlist *evlist); void perf_evlist__toggle_enable(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 04e536ae4d88..413f74df08de 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -8,16 +8,24 @@ */ #include <byteswap.h> +#include <errno.h> +#include <inttypes.h> #include <linux/bitops.h> +#include <api/fs/fs.h> #include <api/fs/tracing_path.h> #include <traceevent/event-parse.h> #include <linux/hw_breakpoint.h> #include <linux/perf_event.h> +#include <linux/compiler.h> #include <linux/err.h> +#include <sys/ioctl.h> #include <sys/resource.h> +#include <sys/types.h> +#include <dirent.h> #include "asm/bug.h" #include "callchain.h" #include "cgroup.h" +#include "event.h" #include "evsel.h" #include "evlist.h" #include "util.h" @@ -30,6 +38,8 @@ #include "stat.h" #include "util/parse-branch-options.h" +#include "sane_ctype.h" + static struct { bool sample_id_all; bool exclude_guest; @@ -236,6 +246,10 @@ void perf_evsel__init(struct perf_evsel *evsel, evsel->sample_size = __perf_evsel__sample_size(attr->sample_type); perf_evsel__calc_id_pos(evsel); evsel->cmdline_group_boundary = false; + evsel->metric_expr = NULL; + evsel->metric_name = NULL; + evsel->metric_events = NULL; + evsel->collect_stat = false; } struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -259,20 +273,35 @@ struct perf_evsel *perf_evsel__new_cycles(void) struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, + .exclude_kernel = geteuid() != 0, }; struct perf_evsel *evsel; event_attr_init(&attr); + /* + * Unnamed union member, not supported as struct member named + * initializer in older compilers such as gcc 4.4.7 + * + * Just for probing the precise_ip: + */ + attr.sample_period = 1; perf_event_attr__set_max_precise_ip(&attr); + /* + * Now let the usual logic to set up the perf_event_attr defaults + * to kick in when we return and before perf_evsel__open() is called. + */ + attr.sample_period = 0; evsel = perf_evsel__new(&attr); if (evsel == NULL) goto out; /* use asprintf() because free(evsel) assumes name is allocated */ - if (asprintf(&evsel->name, "cycles%.*s", - attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0) + if (asprintf(&evsel->name, "cycles%s%s%.*s", + (attr.precise_ip || attr.exclude_kernel) ? ":" : "", + attr.exclude_kernel ? "u" : "", + attr.precise_ip ? attr.precise_ip + 1 : 0, "ppp") < 0) goto error_free; out: return evsel; @@ -932,6 +961,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; + if (opts->record_namespaces) + attr->namespaces = track; + if (opts->record_switch_events) attr->context_switch = track; @@ -1232,7 +1264,7 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, if (FD(evsel, cpu, thread) < 0) return -EINVAL; - if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) < 0) + if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) <= 0) return -errno; return 0; @@ -1250,7 +1282,7 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0) return -ENOMEM; - if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0) + if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0) return -errno; perf_evsel__compute_deltas(evsel, cpu, thread, &count); @@ -1416,7 +1448,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, } static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, - void *priv __attribute__((unused))) + void *priv __maybe_unused) { return fprintf(fp, " %-32s %s\n", name, val); } @@ -1448,8 +1480,8 @@ static bool ignore_missing_thread(struct perf_evsel *evsel, return true; } -static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads) +int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, + struct thread_map *threads) { int cpu, thread, nthreads; unsigned long flags = PERF_FLAG_FD_CLOEXEC; @@ -1459,6 +1491,30 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, if (perf_missing_features.write_backward && evsel->attr.write_backward) return -EINVAL; + if (cpus == NULL) { + static struct cpu_map *empty_cpu_map; + + if (empty_cpu_map == NULL) { + empty_cpu_map = cpu_map__dummy_new(); + if (empty_cpu_map == NULL) + return -ENOMEM; + } + + cpus = empty_cpu_map; + } + + if (threads == NULL) { + static struct thread_map *empty_thread_map; + + if (empty_thread_map == NULL) { + empty_thread_map = thread_map__new_by_tid(-1); + if (empty_thread_map == NULL) + return -ENOMEM; + } + + threads = empty_thread_map; + } + if (evsel->system_wide) nthreads = 1; else @@ -1655,46 +1711,16 @@ void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads) perf_evsel__free_fd(evsel); } -static struct { - struct cpu_map map; - int cpus[1]; -} empty_cpu_map = { - .map.nr = 1, - .cpus = { -1, }, -}; - -static struct { - struct thread_map map; - int threads[1]; -} empty_thread_map = { - .map.nr = 1, - .threads = { -1, }, -}; - -int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads) -{ - if (cpus == NULL) { - /* Work around old compiler warnings about strict aliasing */ - cpus = &empty_cpu_map.map; - } - - if (threads == NULL) - threads = &empty_thread_map.map; - - return __perf_evsel__open(evsel, cpus, threads); -} - int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus) { - return __perf_evsel__open(evsel, cpus, &empty_thread_map.map); + return perf_evsel__open(evsel, cpus, NULL); } int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads) { - return __perf_evsel__open(evsel, &empty_cpu_map.map, threads); + return perf_evsel__open(evsel, NULL, threads); } static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel, @@ -2452,15 +2478,57 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, return false; } +static bool find_process(const char *name) +{ + size_t len = strlen(name); + DIR *dir; + struct dirent *d; + int ret = -1; + + dir = opendir(procfs__mountpoint()); + if (!dir) + return false; + + /* Walk through the directory. */ + while (ret && (d = readdir(dir)) != NULL) { + char path[PATH_MAX]; + char *data; + size_t size; + + if ((d->d_type != DT_DIR) || + !strcmp(".", d->d_name) || + !strcmp("..", d->d_name)) + continue; + + scnprintf(path, sizeof(path), "%s/%s/comm", + procfs__mountpoint(), d->d_name); + + if (filename__read_str(path, &data, &size)) + continue; + + ret = strncmp(name, data, len); + free(data); + } + + closedir(dir); + return ret ? false : true; +} + int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, int err, char *msg, size_t size) { char sbuf[STRERR_BUFSIZE]; + int printed = 0; switch (err) { case EPERM: case EACCES: - return scnprintf(msg, size, + if (err == EPERM) + printed = scnprintf(msg, size, + "No permission to enable %s event.\n\n", + perf_evsel__name(evsel)); + + return scnprintf(msg + printed, size - printed, "You may not have permission to collect %sstats.\n\n" "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n" "which controls use of the performance events system by\n" @@ -2469,7 +2537,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, " -1: Allow use of (almost) all events by all users\n" ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n" ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" - ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN", + ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n" + "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n" + " kernel.perf_event_paranoid = -1\n" , target->system_wide ? "system-wide " : "", perf_event_paranoid()); case ENOENT: diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 06ef6f29efa1..d101695c482c 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -131,6 +131,11 @@ struct perf_evsel { bool cmdline_group_boundary; struct list_head config_terms; int bpf_fd; + bool merged_stat; + const char * metric_expr; + const char * metric_name; + struct perf_evsel **metric_events; + bool collect_stat; }; union u64_swap { diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 6b2925542c0a..583f3a602506 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -1,10 +1,13 @@ +#include <inttypes.h> #include <stdio.h> #include <stdbool.h> #include <traceevent/event-parse.h> #include "evsel.h" #include "callchain.h" #include "map.h" +#include "strlist.h" #include "symbol.h" +#include "srcline.h" static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) { @@ -166,9 +169,40 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (!print_oneline) printed += fprintf(fp, "\n"); + if (symbol_conf.inline_name && node->map) { + struct inline_node *inode; + + addr = map__rip_2objdump(node->map, node->ip), + inode = dso__parse_addr_inlines(node->map->dso, addr); + + if (inode) { + struct inline_list *ilist; + + list_for_each_entry(ilist, &inode->val, list) { + if (print_arrow) + printed += fprintf(fp, " <-"); + + /* IP is same, just skip it */ + if (print_ip) + printed += fprintf(fp, "%c%16s", + s, ""); + if (print_sym) + printed += fprintf(fp, " %s", + ilist->funcname); + if (print_srcline) + printed += fprintf(fp, "\n %s:%d", + ilist->filename, + ilist->line_nr); + if (!print_oneline) + printed += fprintf(fp, "\n"); + } + + inline_node__delete(inode); + } + } + if (symbol_conf.bt_stop_list && node->sym && - node->sym->name && strlist__has_entry(symbol_conf.bt_stop_list, node->sym->name)) { break; diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h new file mode 100644 index 000000000000..9c2760a1a96e --- /dev/null +++ b/tools/perf/util/expr.h @@ -0,0 +1,25 @@ +#ifndef PARSE_CTX_H +#define PARSE_CTX_H 1 + +#define EXPR_MAX_OTHER 8 +#define MAX_PARSE_ID EXPR_MAX_OTHER + +struct parse_id { + const char *name; + double val; +}; + +struct parse_ctx { + int num_ids; + struct parse_id ids[MAX_PARSE_ID]; +}; + +void expr__ctx_init(struct parse_ctx *ctx); +void expr__add_id(struct parse_ctx *ctx, const char *id, double val); +#ifndef IN_EXPR_Y +int expr__parse(double *final_val, struct parse_ctx *ctx, const char **pp); +#endif +int expr__find_other(const char *p, const char *one, const char ***other, + int *num_other); + +#endif diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y new file mode 100644 index 000000000000..954556bea36e --- /dev/null +++ b/tools/perf/util/expr.y @@ -0,0 +1,173 @@ +/* Simple expression parser */ +%{ +#include "util.h" +#include "util/debug.h" +#define IN_EXPR_Y 1 +#include "expr.h" +#include <string.h> + +#define MAXIDLEN 256 +%} + +%pure-parser +%parse-param { double *final_val } +%parse-param { struct parse_ctx *ctx } +%parse-param { const char **pp } +%lex-param { const char **pp } + +%union { + double num; + char id[MAXIDLEN+1]; +} + +%token <num> NUMBER +%token <id> ID +%left '|' +%left '^' +%left '&' +%left '-' '+' +%left '*' '/' '%' +%left NEG NOT +%type <num> expr + +%{ +static int expr__lex(YYSTYPE *res, const char **pp); + +static void expr__error(double *final_val __maybe_unused, + struct parse_ctx *ctx __maybe_unused, + const char **pp __maybe_unused, + const char *s) +{ + pr_debug("%s\n", s); +} + +static int lookup_id(struct parse_ctx *ctx, char *id, double *val) +{ + int i; + + for (i = 0; i < ctx->num_ids; i++) { + if (!strcasecmp(ctx->ids[i].name, id)) { + *val = ctx->ids[i].val; + return 0; + } + } + return -1; +} + +%} +%% + +all_expr: expr { *final_val = $1; } + ; + +expr: NUMBER + | ID { if (lookup_id(ctx, $1, &$$) < 0) { + pr_debug("%s not found", $1); + YYABORT; + } + } + | expr '+' expr { $$ = $1 + $3; } + | expr '-' expr { $$ = $1 - $3; } + | expr '*' expr { $$ = $1 * $3; } + | expr '/' expr { if ($3 == 0) YYABORT; $$ = $1 / $3; } + | expr '%' expr { if ((long)$3 == 0) YYABORT; $$ = (long)$1 % (long)$3; } + | '-' expr %prec NEG { $$ = -$2; } + | '(' expr ')' { $$ = $2; } + ; + +%% + +static int expr__symbol(YYSTYPE *res, const char *p, const char **pp) +{ + char *dst = res->id; + const char *s = p; + + while (isalnum(*p) || *p == '_' || *p == '.') { + if (p - s >= MAXIDLEN) + return -1; + *dst++ = *p++; + } + *dst = 0; + *pp = p; + return ID; +} + +static int expr__lex(YYSTYPE *res, const char **pp) +{ + int tok; + const char *s; + const char *p = *pp; + + while (isspace(*p)) + p++; + s = p; + switch (*p++) { + case 'a' ... 'z': + case 'A' ... 'Z': + return expr__symbol(res, p - 1, pp); + case '0' ... '9': case '.': + res->num = strtod(s, (char **)&p); + tok = NUMBER; + break; + default: + tok = *s; + break; + } + *pp = p; + return tok; +} + +/* Caller must make sure id is allocated */ +void expr__add_id(struct parse_ctx *ctx, const char *name, double val) +{ + int idx; + assert(ctx->num_ids < MAX_PARSE_ID); + idx = ctx->num_ids++; + ctx->ids[idx].name = name; + ctx->ids[idx].val = val; +} + +void expr__ctx_init(struct parse_ctx *ctx) +{ + ctx->num_ids = 0; +} + +int expr__find_other(const char *p, const char *one, const char ***other, + int *num_otherp) +{ + const char *orig = p; + int err = -1; + int num_other; + + *other = malloc((EXPR_MAX_OTHER + 1) * sizeof(char *)); + if (!*other) + return -1; + + num_other = 0; + for (;;) { + YYSTYPE val; + int tok = expr__lex(&val, &p); + if (tok == 0) { + err = 0; + break; + } + if (tok == ID && strcasecmp(one, val.id)) { + if (num_other >= EXPR_MAX_OTHER - 1) { + pr_debug("Too many extra events in %s\n", orig); + break; + } + (*other)[num_other] = strdup(val.id); + if (!(*other)[num_other]) + return -1; + num_other++; + } + } + (*other)[num_other] = NULL; + *num_otherp = num_other; + if (err) { + *num_otherp = 0; + free(*other); + *other = NULL; + } + return err; +} diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c index 5980f7d256b1..40789d8603d0 100644 --- a/tools/perf/util/genelf_debug.c +++ b/tools/perf/util/genelf_debug.c @@ -11,6 +11,7 @@ * @remark Copyright 2007 OProfile authors * @author Philippe Elie */ +#include <linux/compiler.h> #include <sys/types.h> #include <stdio.h> #include <getopt.h> @@ -125,7 +126,7 @@ struct debug_line_header { * and filesize, last entry is followed by en empty string. */ /* follow the first program statement */ -} __attribute__((packed)); +} __packed; /* DWARF 2 spec talk only about one possible compilation unit header while * binutils can handle two flavours of dwarf 2, 32 and 64 bits, this is not @@ -138,7 +139,7 @@ struct compilation_unit_header { uhalf version; uword debug_abbrev_offset; ubyte pointer_size; -} __attribute__((packed)); +} __packed; #define DW_LNS_num_opcode (DW_LNS_set_isa + 1) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d89c9c7ef4e5..76ed7d03e500 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1,17 +1,26 @@ +#include <errno.h> +#include <inttypes.h> #include "util.h" +#include "string2.h" +#include <sys/param.h> #include <sys/types.h> #include <byteswap.h> #include <unistd.h> #include <stdio.h> #include <stdlib.h> +#include <linux/compiler.h> #include <linux/list.h> #include <linux/kernel.h> #include <linux/bitops.h> +#include <sys/stat.h> +#include <sys/types.h> #include <sys/utsname.h> +#include <unistd.h> #include "evlist.h" #include "evsel.h" #include "header.h" +#include "memswap.h" #include "../perf.h" #include "trace-event.h" #include "session.h" @@ -26,6 +35,8 @@ #include <api/fs/fs.h> #include "asm/bug.h" +#include "sane_ctype.h" + /* * magic2 = "PERFILE2" * must be a numerical value to let the endianness @@ -41,6 +52,8 @@ static const u64 __perf_magic2_sw = 0x50455246494c4532ULL; #define PERF_MAGIC __perf_magic2 +const char perf_version_string[] = PERF_VERSION; + struct perf_file_attr { struct perf_event_attr attr; struct perf_file_section ids; @@ -293,11 +306,7 @@ static int write_nrcpus(int fd, struct perf_header *h __maybe_unused, u32 nrc, nra; int ret; - nr = sysconf(_SC_NPROCESSORS_CONF); - if (nr < 0) - return -1; - - nrc = (u32)(nr & UINT_MAX); + nrc = cpu__max_present_cpu(); nr = sysconf(_SC_NPROCESSORS_ONLN); if (nr < 0) @@ -372,15 +381,11 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused, struct perf_evlist *evlist __maybe_unused) { char buf[MAXPATHLEN]; - char proc[32]; u32 n; int i, ret; - /* - * actual atual path to perf binary - */ - sprintf(proc, "/proc/%d/exe", getpid()); - ret = readlink(proc, buf, sizeof(buf)); + /* actual path to perf binary */ + ret = readlink("/proc/self/exe", buf, sizeof(buf) - 1); if (ret <= 0) return -1; @@ -503,24 +508,29 @@ static void free_cpu_topo(struct cpu_topo *tp) static struct cpu_topo *build_cpu_topology(void) { - struct cpu_topo *tp; + struct cpu_topo *tp = NULL; void *addr; u32 nr, i; size_t sz; long ncpus; int ret = -1; + struct cpu_map *map; - ncpus = sysconf(_SC_NPROCESSORS_CONF); - if (ncpus < 0) + ncpus = cpu__max_present_cpu(); + + /* build online CPU map */ + map = cpu_map__new(NULL); + if (map == NULL) { + pr_debug("failed to get system cpumap\n"); return NULL; + } nr = (u32)(ncpus & UINT_MAX); sz = nr * sizeof(char *); - addr = calloc(1, sizeof(*tp) + 2 * sz); if (!addr) - return NULL; + goto out_free; tp = addr; tp->cpu_nr = nr; @@ -530,10 +540,16 @@ static struct cpu_topo *build_cpu_topology(void) tp->thread_siblings = addr; for (i = 0; i < nr; i++) { + if (!cpu_map__has(map, i)) + continue; + ret = build_cpu_topo(tp, i); if (ret < 0) break; } + +out_free: + cpu_map__put(map); if (ret) { free_cpu_topo(tp); tp = NULL; @@ -826,7 +842,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused, /* * default get_cpuid(): nothing gets recorded - * actual implementation must be in arch/$(ARCH)/util/header.c + * actual implementation must be in arch/$(SRCARCH)/util/header.c */ int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused) { @@ -1124,7 +1140,7 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused, { int nr, i; char *str; - int cpu_nr = ph->env.nr_cpus_online; + int cpu_nr = ph->env.nr_cpus_avail; nr = ph->env.nr_sibling_cores; str = ph->env.sibling_cores; @@ -1259,7 +1275,7 @@ error: } static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val, - void *priv __attribute__((unused))) + void *priv __maybe_unused) { return fprintf(fp, ", %s = %s", name, val); } @@ -1454,8 +1470,16 @@ static int __event_process_build_id(struct build_id_event *bev, dso__set_build_id(dso, &bev->build_id); - if (!is_kernel_module(filename, cpumode)) - dso->kernel = dso_type; + if (dso_type != DSO_TYPE_USER) { + struct kmod_path m = { .name = NULL, }; + + if (!kmod_path__parse_name(&m, filename) && m.kmod) + dso__set_module_info(dso, &m, machine); + else + dso->kernel = dso_type; + + free(m.name); + } build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); @@ -1779,7 +1803,7 @@ static int process_cpu_topology(struct perf_file_section *section, u32 nr, i; char *str; struct strbuf sb; - int cpu_nr = ph->env.nr_cpus_online; + int cpu_nr = ph->env.nr_cpus_avail; u64 size = 0; ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu)); @@ -1860,7 +1884,7 @@ static int process_cpu_topology(struct perf_file_section *section, if (ph->needs_swap) nr = bswap_32(nr); - if (nr > (u32)cpu_nr) { + if (nr != (u32)-1 && nr > (u32)cpu_nr) { pr_debug("socket_id number is too big." "You may need to upgrade the perf tool.\n"); goto free_cpu; @@ -2265,6 +2289,9 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) perf_header__process_sections(header, fd, &hd, perf_file_section__fprintf_info); + if (session->file->is_pipe) + return 0; + fprintf(fp, "# missing features: "); for_each_clear_bit(bit, header->adds_features, HEADER_LAST_FEATURE) { if (bit) @@ -2801,8 +2828,10 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, } event = pevent_find_event(pevent, evsel->attr.config); - if (event == NULL) + if (event == NULL) { + pr_debug("cannot find event format for %d\n", (int)evsel->attr.config); return -1; + } if (!evsel->name) { snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name); @@ -3201,6 +3230,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, case PERF_EVENT_UPDATE__SCALE: ev_scale = (struct event_update_event_scale *) ev->data; evsel->scale = ev_scale->scale; + break; case PERF_EVENT_UPDATE__CPUS: ev_cpus = (struct event_update_event_cpus *) ev->data; diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c index 2821f8d77e52..15b95300d7f3 100644 --- a/tools/perf/util/help-unknown-cmd.c +++ b/tools/perf/util/help-unknown-cmd.c @@ -1,21 +1,18 @@ #include "cache.h" #include "config.h" +#include <poll.h> #include <stdio.h> #include <subcmd/help.h> #include "../builtin.h" #include "levenshtein.h" static int autocorrect; -static struct cmdnames aliases; static int perf_unknown_cmd_config(const char *var, const char *value, void *cb __maybe_unused) { if (!strcmp(var, "help.autocorrect")) - autocorrect = perf_config_int(var,value); - /* Also use aliases for command lookup */ - if (!prefixcmp(var, "alias.")) - add_cmdname(&aliases, var + 6, strlen(var + 6)); + return perf_config_int(&autocorrect, var,value); return 0; } @@ -59,14 +56,12 @@ const char *help_unknown_cmd(const char *cmd) memset(&main_cmds, 0, sizeof(main_cmds)); memset(&other_cmds, 0, sizeof(main_cmds)); - memset(&aliases, 0, sizeof(aliases)); perf_config(perf_unknown_cmd_config, NULL); load_command_list("perf-", &main_cmds, &other_cmds); - if (add_cmd_list(&main_cmds, &aliases) < 0 || - add_cmd_list(&main_cmds, &other_cmds) < 0) { + if (add_cmd_list(&main_cmds, &other_cmds) < 0) { fprintf(stderr, "ERROR: Failed to allocate command list for unknown command.\n"); goto end; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 6770a9645609..cf0186a088c1 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1,13 +1,19 @@ #include "util.h" #include "build-id.h" #include "hist.h" +#include "map.h" #include "session.h" +#include "namespaces.h" #include "sort.h" #include "evlist.h" #include "evsel.h" #include "annotate.h" +#include "srcline.h" +#include "thread.h" #include "ui/progress.h" +#include <errno.h> #include <math.h> +#include <sys/param.h> static bool hists__filter_entry_by_dso(struct hists *hists, struct hist_entry *he); @@ -68,7 +74,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) */ if (h->ms.sym) { symlen = h->ms.sym->namelen + 4; - if (verbose) + if (verbose > 0) symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL, symlen); } else { @@ -92,7 +98,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) if (h->branch_info) { if (h->branch_info->from.sym) { symlen = (int)h->branch_info->from.sym->namelen + 4; - if (verbose) + if (verbose > 0) symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen); @@ -106,7 +112,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) if (h->branch_info->to.sym) { symlen = (int)h->branch_info->to.sym->namelen + 4; - if (verbose) + if (verbose > 0) symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen); @@ -168,6 +174,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO); } + hists__new_col_len(hists, HISTC_CGROUP_ID, 20); hists__new_col_len(hists, HISTC_CPU, 3); hists__new_col_len(hists, HISTC_SOCKET, 6); hists__new_col_len(hists, HISTC_MEM_LOCKED, 6); @@ -573,9 +580,14 @@ __hists__add_entry(struct hists *hists, bool sample_self, struct hist_entry_ops *ops) { + struct namespaces *ns = thread__namespaces(al->thread); struct hist_entry entry = { .thread = al->thread, .comm = thread__comm(al->thread), + .cgroup_id = { + .dev = ns ? ns->link_info[CGROUP_NS_INDEX].dev : 0, + .ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0, + }, .ms = { .map = al->map, .sym = al->sym, @@ -1019,6 +1031,10 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, int max_stack_depth, void *arg) { int err, err2; + struct map *alm = NULL; + + if (al && al->map) + alm = map__get(al->map); err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent, iter->evsel, al, max_stack_depth); @@ -1058,6 +1074,8 @@ out: if (!err) err = err2; + map__put(alm); + return err; } @@ -1122,6 +1140,11 @@ void hist_entry__delete(struct hist_entry *he) zfree(&he->mem_info); } + if (he->inline_node) { + inline_node__delete(he->inline_node); + he->inline_node = NULL; + } + zfree(&he->stat_acc); free_srcline(he->srcline); if (he->srcfile && he->srcfile[0]) @@ -2439,8 +2462,10 @@ int parse_filter_percentage(const struct option *opt __maybe_unused, symbol_conf.filter_relative = true; else if (!strcmp(arg, "absolute")) symbol_conf.filter_relative = false; - else + else { + pr_debug("Invalid percentage: %s\n", arg); return -1; + } return 0; } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index d4b6514eeef5..ee3670a388df 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -30,6 +30,7 @@ enum hist_column { HISTC_DSO, HISTC_THREAD, HISTC_COMM, + HISTC_CGROUP_ID, HISTC_PARENT, HISTC_CPU, HISTC_SOCKET, @@ -57,6 +58,7 @@ enum hist_column { HISTC_SRCLINE_FROM, HISTC_SRCLINE_TO, HISTC_TRACE, + HISTC_SYM_SIZE, HISTC_NR_COLS, /* Last entry */ }; @@ -283,6 +285,8 @@ void perf_hpp_list__column_register(struct perf_hpp_list *list, struct perf_hpp_fmt *format); void perf_hpp_list__register_sort_field(struct perf_hpp_list *list, struct perf_hpp_fmt *format); +void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list, + struct perf_hpp_fmt *format); static inline void perf_hpp__column_register(struct perf_hpp_fmt *format) { @@ -294,6 +298,11 @@ static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format) perf_hpp_list__register_sort_field(&perf_hpp_list, format); } +static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format) +{ + perf_hpp_list__prepend_sort_field(&perf_hpp_list, format); +} + #define perf_hpp_list__for_each_format(_list, format) \ list_for_each_entry(format, &(_list)->fields, list) diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index 6c2eb5da4afc..218ee2bac9a5 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -14,7 +14,9 @@ */ #include <endian.h> +#include <errno.h> #include <byteswap.h> +#include <inttypes.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/bitops.h> @@ -864,8 +866,6 @@ static void intel_bts_print_info(u64 *arr, int start, int finish) fprintf(stdout, intel_bts_info_fmts[i], arr[i]); } -u64 intel_bts_auxtrace_info_priv[INTEL_BTS_AUXTRACE_PRIV_SIZE]; - int intel_bts_process_auxtrace_info(union perf_event *event, struct perf_session *session) { diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index 9b742ea8bfe8..7aca5d6d7e1f 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -23,4 +23,8 @@ $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/in $(call rule_mkdir) $(call if_changed_dep,cc_o_c) -CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder -Wno-override-init +CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder + +ifneq ($(CC), clang) + CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init +endif diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index e4e7dc781d21..aa1593ce551d 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -22,6 +22,7 @@ #include <errno.h> #include <stdint.h> #include <inttypes.h> +#include <linux/compiler.h> #include "../cache.h" #include "../util.h" @@ -63,6 +64,25 @@ enum intel_pt_pkt_state { INTEL_PT_STATE_FUP_NO_TIP, }; +static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state) +{ + switch (pkt_state) { + case INTEL_PT_STATE_NO_PSB: + case INTEL_PT_STATE_NO_IP: + case INTEL_PT_STATE_ERR_RESYNC: + case INTEL_PT_STATE_IN_SYNC: + case INTEL_PT_STATE_TNT: + return true; + case INTEL_PT_STATE_TIP: + case INTEL_PT_STATE_TIP_PGD: + case INTEL_PT_STATE_FUP: + case INTEL_PT_STATE_FUP_NO_TIP: + return false; + default: + return true; + }; +} + #ifdef INTEL_PT_STRICT #define INTEL_PT_STATE_ERR1 INTEL_PT_STATE_NO_PSB #define INTEL_PT_STATE_ERR2 INTEL_PT_STATE_NO_PSB @@ -86,11 +106,13 @@ struct intel_pt_decoder { const unsigned char *buf; size_t len; bool return_compression; + bool branch_enable; bool mtc_insn; bool pge; bool have_tma; bool have_cyc; bool fixup_last_mtc; + bool have_last_ip; uint64_t pos; uint64_t last_ip; uint64_t ip; @@ -98,6 +120,7 @@ struct intel_pt_decoder { uint64_t timestamp; uint64_t tsc_timestamp; uint64_t ref_timestamp; + uint64_t sample_timestamp; uint64_t ret_addr; uint64_t ctc_timestamp; uint64_t ctc_delta; @@ -118,6 +141,7 @@ struct intel_pt_decoder { int pkt_len; int last_packet_type; unsigned int cbr; + unsigned int cbr_seen; unsigned int max_non_turbo_ratio; double max_non_turbo_ratio_fp; double cbr_cyc_to_tsc; @@ -135,9 +159,18 @@ struct intel_pt_decoder { bool continuous_period; bool overflow; bool set_fup_tx_flags; + bool set_fup_ptw; + bool set_fup_mwait; + bool set_fup_pwre; + bool set_fup_exstop; unsigned int fup_tx_flags; unsigned int tx_flags; + uint64_t fup_ptw_payload; + uint64_t fup_mwait_payload; + uint64_t fup_pwre_payload; + uint64_t cbr_payload; uint64_t timestamp_insn_cnt; + uint64_t sample_insn_cnt; uint64_t stuck_ip; int no_progress; int stuck_ip_prd; @@ -191,6 +224,7 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->pgd_ip = params->pgd_ip; decoder->data = params->data; decoder->return_compression = params->return_compression; + decoder->branch_enable = params->branch_enable; decoder->period = params->period; decoder->period_type = params->period_type; @@ -397,6 +431,7 @@ static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet, static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder) { decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip); + decoder->have_last_ip = true; } static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder) @@ -634,6 +669,8 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) case INTEL_PT_PAD: case INTEL_PT_VMCS: case INTEL_PT_MNT: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: return 0; case INTEL_PT_MTC: @@ -674,6 +711,12 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) break; case INTEL_PT_TSC: + /* + * For now, do not support using TSC packets - refer + * intel_pt_calc_cyc_to_tsc(). + */ + if (data->from_mtc) + return 1; timestamp = pkt_info->packet.payload | (data->timestamp & (0xffULL << 56)); if (data->from_mtc && timestamp < data->timestamp && @@ -732,6 +775,11 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) case INTEL_PT_TIP_PGD: case INTEL_PT_TRACESTOP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: case INTEL_PT_OVF: case INTEL_PT_BAD: /* Does not happen */ default: @@ -786,6 +834,14 @@ static void intel_pt_calc_cyc_to_tsc(struct intel_pt_decoder *decoder, .cbr_cyc_to_tsc = 0, }; + /* + * For now, do not support using TSC packets for at least the reasons: + * 1) timing might have stopped + * 2) TSC packets within PSB+ can slip against CYC packets + */ + if (!from_mtc) + return; + intel_pt_pkt_lookahead(decoder, intel_pt_calc_cyc_cb, &data); } @@ -897,6 +953,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder, decoder->tot_insn_cnt += insn_cnt; decoder->timestamp_insn_cnt += insn_cnt; + decoder->sample_insn_cnt += insn_cnt; decoder->period_insn_cnt += insn_cnt; if (err) { @@ -989,6 +1046,57 @@ out_no_progress: return err; } +static bool intel_pt_fup_event(struct intel_pt_decoder *decoder) +{ + bool ret = false; + + if (decoder->set_fup_tx_flags) { + decoder->set_fup_tx_flags = false; + decoder->tx_flags = decoder->fup_tx_flags; + decoder->state.type = INTEL_PT_TRANSACTION; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.flags = decoder->fup_tx_flags; + return true; + } + if (decoder->set_fup_ptw) { + decoder->set_fup_ptw = false; + decoder->state.type = INTEL_PT_PTW; + decoder->state.flags |= INTEL_PT_FUP_IP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.ptw_payload = decoder->fup_ptw_payload; + return true; + } + if (decoder->set_fup_mwait) { + decoder->set_fup_mwait = false; + decoder->state.type = INTEL_PT_MWAIT_OP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.mwait_payload = decoder->fup_mwait_payload; + ret = true; + } + if (decoder->set_fup_pwre) { + decoder->set_fup_pwre = false; + decoder->state.type |= INTEL_PT_PWR_ENTRY; + decoder->state.type &= ~INTEL_PT_BRANCH; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.pwre_payload = decoder->fup_pwre_payload; + ret = true; + } + if (decoder->set_fup_exstop) { + decoder->set_fup_exstop = false; + decoder->state.type |= INTEL_PT_EX_STOP; + decoder->state.type &= ~INTEL_PT_BRANCH; + decoder->state.flags |= INTEL_PT_FUP_IP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + ret = true; + } + return ret; +} + static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) { struct intel_pt_insn intel_pt_insn; @@ -1002,15 +1110,8 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder) if (err == INTEL_PT_RETURN) return 0; if (err == -EAGAIN) { - if (decoder->set_fup_tx_flags) { - decoder->set_fup_tx_flags = false; - decoder->tx_flags = decoder->fup_tx_flags; - decoder->state.type = INTEL_PT_TRANSACTION; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; - decoder->state.flags = decoder->fup_tx_flags; + if (intel_pt_fup_event(decoder)) return 0; - } return err; } decoder->set_fup_tx_flags = false; @@ -1359,7 +1460,9 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder) static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder) { - unsigned int cbr = decoder->packet.payload; + unsigned int cbr = decoder->packet.payload & 0xff; + + decoder->cbr_payload = decoder->packet.payload; if (decoder->cbr == cbr) return; @@ -1416,6 +1519,13 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder) case INTEL_PT_TRACESTOP: case INTEL_PT_BAD: case INTEL_PT_PSB: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: decoder->have_tma = false; intel_pt_log("ERROR: Unexpected packet\n"); return -EAGAIN; @@ -1445,7 +1555,8 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: decoder->pge = true; - intel_pt_set_last_ip(decoder); + if (decoder->packet.count) + intel_pt_set_last_ip(decoder); break; case INTEL_PT_MODE_TSX: @@ -1496,6 +1607,13 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder) case INTEL_PT_MODE_TSX: case INTEL_PT_BAD: case INTEL_PT_PSBEND: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: intel_pt_log("ERROR: Missing TIP after FUP\n"); decoder->pkt_state = INTEL_PT_STATE_ERR3; return -ENOENT; @@ -1624,6 +1742,15 @@ next: break; } intel_pt_set_last_ip(decoder); + if (!decoder->branch_enable) { + decoder->ip = decoder->last_ip; + if (intel_pt_fup_event(decoder)) + return 0; + no_tip = false; + break; + } + if (decoder->set_fup_mwait) + no_tip = true; err = intel_pt_walk_fup(decoder); if (err != -EAGAIN) { if (err) @@ -1649,6 +1776,8 @@ next: break; case INTEL_PT_PSB: + decoder->last_ip = 0; + decoder->have_last_ip = true; intel_pt_clear_stack(&decoder->stack); err = intel_pt_walk_psbend(decoder); if (err == -EAGAIN) @@ -1695,6 +1824,16 @@ next: case INTEL_PT_CBR: intel_pt_calc_cbr(decoder); + if (!decoder->branch_enable && + decoder->cbr != decoder->cbr_seen) { + decoder->cbr_seen = decoder->cbr; + decoder->state.type = INTEL_PT_CBR_CHG; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.cbr_payload = + decoder->packet.payload; + return 0; + } break; case INTEL_PT_MODE_EXEC: @@ -1721,6 +1860,71 @@ next: case INTEL_PT_PAD: break; + case INTEL_PT_PTWRITE_IP: + decoder->fup_ptw_payload = decoder->packet.payload; + err = intel_pt_get_next_packet(decoder); + if (err) + return err; + if (decoder->packet.type == INTEL_PT_FUP) { + decoder->set_fup_ptw = true; + no_tip = true; + } else { + intel_pt_log_at("ERROR: Missing FUP after PTWRITE", + decoder->pos); + } + goto next; + + case INTEL_PT_PTWRITE: + decoder->state.type = INTEL_PT_PTW; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.ptw_payload = decoder->packet.payload; + return 0; + + case INTEL_PT_MWAIT: + decoder->fup_mwait_payload = decoder->packet.payload; + decoder->set_fup_mwait = true; + break; + + case INTEL_PT_PWRE: + if (decoder->set_fup_mwait) { + decoder->fup_pwre_payload = + decoder->packet.payload; + decoder->set_fup_pwre = true; + break; + } + decoder->state.type = INTEL_PT_PWR_ENTRY; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.pwrx_payload = decoder->packet.payload; + return 0; + + case INTEL_PT_EXSTOP_IP: + err = intel_pt_get_next_packet(decoder); + if (err) + return err; + if (decoder->packet.type == INTEL_PT_FUP) { + decoder->set_fup_exstop = true; + no_tip = true; + } else { + intel_pt_log_at("ERROR: Missing FUP after EXSTOP", + decoder->pos); + } + goto next; + + case INTEL_PT_EXSTOP: + decoder->state.type = INTEL_PT_EX_STOP; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + return 0; + + case INTEL_PT_PWRX: + decoder->state.type = INTEL_PT_PWR_EXIT; + decoder->state.from_ip = decoder->ip; + decoder->state.to_ip = 0; + decoder->state.pwrx_payload = decoder->packet.payload; + return 0; + default: return intel_pt_bug(decoder); } @@ -1729,8 +1933,9 @@ next: static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder) { - return decoder->last_ip || decoder->packet.count == 0 || - decoder->packet.count == 3 || decoder->packet.count == 6; + return decoder->packet.count && + (decoder->have_last_ip || decoder->packet.count == 3 || + decoder->packet.count == 6); } /* Walk PSB+ packets to get in sync. */ @@ -1746,8 +1951,16 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) switch (decoder->packet.type) { case INTEL_PT_TIP_PGD: decoder->continuous_period = false; + __fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: intel_pt_log("ERROR: Unexpected packet\n"); return -ENOENT; @@ -1799,6 +2012,8 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) decoder->pge = false; decoder->continuous_period = false; intel_pt_clear_tx_flags(decoder); + __fallthrough; + case INTEL_PT_TNT: decoder->have_tma = false; intel_pt_log("ERROR: Unexpected packet\n"); @@ -1839,6 +2054,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) switch (decoder->packet.type) { case INTEL_PT_TIP_PGD: decoder->continuous_period = false; + __fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD; @@ -1849,14 +2065,10 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) break; case INTEL_PT_FUP: - if (decoder->overflow) { - if (intel_pt_have_ip(decoder)) - intel_pt_set_ip(decoder); - if (decoder->ip) - return 0; - } - if (decoder->packet.count) - intel_pt_set_last_ip(decoder); + if (intel_pt_have_ip(decoder)) + intel_pt_set_ip(decoder); + if (decoder->ip) + return 0; break; case INTEL_PT_MTC: @@ -1905,6 +2117,9 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) break; case INTEL_PT_PSB: + decoder->last_ip = 0; + decoder->have_last_ip = true; + intel_pt_clear_stack(&decoder->stack); err = intel_pt_walk_psb(decoder); if (err) return err; @@ -1920,6 +2135,13 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) case INTEL_PT_VMCS: case INTEL_PT_MNT: case INTEL_PT_PAD: + case INTEL_PT_PTWRITE: + case INTEL_PT_PTWRITE_IP: + case INTEL_PT_EXSTOP: + case INTEL_PT_EXSTOP_IP: + case INTEL_PT_MWAIT: + case INTEL_PT_PWRE: + case INTEL_PT_PWRX: default: break; } @@ -1930,6 +2152,19 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder) { int err; + decoder->set_fup_tx_flags = false; + decoder->set_fup_ptw = false; + decoder->set_fup_mwait = false; + decoder->set_fup_pwre = false; + decoder->set_fup_exstop = false; + + if (!decoder->branch_enable) { + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + decoder->overflow = false; + decoder->state.type = 0; /* Do not have a sample */ + return 0; + } + intel_pt_log("Scanning for full IP\n"); err = intel_pt_walk_to_ip(decoder); if (err) @@ -2038,6 +2273,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) decoder->pge = false; decoder->continuous_period = false; + decoder->have_last_ip = false; decoder->last_ip = 0; decoder->ip = 0; intel_pt_clear_stack(&decoder->stack); @@ -2046,6 +2282,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) if (err) return err; + decoder->have_last_ip = true; decoder->pkt_state = INTEL_PT_STATE_NO_IP; err = intel_pt_walk_psb(decoder); @@ -2064,7 +2301,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder) { - uint64_t est = decoder->timestamp_insn_cnt << 1; + uint64_t est = decoder->sample_insn_cnt << 1; if (!decoder->cbr || !decoder->max_non_turbo_ratio) goto out; @@ -2072,7 +2309,7 @@ static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder) est *= decoder->max_non_turbo_ratio; est /= decoder->cbr; out: - return decoder->timestamp + est; + return decoder->sample_timestamp + est; } const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) @@ -2088,8 +2325,10 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) err = intel_pt_sync(decoder); break; case INTEL_PT_STATE_NO_IP: + decoder->have_last_ip = false; decoder->last_ip = 0; - /* Fall through */ + decoder->ip = 0; + __fallthrough; case INTEL_PT_STATE_ERR_RESYNC: err = intel_pt_sync_ip(decoder); break; @@ -2125,15 +2364,29 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) } } while (err == -ENOLINK); - decoder->state.err = err ? intel_pt_ext_err(err) : 0; - decoder->state.timestamp = decoder->timestamp; + if (err) { + decoder->state.err = intel_pt_ext_err(err); + decoder->state.from_ip = decoder->ip; + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; + } else { + decoder->state.err = 0; + if (decoder->cbr != decoder->cbr_seen && decoder->state.type) { + decoder->cbr_seen = decoder->cbr; + decoder->state.type |= INTEL_PT_CBR_CHG; + decoder->state.cbr_payload = decoder->cbr_payload; + } + if (intel_pt_sample_time(decoder->pkt_state)) { + decoder->sample_timestamp = decoder->timestamp; + decoder->sample_insn_cnt = decoder->timestamp_insn_cnt; + } + } + + decoder->state.timestamp = decoder->sample_timestamp; decoder->state.est_timestamp = intel_pt_est_timestamp(decoder); decoder->state.cr3 = decoder->cr3; decoder->state.tot_insn_cnt = decoder->tot_insn_cnt; - if (err) - decoder->state.from_ip = decoder->ip; - return &decoder->state; } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h index e90619a43c0c..921b22e8ca0e 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h @@ -25,11 +25,18 @@ #define INTEL_PT_IN_TX (1 << 0) #define INTEL_PT_ABORT_TX (1 << 1) #define INTEL_PT_ASYNC (1 << 2) +#define INTEL_PT_FUP_IP (1 << 3) enum intel_pt_sample_type { INTEL_PT_BRANCH = 1 << 0, INTEL_PT_INSTRUCTION = 1 << 1, INTEL_PT_TRANSACTION = 1 << 2, + INTEL_PT_PTW = 1 << 3, + INTEL_PT_MWAIT_OP = 1 << 4, + INTEL_PT_PWR_ENTRY = 1 << 5, + INTEL_PT_EX_STOP = 1 << 6, + INTEL_PT_PWR_EXIT = 1 << 7, + INTEL_PT_CBR_CHG = 1 << 8, }; enum intel_pt_period_type { @@ -63,6 +70,11 @@ struct intel_pt_state { uint64_t timestamp; uint64_t est_timestamp; uint64_t trace_nr; + uint64_t ptw_payload; + uint64_t mwait_payload; + uint64_t pwre_payload; + uint64_t pwrx_payload; + uint64_t cbr_payload; uint32_t flags; enum intel_pt_insn_op insn_op; int insn_len; @@ -87,6 +99,7 @@ struct intel_pt_params { bool (*pgd_ip)(uint64_t ip, void *data); void *data; bool return_compression; + bool branch_enable; uint64_t period; enum intel_pt_period_type period_type; unsigned max_non_turbo_ratio; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index 7913363bde5c..54818828023b 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -26,12 +26,13 @@ #include "insn.c" #include "intel-pt-insn-decoder.h" +#include "dump-insn.h" #if INTEL_PT_INSN_BUF_SZ < MAX_INSN_SIZE || INTEL_PT_INSN_BUF_SZ > MAX_INSN #error Instruction buffer size too small #endif -/* Based on branch_type() from perf_event_intel_lbr.c */ +/* Based on branch_type() from arch/x86/events/intel/lbr.c */ static void intel_pt_insn_decoder(struct insn *insn, struct intel_pt_insn *intel_pt_insn) { @@ -39,6 +40,8 @@ static void intel_pt_insn_decoder(struct insn *insn, enum intel_pt_insn_branch branch = INTEL_PT_BR_NO_BRANCH; int ext; + intel_pt_insn->rel = 0; + if (insn_is_avx(insn)) { intel_pt_insn->op = INTEL_PT_OP_OTHER; intel_pt_insn->branch = INTEL_PT_BR_NO_BRANCH; @@ -177,6 +180,29 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64, return 0; } +const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused, + u8 *inbuf, int inlen, int *lenp) +{ + struct insn insn; + int n, i; + int left; + + insn_init(&insn, inbuf, inlen, x->is64bit); + insn_get_length(&insn); + if (!insn_complete(&insn) || insn.length > inlen) + return "<bad>"; + if (lenp) + *lenp = insn.length; + left = sizeof(x->out); + n = snprintf(x->out, left, "insn: "); + left -= n; + for (i = 0; i < insn.length; i++) { + n += snprintf(x->out + n, left, "%02x ", inbuf[i]); + left -= n; + } + return x->out; +} + const char *branch_name[] = { [INTEL_PT_OP_OTHER] = "Other", [INTEL_PT_OP_CALL] = "Call", diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h index debe751dc3d6..45b64f93f358 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h @@ -16,6 +16,7 @@ #ifndef INCLUDE__INTEL_PT_LOG_H__ #define INCLUDE__INTEL_PT_LOG_H__ +#include <linux/compiler.h> #include <stdint.h> #include <inttypes.h> @@ -34,8 +35,7 @@ void __intel_pt_log_insn(struct intel_pt_insn *intel_pt_insn, uint64_t ip); void __intel_pt_log_insn_no_data(struct intel_pt_insn *intel_pt_insn, uint64_t ip); -__attribute__((format(printf, 1, 2))) -void __intel_pt_log(const char *fmt, ...); +void __intel_pt_log(const char *fmt, ...) __printf(1, 2); #define intel_pt_log(fmt, ...) \ do { \ diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index 4f7b32020487..ba4c9dd18643 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -17,6 +17,7 @@ #include <string.h> #include <endian.h> #include <byteswap.h> +#include <linux/compiler.h> #include "intel-pt-pkt-decoder.h" @@ -63,6 +64,13 @@ static const char * const packet_name[] = { [INTEL_PT_PIP] = "PIP", [INTEL_PT_OVF] = "OVF", [INTEL_PT_MNT] = "MNT", + [INTEL_PT_PTWRITE] = "PTWRITE", + [INTEL_PT_PTWRITE_IP] = "PTWRITE", + [INTEL_PT_EXSTOP] = "EXSTOP", + [INTEL_PT_EXSTOP_IP] = "EXSTOP", + [INTEL_PT_MWAIT] = "MWAIT", + [INTEL_PT_PWRE] = "PWRE", + [INTEL_PT_PWRX] = "PWRX", }; const char *intel_pt_pkt_name(enum intel_pt_pkt_type type) @@ -122,7 +130,7 @@ static int intel_pt_get_cbr(const unsigned char *buf, size_t len, if (len < 4) return INTEL_PT_NEED_MORE_BYTES; packet->type = INTEL_PT_CBR; - packet->payload = buf[2]; + packet->payload = le16_to_cpu(*(uint16_t *)(buf + 2)); return 4; } @@ -216,12 +224,80 @@ static int intel_pt_get_3byte(const unsigned char *buf, size_t len, } } +static int intel_pt_get_ptwrite(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + packet->count = (buf[1] >> 5) & 0x3; + packet->type = buf[1] & BIT(7) ? INTEL_PT_PTWRITE_IP : + INTEL_PT_PTWRITE; + + switch (packet->count) { + case 0: + if (len < 6) + return INTEL_PT_NEED_MORE_BYTES; + packet->payload = le32_to_cpu(*(uint32_t *)(buf + 2)); + return 6; + case 1: + if (len < 10) + return INTEL_PT_NEED_MORE_BYTES; + packet->payload = le64_to_cpu(*(uint64_t *)(buf + 2)); + return 10; + default: + return INTEL_PT_BAD_PACKET; + } +} + +static int intel_pt_get_exstop(struct intel_pt_pkt *packet) +{ + packet->type = INTEL_PT_EXSTOP; + return 2; +} + +static int intel_pt_get_exstop_ip(struct intel_pt_pkt *packet) +{ + packet->type = INTEL_PT_EXSTOP_IP; + return 2; +} + +static int intel_pt_get_mwait(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + if (len < 10) + return INTEL_PT_NEED_MORE_BYTES; + packet->type = INTEL_PT_MWAIT; + packet->payload = le64_to_cpu(*(uint64_t *)(buf + 2)); + return 10; +} + +static int intel_pt_get_pwre(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + if (len < 4) + return INTEL_PT_NEED_MORE_BYTES; + packet->type = INTEL_PT_PWRE; + memcpy_le64(&packet->payload, buf + 2, 2); + return 4; +} + +static int intel_pt_get_pwrx(const unsigned char *buf, size_t len, + struct intel_pt_pkt *packet) +{ + if (len < 7) + return INTEL_PT_NEED_MORE_BYTES; + packet->type = INTEL_PT_PWRX; + memcpy_le64(&packet->payload, buf + 2, 5); + return 7; +} + static int intel_pt_get_ext(const unsigned char *buf, size_t len, struct intel_pt_pkt *packet) { if (len < 2) return INTEL_PT_NEED_MORE_BYTES; + if ((buf[1] & 0x1f) == 0x12) + return intel_pt_get_ptwrite(buf, len, packet); + switch (buf[1]) { case 0xa3: /* Long TNT */ return intel_pt_get_long_tnt(buf, len, packet); @@ -243,6 +319,16 @@ static int intel_pt_get_ext(const unsigned char *buf, size_t len, return intel_pt_get_tma(buf, len, packet); case 0xC3: /* 3-byte header */ return intel_pt_get_3byte(buf, len, packet); + case 0x62: /* EXSTOP no IP */ + return intel_pt_get_exstop(packet); + case 0xE2: /* EXSTOP with IP */ + return intel_pt_get_exstop_ip(packet); + case 0xC2: /* MWAIT */ + return intel_pt_get_mwait(buf, len, packet); + case 0x22: /* PWRE */ + return intel_pt_get_pwre(buf, len, packet); + case 0xA2: /* PWRX */ + return intel_pt_get_pwrx(buf, len, packet); default: return INTEL_PT_BAD_PACKET; } @@ -498,6 +584,7 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, case INTEL_PT_FUP: if (!(packet->count)) return snprintf(buf, buf_len, "%s no ip", name); + __fallthrough; case INTEL_PT_CYC: case INTEL_PT_VMCS: case INTEL_PT_MTC: @@ -520,6 +607,29 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, ret = snprintf(buf, buf_len, "%s 0x%llx (NR=%d)", name, payload, nr); return ret; + case INTEL_PT_PTWRITE: + return snprintf(buf, buf_len, "%s 0x%llx IP:0", name, payload); + case INTEL_PT_PTWRITE_IP: + return snprintf(buf, buf_len, "%s 0x%llx IP:1", name, payload); + case INTEL_PT_EXSTOP: + return snprintf(buf, buf_len, "%s IP:0", name); + case INTEL_PT_EXSTOP_IP: + return snprintf(buf, buf_len, "%s IP:1", name); + case INTEL_PT_MWAIT: + return snprintf(buf, buf_len, "%s 0x%llx Hints 0x%x Extensions 0x%x", + name, payload, (unsigned int)(payload & 0xff), + (unsigned int)((payload >> 32) & 0x3)); + case INTEL_PT_PWRE: + return snprintf(buf, buf_len, "%s 0x%llx HW:%u CState:%u Sub-CState:%u", + name, payload, !!(payload & 0x80), + (unsigned int)((payload >> 12) & 0xf), + (unsigned int)((payload >> 8) & 0xf)); + case INTEL_PT_PWRX: + return snprintf(buf, buf_len, "%s 0x%llx Last CState:%u Deepest CState:%u Wake Reason 0x%x", + name, payload, + (unsigned int)((payload >> 4) & 0xf), + (unsigned int)(payload & 0xf), + (unsigned int)((payload >> 8) & 0xf)); default: break; } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h index 781bb79883bd..73ddc3a88d07 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h @@ -52,6 +52,13 @@ enum intel_pt_pkt_type { INTEL_PT_PIP, INTEL_PT_OVF, INTEL_PT_MNT, + INTEL_PT_PTWRITE, + INTEL_PT_PTWRITE_IP, + INTEL_PT_EXSTOP, + INTEL_PT_EXSTOP_IP, + INTEL_PT_MWAIT, + INTEL_PT_PWRE, + INTEL_PT_PWRX, }; struct intel_pt_pkt { diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt index 767be7c76034..12e377184ee4 100644 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt @@ -1009,7 +1009,7 @@ GrpTable: Grp15 1: fxstor | RDGSBASE Ry (F3),(11B) 2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B) 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) -4: XSAVE +4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) 7: clflush | clflushopt (66) | sfence (11B) diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 85d5eeb66c75..b58f9fd1e2ee 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -13,6 +13,7 @@ * */ +#include <inttypes.h> #include <stdio.h> #include <stdbool.h> #include <errno.h> @@ -22,6 +23,7 @@ #include "../perf.h" #include "session.h" #include "machine.h" +#include "memswap.h" #include "sort.h" #include "tool.h" #include "event.h" @@ -79,7 +81,6 @@ struct intel_pt { bool sample_instructions; u64 instructions_sample_type; - u64 instructions_sample_period; u64 instructions_id; bool sample_branches; @@ -91,6 +92,18 @@ struct intel_pt { u64 transactions_sample_type; u64 transactions_id; + bool sample_ptwrites; + u64 ptwrites_sample_type; + u64 ptwrites_id; + + bool sample_pwr_events; + u64 pwr_events_sample_type; + u64 mwait_id; + u64 pwre_id; + u64 exstop_id; + u64 pwrx_id; + u64 cbr_id; + bool synth_needs_swap; u64 tsc_bit; @@ -101,6 +114,7 @@ struct intel_pt { u64 cyc_bit; u64 noretcomp_bit; unsigned max_non_turbo_ratio; + unsigned cbr2khz; unsigned long num_events; @@ -666,6 +680,19 @@ static bool intel_pt_return_compression(struct intel_pt *pt) return true; } +static bool intel_pt_branch_enable(struct intel_pt *pt) +{ + struct perf_evsel *evsel; + u64 config; + + evlist__for_each_entry(pt->session->evlist, evsel) { + if (intel_pt_get_config(pt, &evsel->attr, &config) && + (config & 1) && !(config & 0x2000)) + return false; + } + return true; +} + static unsigned int intel_pt_mtc_period(struct intel_pt *pt) { struct perf_evsel *evsel; @@ -797,6 +824,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt, params.walk_insn = intel_pt_walk_next_insn; params.data = ptq; params.return_compression = intel_pt_return_compression(pt); + params.branch_enable = intel_pt_branch_enable(pt); params.max_non_turbo_ratio = pt->max_non_turbo_ratio; params.mtc_period = intel_pt_mtc_period(pt); params.tsc_ctc_ratio_n = pt->tsc_ctc_ratio_n; @@ -1042,6 +1070,36 @@ static void intel_pt_update_last_branch_rb(struct intel_pt_queue *ptq) bs->nr += 1; } +static inline bool intel_pt_skip_event(struct intel_pt *pt) +{ + return pt->synth_opts.initial_skip && + pt->num_events++ < pt->synth_opts.initial_skip; +} + +static void intel_pt_prep_b_sample(struct intel_pt *pt, + struct intel_pt_queue *ptq, + union perf_event *event, + struct perf_sample *sample) +{ + event->sample.header.type = PERF_RECORD_SAMPLE; + event->sample.header.misc = PERF_RECORD_MISC_USER; + event->sample.header.size = sizeof(struct perf_event_header); + + if (!pt->timeless_decoding) + sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + + sample->cpumode = PERF_RECORD_MISC_USER; + sample->ip = ptq->state->from_ip; + sample->pid = ptq->pid; + sample->tid = ptq->tid; + sample->addr = ptq->state->to_ip; + sample->period = 1; + sample->cpu = ptq->cpu; + sample->flags = ptq->flags; + sample->insn_len = ptq->insn_len; + memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); +} + static int intel_pt_inject_event(union perf_event *event, struct perf_sample *sample, u64 type, bool swapped) @@ -1050,9 +1108,35 @@ static int intel_pt_inject_event(union perf_event *event, return perf_event__synthesize_sample(event, type, 0, sample, swapped); } -static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) +static inline int intel_pt_opt_inject(struct intel_pt *pt, + union perf_event *event, + struct perf_sample *sample, u64 type) +{ + if (!pt->synth_opts.inject) + return 0; + + return intel_pt_inject_event(event, sample, type, pt->synth_needs_swap); +} + +static int intel_pt_deliver_synth_b_event(struct intel_pt *pt, + union perf_event *event, + struct perf_sample *sample, u64 type) { int ret; + + ret = intel_pt_opt_inject(pt, event, sample, type); + if (ret) + return ret; + + ret = perf_session__deliver_synth_event(pt->session, event, sample); + if (ret) + pr_err("Intel PT: failed to deliver event, error %d\n", ret); + + return ret; +} + +static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) +{ struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; @@ -1064,29 +1148,13 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) if (pt->branches_filter && !(pt->branches_filter & ptq->flags)) return 0; - if (pt->synth_opts.initial_skip && - pt->num_events++ < pt->synth_opts.initial_skip) + if (intel_pt_skip_event(pt)) return 0; - event->sample.header.type = PERF_RECORD_SAMPLE; - event->sample.header.misc = PERF_RECORD_MISC_USER; - event->sample.header.size = sizeof(struct perf_event_header); - - if (!pt->timeless_decoding) - sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + intel_pt_prep_b_sample(pt, ptq, event, &sample); - sample.cpumode = PERF_RECORD_MISC_USER; - sample.ip = ptq->state->from_ip; - sample.pid = ptq->pid; - sample.tid = ptq->tid; - sample.addr = ptq->state->to_ip; sample.id = ptq->pt->branches_id; sample.stream_id = ptq->pt->branches_id; - sample.period = 1; - sample.cpu = ptq->cpu; - sample.flags = ptq->flags; - sample.insn_len = ptq->insn_len; - memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); /* * perf report cannot handle events without a branch stack when using @@ -1103,144 +1171,251 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) sample.branch_stack = (struct branch_stack *)&dummy_bs; } - if (pt->synth_opts.inject) { - ret = intel_pt_inject_event(event, &sample, - pt->branches_sample_type, - pt->synth_needs_swap); - if (ret) - return ret; + return intel_pt_deliver_synth_b_event(pt, event, &sample, + pt->branches_sample_type); +} + +static void intel_pt_prep_sample(struct intel_pt *pt, + struct intel_pt_queue *ptq, + union perf_event *event, + struct perf_sample *sample) +{ + intel_pt_prep_b_sample(pt, ptq, event, sample); + + if (pt->synth_opts.callchain) { + thread_stack__sample(ptq->thread, ptq->chain, + pt->synth_opts.callchain_sz, sample->ip); + sample->callchain = ptq->chain; } - ret = perf_session__deliver_synth_event(pt->session, event, &sample); - if (ret) - pr_err("Intel Processor Trace: failed to deliver branch event, error %d\n", - ret); + if (pt->synth_opts.last_branch) { + intel_pt_copy_last_branch_rb(ptq); + sample->branch_stack = ptq->last_branch; + } +} + +static inline int intel_pt_deliver_synth_event(struct intel_pt *pt, + struct intel_pt_queue *ptq, + union perf_event *event, + struct perf_sample *sample, + u64 type) +{ + int ret; + + ret = intel_pt_deliver_synth_b_event(pt, event, sample, type); + + if (pt->synth_opts.last_branch) + intel_pt_reset_last_branch_rb(ptq); return ret; } static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) { - int ret; struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; - if (pt->synth_opts.initial_skip && - pt->num_events++ < pt->synth_opts.initial_skip) + if (intel_pt_skip_event(pt)) return 0; - event->sample.header.type = PERF_RECORD_SAMPLE; - event->sample.header.misc = PERF_RECORD_MISC_USER; - event->sample.header.size = sizeof(struct perf_event_header); - - if (!pt->timeless_decoding) - sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + intel_pt_prep_sample(pt, ptq, event, &sample); - sample.cpumode = PERF_RECORD_MISC_USER; - sample.ip = ptq->state->from_ip; - sample.pid = ptq->pid; - sample.tid = ptq->tid; - sample.addr = ptq->state->to_ip; sample.id = ptq->pt->instructions_id; sample.stream_id = ptq->pt->instructions_id; sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt; - sample.cpu = ptq->cpu; - sample.flags = ptq->flags; - sample.insn_len = ptq->insn_len; - memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); ptq->last_insn_cnt = ptq->state->tot_insn_cnt; - if (pt->synth_opts.callchain) { - thread_stack__sample(ptq->thread, ptq->chain, - pt->synth_opts.callchain_sz, sample.ip); - sample.callchain = ptq->chain; - } + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->instructions_sample_type); +} - if (pt->synth_opts.last_branch) { - intel_pt_copy_last_branch_rb(ptq); - sample.branch_stack = ptq->last_branch; - } +static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; - if (pt->synth_opts.inject) { - ret = intel_pt_inject_event(event, &sample, - pt->instructions_sample_type, - pt->synth_needs_swap); - if (ret) - return ret; - } + if (intel_pt_skip_event(pt)) + return 0; - ret = perf_session__deliver_synth_event(pt->session, event, &sample); - if (ret) - pr_err("Intel Processor Trace: failed to deliver instruction event, error %d\n", - ret); + intel_pt_prep_sample(pt, ptq, event, &sample); - if (pt->synth_opts.last_branch) - intel_pt_reset_last_branch_rb(ptq); + sample.id = ptq->pt->transactions_id; + sample.stream_id = ptq->pt->transactions_id; - return ret; + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->transactions_sample_type); } -static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) +static void intel_pt_prep_p_sample(struct intel_pt *pt, + struct intel_pt_queue *ptq, + union perf_event *event, + struct perf_sample *sample) +{ + intel_pt_prep_sample(pt, ptq, event, sample); + + /* + * Zero IP is used to mean "trace start" but that is not the case for + * power or PTWRITE events with no IP, so clear the flags. + */ + if (!sample->ip) + sample->flags = 0; +} + +static int intel_pt_synth_ptwrite_sample(struct intel_pt_queue *ptq) { - int ret; struct intel_pt *pt = ptq->pt; union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_ptwrite raw; - if (pt->synth_opts.initial_skip && - pt->num_events++ < pt->synth_opts.initial_skip) + if (intel_pt_skip_event(pt)) return 0; - event->sample.header.type = PERF_RECORD_SAMPLE; - event->sample.header.misc = PERF_RECORD_MISC_USER; - event->sample.header.size = sizeof(struct perf_event_header); + intel_pt_prep_p_sample(pt, ptq, event, &sample); - if (!pt->timeless_decoding) - sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc); + sample.id = ptq->pt->ptwrites_id; + sample.stream_id = ptq->pt->ptwrites_id; - sample.cpumode = PERF_RECORD_MISC_USER; - sample.ip = ptq->state->from_ip; - sample.pid = ptq->pid; - sample.tid = ptq->tid; - sample.addr = ptq->state->to_ip; - sample.id = ptq->pt->transactions_id; - sample.stream_id = ptq->pt->transactions_id; - sample.period = 1; - sample.cpu = ptq->cpu; - sample.flags = ptq->flags; - sample.insn_len = ptq->insn_len; - memcpy(sample.insn, ptq->insn, INTEL_PT_INSN_BUF_SZ); + raw.flags = 0; + raw.ip = !!(ptq->state->flags & INTEL_PT_FUP_IP); + raw.payload = cpu_to_le64(ptq->state->ptw_payload); - if (pt->synth_opts.callchain) { - thread_stack__sample(ptq->thread, ptq->chain, - pt->synth_opts.callchain_sz, sample.ip); - sample.callchain = ptq->chain; - } + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); - if (pt->synth_opts.last_branch) { - intel_pt_copy_last_branch_rb(ptq); - sample.branch_stack = ptq->last_branch; - } + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->ptwrites_sample_type); +} - if (pt->synth_opts.inject) { - ret = intel_pt_inject_event(event, &sample, - pt->transactions_sample_type, - pt->synth_needs_swap); - if (ret) - return ret; - } +static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_cbr raw; + u32 flags; - ret = perf_session__deliver_synth_event(pt->session, event, &sample); - if (ret) - pr_err("Intel Processor Trace: failed to deliver transaction event, error %d\n", - ret); + if (intel_pt_skip_event(pt)) + return 0; - if (pt->synth_opts.last_branch) - intel_pt_reset_last_branch_rb(ptq); + intel_pt_prep_p_sample(pt, ptq, event, &sample); - return ret; + sample.id = ptq->pt->cbr_id; + sample.stream_id = ptq->pt->cbr_id; + + flags = (u16)ptq->state->cbr_payload | (pt->max_non_turbo_ratio << 16); + raw.flags = cpu_to_le32(flags); + raw.freq = cpu_to_le32(raw.cbr * pt->cbr2khz); + raw.reserved3 = 0; + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); +} + +static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_mwait raw; + + if (intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_p_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->mwait_id; + sample.stream_id = ptq->pt->mwait_id; + + raw.reserved = 0; + raw.payload = cpu_to_le64(ptq->state->mwait_payload); + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); +} + +static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_pwre raw; + + if (intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_p_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->pwre_id; + sample.stream_id = ptq->pt->pwre_id; + + raw.reserved = 0; + raw.payload = cpu_to_le64(ptq->state->pwre_payload); + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); +} + +static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_exstop raw; + + if (intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_p_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->exstop_id; + sample.stream_id = ptq->pt->exstop_id; + + raw.flags = 0; + raw.ip = !!(ptq->state->flags & INTEL_PT_FUP_IP); + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); +} + +static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq) +{ + struct intel_pt *pt = ptq->pt; + union perf_event *event = ptq->event_buf; + struct perf_sample sample = { .ip = 0, }; + struct perf_synth_intel_pwrx raw; + + if (intel_pt_skip_event(pt)) + return 0; + + intel_pt_prep_p_sample(pt, ptq, event, &sample); + + sample.id = ptq->pt->pwrx_id; + sample.stream_id = ptq->pt->pwrx_id; + + raw.reserved = 0; + raw.payload = cpu_to_le64(ptq->state->pwrx_payload); + + sample.raw_size = perf_synth__raw_size(raw); + sample.raw_data = perf_synth__raw_data(&raw); + + return intel_pt_deliver_synth_event(pt, ptq, event, &sample, + pt->pwr_events_sample_type); } static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu, @@ -1294,6 +1469,10 @@ static inline bool intel_pt_is_switch_ip(struct intel_pt_queue *ptq, u64 ip) PERF_IP_FLAG_INTERRUPT | PERF_IP_FLAG_TX_ABORT)); } +#define INTEL_PT_PWR_EVT (INTEL_PT_MWAIT_OP | INTEL_PT_PWR_ENTRY | \ + INTEL_PT_EX_STOP | INTEL_PT_PWR_EXIT | \ + INTEL_PT_CBR_CHG) + static int intel_pt_sample(struct intel_pt_queue *ptq) { const struct intel_pt_state *state = ptq->state; @@ -1305,24 +1484,52 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) ptq->have_sample = false; - if (pt->sample_instructions && - (state->type & INTEL_PT_INSTRUCTION) && - (!pt->synth_opts.initial_skip || - pt->num_events++ >= pt->synth_opts.initial_skip)) { + if (pt->sample_pwr_events && (state->type & INTEL_PT_PWR_EVT)) { + if (state->type & INTEL_PT_CBR_CHG) { + err = intel_pt_synth_cbr_sample(ptq); + if (err) + return err; + } + if (state->type & INTEL_PT_MWAIT_OP) { + err = intel_pt_synth_mwait_sample(ptq); + if (err) + return err; + } + if (state->type & INTEL_PT_PWR_ENTRY) { + err = intel_pt_synth_pwre_sample(ptq); + if (err) + return err; + } + if (state->type & INTEL_PT_EX_STOP) { + err = intel_pt_synth_exstop_sample(ptq); + if (err) + return err; + } + if (state->type & INTEL_PT_PWR_EXIT) { + err = intel_pt_synth_pwrx_sample(ptq); + if (err) + return err; + } + } + + if (pt->sample_instructions && (state->type & INTEL_PT_INSTRUCTION)) { err = intel_pt_synth_instruction_sample(ptq); if (err) return err; } - if (pt->sample_transactions && - (state->type & INTEL_PT_TRANSACTION) && - (!pt->synth_opts.initial_skip || - pt->num_events++ >= pt->synth_opts.initial_skip)) { + if (pt->sample_transactions && (state->type & INTEL_PT_TRANSACTION)) { err = intel_pt_synth_transaction_sample(ptq); if (err) return err; } + if (pt->sample_ptwrites && (state->type & INTEL_PT_PTW)) { + err = intel_pt_synth_ptwrite_sample(ptq); + if (err) + return err; + } + if (!(state->type & INTEL_PT_BRANCH)) return 0; @@ -1923,36 +2130,65 @@ static int intel_pt_event_synth(struct perf_tool *tool, NULL); } -static int intel_pt_synth_event(struct perf_session *session, +static int intel_pt_synth_event(struct perf_session *session, const char *name, struct perf_event_attr *attr, u64 id) { struct intel_pt_synth intel_pt_synth; + int err; + + pr_debug("Synthesizing '%s' event with id %" PRIu64 " sample type %#" PRIx64 "\n", + name, id, (u64)attr->sample_type); memset(&intel_pt_synth, 0, sizeof(struct intel_pt_synth)); intel_pt_synth.session = session; - return perf_event__synthesize_attr(&intel_pt_synth.dummy_tool, attr, 1, - &id, intel_pt_event_synth); + err = perf_event__synthesize_attr(&intel_pt_synth.dummy_tool, attr, 1, + &id, intel_pt_event_synth); + if (err) + pr_err("%s: failed to synthesize '%s' event type\n", + __func__, name); + + return err; } -static int intel_pt_synth_events(struct intel_pt *pt, - struct perf_session *session) +static void intel_pt_set_event_name(struct perf_evlist *evlist, u64 id, + const char *name) { - struct perf_evlist *evlist = session->evlist; struct perf_evsel *evsel; - struct perf_event_attr attr; - bool found = false; - u64 id; - int err; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == pt->pmu_type && evsel->ids) { - found = true; + if (evsel->id && evsel->id[0] == id) { + if (evsel->name) + zfree(&evsel->name); + evsel->name = strdup(name); break; } } +} + +static struct perf_evsel *intel_pt_evsel(struct intel_pt *pt, + struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->attr.type == pt->pmu_type && evsel->ids) + return evsel; + } + + return NULL; +} - if (!found) { +static int intel_pt_synth_events(struct intel_pt *pt, + struct perf_session *session) +{ + struct perf_evlist *evlist = session->evlist; + struct perf_evsel *evsel = intel_pt_evsel(pt, evlist); + struct perf_event_attr attr; + u64 id; + int err; + + if (!evsel) { pr_debug("There are no selected events with Intel Processor Trace data\n"); return 0; } @@ -1981,6 +2217,25 @@ static int intel_pt_synth_events(struct intel_pt *pt, if (!id) id = 1; + if (pt->synth_opts.branches) { + attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS; + attr.sample_period = 1; + attr.sample_type |= PERF_SAMPLE_ADDR; + err = intel_pt_synth_event(session, "branches", &attr, id); + if (err) + return err; + pt->sample_branches = true; + pt->branches_sample_type = attr.sample_type; + pt->branches_id = id; + id += 1; + attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR; + } + + if (pt->synth_opts.callchain) + attr.sample_type |= PERF_SAMPLE_CALLCHAIN; + if (pt->synth_opts.last_branch) + attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + if (pt->synth_opts.instructions) { attr.config = PERF_COUNT_HW_INSTRUCTIONS; if (pt->synth_opts.period_type == PERF_ITRACE_PERIOD_NANOSECS) @@ -1988,70 +2243,90 @@ static int intel_pt_synth_events(struct intel_pt *pt, intel_pt_ns_to_ticks(pt, pt->synth_opts.period); else attr.sample_period = pt->synth_opts.period; - pt->instructions_sample_period = attr.sample_period; - if (pt->synth_opts.callchain) - attr.sample_type |= PERF_SAMPLE_CALLCHAIN; - if (pt->synth_opts.last_branch) - attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; - pr_debug("Synthesizing 'instructions' event with id %" PRIu64 " sample type %#" PRIx64 "\n", - id, (u64)attr.sample_type); - err = intel_pt_synth_event(session, &attr, id); - if (err) { - pr_err("%s: failed to synthesize 'instructions' event type\n", - __func__); + err = intel_pt_synth_event(session, "instructions", &attr, id); + if (err) return err; - } pt->sample_instructions = true; pt->instructions_sample_type = attr.sample_type; pt->instructions_id = id; id += 1; } + attr.sample_type &= ~(u64)PERF_SAMPLE_PERIOD; + attr.sample_period = 1; + if (pt->synth_opts.transactions) { attr.config = PERF_COUNT_HW_INSTRUCTIONS; - attr.sample_period = 1; - if (pt->synth_opts.callchain) - attr.sample_type |= PERF_SAMPLE_CALLCHAIN; - if (pt->synth_opts.last_branch) - attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; - pr_debug("Synthesizing 'transactions' event with id %" PRIu64 " sample type %#" PRIx64 "\n", - id, (u64)attr.sample_type); - err = intel_pt_synth_event(session, &attr, id); - if (err) { - pr_err("%s: failed to synthesize 'transactions' event type\n", - __func__); + err = intel_pt_synth_event(session, "transactions", &attr, id); + if (err) return err; - } pt->sample_transactions = true; + pt->transactions_sample_type = attr.sample_type; pt->transactions_id = id; + intel_pt_set_event_name(evlist, id, "transactions"); id += 1; - evlist__for_each_entry(evlist, evsel) { - if (evsel->id && evsel->id[0] == pt->transactions_id) { - if (evsel->name) - zfree(&evsel->name); - evsel->name = strdup("transactions"); - break; - } - } } - if (pt->synth_opts.branches) { - attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS; - attr.sample_period = 1; - attr.sample_type |= PERF_SAMPLE_ADDR; - attr.sample_type &= ~(u64)PERF_SAMPLE_CALLCHAIN; - attr.sample_type &= ~(u64)PERF_SAMPLE_BRANCH_STACK; - pr_debug("Synthesizing 'branches' event with id %" PRIu64 " sample type %#" PRIx64 "\n", - id, (u64)attr.sample_type); - err = intel_pt_synth_event(session, &attr, id); - if (err) { - pr_err("%s: failed to synthesize 'branches' event type\n", - __func__); + attr.type = PERF_TYPE_SYNTH; + attr.sample_type |= PERF_SAMPLE_RAW; + + if (pt->synth_opts.ptwrites) { + attr.config = PERF_SYNTH_INTEL_PTWRITE; + err = intel_pt_synth_event(session, "ptwrite", &attr, id); + if (err) return err; - } - pt->sample_branches = true; - pt->branches_sample_type = attr.sample_type; - pt->branches_id = id; + pt->sample_ptwrites = true; + pt->ptwrites_sample_type = attr.sample_type; + pt->ptwrites_id = id; + intel_pt_set_event_name(evlist, id, "ptwrite"); + id += 1; + } + + if (pt->synth_opts.pwr_events) { + pt->sample_pwr_events = true; + pt->pwr_events_sample_type = attr.sample_type; + + attr.config = PERF_SYNTH_INTEL_CBR; + err = intel_pt_synth_event(session, "cbr", &attr, id); + if (err) + return err; + pt->cbr_id = id; + intel_pt_set_event_name(evlist, id, "cbr"); + id += 1; + } + + if (pt->synth_opts.pwr_events && (evsel->attr.config & 0x10)) { + attr.config = PERF_SYNTH_INTEL_MWAIT; + err = intel_pt_synth_event(session, "mwait", &attr, id); + if (err) + return err; + pt->mwait_id = id; + intel_pt_set_event_name(evlist, id, "mwait"); + id += 1; + + attr.config = PERF_SYNTH_INTEL_PWRE; + err = intel_pt_synth_event(session, "pwre", &attr, id); + if (err) + return err; + pt->pwre_id = id; + intel_pt_set_event_name(evlist, id, "pwre"); + id += 1; + + attr.config = PERF_SYNTH_INTEL_EXSTOP; + err = intel_pt_synth_event(session, "exstop", &attr, id); + if (err) + return err; + pt->exstop_id = id; + intel_pt_set_event_name(evlist, id, "exstop"); + id += 1; + + attr.config = PERF_SYNTH_INTEL_PWRX; + err = intel_pt_synth_event(session, "pwrx", &attr, id); + if (err) + return err; + pt->pwrx_id = id; + intel_pt_set_event_name(evlist, id, "pwrx"); + id += 1; } pt->synth_needs_swap = evsel->needs_swap; @@ -2159,7 +2434,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event, addr_filters__init(&pt->filts); - perf_config(intel_pt_perf_config, pt); + err = perf_config(intel_pt_perf_config, pt); + if (err) + goto err_free; err = auxtrace_queues__init(&pt->queues); if (err) @@ -2318,6 +2595,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event, intel_pt_log("TSC frequency %"PRIu64"\n", tsc_freq); intel_pt_log("Maximum non-turbo ratio %u\n", pt->max_non_turbo_ratio); + pt->cbr2khz = tsc_freq / pt->max_non_turbo_ratio / 1000; } if (pt->synth_opts.calls) diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index c9a941ef0f6d..9084930e1757 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -1,5 +1,6 @@ #include <sys/sysmacros.h> #include <sys/types.h> +#include <errno.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -9,13 +10,13 @@ #include <byteswap.h> #include <sys/stat.h> #include <sys/mman.h> +#include <linux/stringify.h> #include "util.h" #include "event.h" #include "debug.h" #include "evlist.h" #include "symbol.h" -#include "strlist.h" #include <elf.h> #include "tsc.h" @@ -25,6 +26,8 @@ #include "genelf.h" #include "../builtin.h" +#include "sane_ctype.h" + struct jit_buf_desc { struct perf_data_file *output; struct perf_session *session; @@ -181,7 +184,7 @@ jit_open(struct jit_buf_desc *jd, const char *name) jd->use_arch_timestamp); if (header.version > JITHEADER_VERSION) { - pr_err("wrong jitdump version %u, expected " STR(JITHEADER_VERSION), + pr_err("wrong jitdump version %u, expected " __stringify(JITHEADER_VERSION), header.version); goto error; } diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index b23ff44cf214..c6a15f204c03 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -12,6 +12,7 @@ #include "llvm-utils.h" #include "config.h" #include "util.h" +#include <sys/wait.h> #define CLANG_BPF_CMD_DEFAULT_TEMPLATE \ "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\ @@ -48,8 +49,10 @@ int perf_llvm_config(const char *var, const char *value) llvm_param.kbuild_opts = strdup(value); else if (!strcmp(var, "dump-obj")) llvm_param.dump_obj = !!perf_config_bool(var, value); - else + else { + pr_debug("Invalid LLVM config option: %s\n", value); return -1; + } llvm_param.user_set_param = true; return 0; } diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index 9ddea5cecd94..4ca7c5c6cdcd 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -1,6 +1,8 @@ +#include <errno.h> #include <lzma.h> #include <stdio.h> #include <linux/compiler.h> +#include "compress.h" #include "util.h" #include "debug.h" diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 9b33bef54581..2e9eb6aa3ce2 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1,3 +1,7 @@ +#include <dirent.h> +#include <errno.h> +#include <inttypes.h> +#include <regex.h> #include "callchain.h" #include "debug.h" #include "event.h" @@ -10,9 +14,15 @@ #include "thread.h" #include "vdso.h" #include <stdbool.h> -#include <symbol/kallsyms.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> #include "unwind.h" #include "linux/hash.h" +#include "asm/bug.h" + +#include "sane_ctype.h" +#include <symbol/kallsyms.h> static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock); @@ -87,6 +97,25 @@ out_delete: return NULL; } +struct machine *machine__new_kallsyms(void) +{ + struct machine *machine = machine__new_host(); + /* + * FIXME: + * 1) MAP__FUNCTION will go away when we stop loading separate maps for + * functions and data objects. + * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely + * ask for not using the kcore parsing code, once this one is fixed + * to create a map per module. + */ + if (machine && __machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION, true) <= 0) { + machine__delete(machine); + machine = NULL; + } + + return machine; +} + static void dsos__purge(struct dsos *dsos) { struct dso *pos, *n; @@ -482,6 +511,37 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event return err; } +int machine__process_namespaces_event(struct machine *machine __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused) +{ + struct thread *thread = machine__findnew_thread(machine, + event->namespaces.pid, + event->namespaces.tid); + int err = 0; + + WARN_ONCE(event->namespaces.nr_namespaces > NR_NAMESPACES, + "\nWARNING: kernel seems to support more namespaces than perf" + " tool.\nTry updating the perf tool..\n\n"); + + WARN_ONCE(event->namespaces.nr_namespaces < NR_NAMESPACES, + "\nWARNING: perf tool seems to support more namespaces than" + " the kernel.\nTry updating the kernel..\n\n"); + + if (dump_trace) + perf_event__fprintf_namespaces(event, stdout); + + if (thread == NULL || + thread__set_namespaces(thread, sample->time, &event->namespaces)) { + dump_printf("problem processing PERF_RECORD_NAMESPACES, skipping event.\n"); + err = -1; + } + + thread__put(thread); + + return err; +} + int machine__process_lost_event(struct machine *machine __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused) { @@ -512,16 +572,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine, if (dso == NULL) goto out_unlock; - if (machine__is_host(machine)) - dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; - else - dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; - - /* _KMODULE_COMP should be next to _KMODULE */ - if (m->kmod && m->comp) - dso->symtab_type++; - - dso__set_short_name(dso, strdup(m->name), true); + dso__set_module_info(dso, m, machine); dso__set_long_name(dso, strdup(filename), true); } @@ -736,11 +787,11 @@ const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL}; * Returns the name of the start symbol in *symbol_name. Pass in NULL as * symbol_name if it's not that important. */ -static u64 machine__get_running_kernel_start(struct machine *machine, - const char **symbol_name) +static int machine__get_running_kernel_start(struct machine *machine, + const char **symbol_name, u64 *start) { char filename[PATH_MAX]; - int i; + int i, err = -1; const char *name; u64 addr = 0; @@ -750,21 +801,28 @@ static u64 machine__get_running_kernel_start(struct machine *machine, return 0; for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { - addr = kallsyms__get_function_start(filename, name); - if (addr) + err = kallsyms__get_function_start(filename, name, &addr); + if (!err) break; } + if (err) + return -1; + if (symbol_name) *symbol_name = name; - return addr; + *start = addr; + return 0; } int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) { - enum map_type type; - u64 start = machine__get_running_kernel_start(machine, NULL); + int type; + u64 start = 0; + + if (machine__get_running_kernel_start(machine, NULL, &start)) + return -1; /* In case of renewal the kernel map, destroy previous one */ machine__destroy_kernel_maps(machine); @@ -794,7 +852,7 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) void machine__destroy_kernel_maps(struct machine *machine) { - enum map_type type; + int type; for (type = 0; type < MAP__NR_TYPES; ++type) { struct kmap *kmap; @@ -1125,8 +1183,8 @@ static int machine__create_modules(struct machine *machine) int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); - const char *name; - u64 addr; + const char *name = NULL; + u64 addr = 0; int ret; if (kernel == NULL) @@ -1151,11 +1209,12 @@ int machine__create_kernel_maps(struct machine *machine) */ map_groups__fixup_end(&machine->kmaps); - addr = machine__get_running_kernel_start(machine, &name); - if (!addr) { - } else if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) { - machine__destroy_kernel_maps(machine); - return -1; + if (!machine__get_running_kernel_start(machine, &name, &addr)) { + if (name && + maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) { + machine__destroy_kernel_maps(machine); + return -1; + } } return 0; @@ -1420,7 +1479,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th, if (machine->last_match == th) machine->last_match = NULL; - BUG_ON(atomic_read(&th->refcnt) == 0); + BUG_ON(refcount_read(&th->refcnt) == 0); if (lock) pthread_rwlock_wrlock(&machine->threads_lock); rb_erase_init(&th->rb_node, &machine->threads); @@ -1519,6 +1578,8 @@ int machine__process_event(struct machine *machine, union perf_event *event, ret = machine__process_comm_event(machine, event, sample); break; case PERF_RECORD_MMAP: ret = machine__process_mmap_event(machine, event, sample); break; + case PERF_RECORD_NAMESPACES: + ret = machine__process_namespaces_event(machine, event, sample); break; case PERF_RECORD_MMAP2: ret = machine__process_mmap2_event(machine, event, sample); break; case PERF_RECORD_FORK: @@ -1546,7 +1607,7 @@ int machine__process_event(struct machine *machine, union perf_event *event, static bool symbol__match_regex(struct symbol *sym, regex_t *regex) { - if (sym->name && !regexec(regex, sym->name, 0, NULL, 0)) + if (!regexec(regex, sym->name, 0, NULL, 0)) return 1; return 0; } @@ -2148,7 +2209,7 @@ int machine__get_kernel_start(struct machine *machine) machine->kernel_start = 1ULL << 63; if (map) { err = map__load(map); - if (map->start) + if (!err) machine->kernel_start = map->start; } return err; diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 354de6e56109..3cdb1340f917 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -97,6 +97,9 @@ int machine__process_itrace_start_event(struct machine *machine, union perf_event *event); int machine__process_switch_event(struct machine *machine, union perf_event *event); +int machine__process_namespaces_event(struct machine *machine, + 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, @@ -129,6 +132,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size); void machines__set_comm_exec(struct machines *machines, bool comm_exec); struct machine *machine__new_host(void); +struct machine *machine__new_kallsyms(void); int machine__init(struct machine *machine, const char *root_dir, pid_t pid); void machine__exit(struct machine *machine); void machine__delete_threads(struct machine *machine); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 4f9a71c63026..2179b2deb730 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -9,13 +9,13 @@ #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ #include "map.h" #include "thread.h" -#include "strlist.h" #include "vdso.h" #include "build-id.h" #include "util.h" #include "debug.h" #include "machine.h" #include <linux/string.h> +#include "srcline.h" #include "unwind.h" static void __maps__insert(struct maps *maps, struct map *map); @@ -141,7 +141,7 @@ void map__init(struct map *map, enum map_type type, RB_CLEAR_NODE(&map->rb_node); map->groups = NULL; map->erange_warned = false; - atomic_set(&map->refcnt, 1); + refcount_set(&map->refcnt, 1); } struct map *map__new(struct machine *machine, u64 start, u64 len, @@ -255,7 +255,7 @@ void map__delete(struct map *map) void map__put(struct map *map) { - if (map && atomic_dec_and_test(&map->refcnt)) + if (map && refcount_dec_and_test(&map->refcnt)) map__delete(map); } @@ -325,11 +325,6 @@ int map__load(struct map *map) return 0; } -int __weak arch__compare_symbol_names(const char *namea, const char *nameb) -{ - return strcmp(namea, nameb); -} - struct symbol *map__find_symbol(struct map *map, u64 addr) { if (map__load(map) < 0) @@ -354,7 +349,7 @@ struct map *map__clone(struct map *from) struct map *map = memdup(from, sizeof(*map)); if (map != NULL) { - atomic_set(&map->refcnt, 1); + refcount_set(&map->refcnt, 1); RB_CLEAR_NODE(&map->rb_node); dso__get(map->dso); map->groups = NULL; @@ -387,10 +382,10 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp) { const char *dsoname = "[unknown]"; - if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (map && map->dso) { if (symbol_conf.show_kernel_path && map->dso->long_name) dsoname = map->dso->long_name; - else if (map->dso->name) + else dsoname = map->dso->name; } @@ -405,7 +400,8 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, if (map && map->dso) { srcline = get_srcline(map->dso, - map__rip_2objdump(map, addr), NULL, true); + map__rip_2objdump(map, addr), NULL, + true, true); if (srcline != SRCLINE_UNKNOWN) ret = fprintf(fp, "%s%s", prefix, srcline); free_srcline(srcline); @@ -485,7 +481,7 @@ void map_groups__init(struct map_groups *mg, struct machine *machine) maps__init(&mg->maps[i]); } mg->machine = machine; - atomic_set(&mg->refcnt, 1); + refcount_set(&mg->refcnt, 1); } static void __maps__purge(struct maps *maps) @@ -547,7 +543,7 @@ void map_groups__delete(struct map_groups *mg) void map_groups__put(struct map_groups *mg) { - if (mg && atomic_dec_and_test(&mg->refcnt)) + if (mg && refcount_dec_and_test(&mg->refcnt)) map_groups__delete(mg); } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index abdacf800c98..f9e8ac8a52cd 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -1,7 +1,7 @@ #ifndef __PERF_MAP_H #define __PERF_MAP_H -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/compiler.h> #include <linux/list.h> #include <linux/rbtree.h> @@ -51,7 +51,7 @@ struct map { struct dso *dso; struct map_groups *groups; - atomic_t refcnt; + refcount_t refcnt; }; struct kmap { @@ -67,7 +67,7 @@ struct maps { struct map_groups { struct maps maps[MAP__NR_TYPES]; struct machine *machine; - atomic_t refcnt; + refcount_t refcnt; }; struct map_groups *map_groups__new(struct machine *machine); @@ -77,7 +77,7 @@ bool map_groups__empty(struct map_groups *mg); static inline struct map_groups *map_groups__get(struct map_groups *mg) { if (mg) - atomic_inc(&mg->refcnt); + refcount_inc(&mg->refcnt); return mg; } @@ -130,13 +130,14 @@ struct thread; */ #define __map__for_each_symbol_by_name(map, sym_name, pos) \ for (pos = map__find_symbol_by_name(map, sym_name); \ - pos && arch__compare_symbol_names(pos->name, sym_name) == 0; \ + pos && \ + !symbol__match_symbol_name(pos->name, sym_name, \ + SYMBOL_TAG_INCLUDE__DEFAULT_ONLY); \ pos = symbol__next_by_name(pos)) #define map__for_each_symbol_by_name(map, sym_name, pos) \ __map__for_each_symbol_by_name(map, sym_name, (pos)) -int arch__compare_symbol_names(const char *namea, const char *nameb); void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct machine *machine, u64 start, u64 len, @@ -150,7 +151,7 @@ struct map *map__clone(struct map *map); static inline struct map *map__get(struct map *map) { if (map) - atomic_inc(&map->refcnt); + refcount_inc(&map->refcnt); return map; } diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 1d4ab53c60ca..06f5a3a4295c 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -6,6 +6,7 @@ #include <sys/stat.h> #include <unistd.h> #include <api/fs/fs.h> +#include <linux/kernel.h> #include "mem-events.h" #include "debug.h" #include "symbol.h" @@ -205,8 +206,8 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) static const char * const snoop_access[] = { "N/A", "None", - "Miss", "Hit", + "Miss", "HitM", }; diff --git a/tools/perf/util/memswap.c b/tools/perf/util/memswap.c new file mode 100644 index 000000000000..55f7faa8d9ec --- /dev/null +++ b/tools/perf/util/memswap.c @@ -0,0 +1,24 @@ +#include <byteswap.h> +#include "memswap.h" +#include <linux/types.h> + +void mem_bswap_32(void *src, int byte_size) +{ + u32 *m = src; + while (byte_size > 0) { + *m = bswap_32(*m); + byte_size -= sizeof(u32); + ++m; + } +} + +void mem_bswap_64(void *src, int byte_size) +{ + u64 *m = src; + + while (byte_size > 0) { + *m = bswap_64(*m); + byte_size -= sizeof(u64); + ++m; + } +} diff --git a/tools/perf/util/memswap.h b/tools/perf/util/memswap.h new file mode 100644 index 000000000000..7d1b1c34bb57 --- /dev/null +++ b/tools/perf/util/memswap.h @@ -0,0 +1,7 @@ +#ifndef PERF_MEMSWAP_H_ +#define PERF_MEMSWAP_H_ + +void mem_bswap_64(void *src, int byte_size); +void mem_bswap_32(void *src, int byte_size); + +#endif /* PERF_MEMSWAP_H_ */ diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c new file mode 100644 index 000000000000..67dcbcc73c7d --- /dev/null +++ b/tools/perf/util/namespaces.c @@ -0,0 +1,37 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * Copyright (C) 2017 Hari Bathini, IBM Corporation + */ + +#include "namespaces.h" +#include "util.h" +#include "event.h" +#include <stdlib.h> +#include <stdio.h> +#include <string.h> + +struct namespaces *namespaces__new(struct namespaces_event *event) +{ + struct namespaces *namespaces; + u64 link_info_size = ((event ? event->nr_namespaces : NR_NAMESPACES) * + sizeof(struct perf_ns_link_info)); + + namespaces = zalloc(sizeof(struct namespaces) + link_info_size); + if (!namespaces) + return NULL; + + namespaces->end_time = -1; + + if (event) + memcpy(namespaces->link_info, event->link_info, link_info_size); + + return namespaces; +} + +void namespaces__free(struct namespaces *namespaces) +{ + free(namespaces); +} diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h new file mode 100644 index 000000000000..468f1e9a1484 --- /dev/null +++ b/tools/perf/util/namespaces.h @@ -0,0 +1,26 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * Copyright (C) 2017 Hari Bathini, IBM Corporation + */ + +#ifndef __PERF_NAMESPACES_H +#define __PERF_NAMESPACES_H + +#include "../perf.h" +#include <linux/list.h> + +struct namespaces_event; + +struct namespaces { + struct list_head list; + u64 end_time; + struct perf_ns_link_info link_info[]; +}; + +struct namespaces *namespaces__new(struct namespaces_event *event); +void namespaces__free(struct namespaces *namespaces); + +#endif /* __PERF_NAMESPACES_H */ diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index fe84df1875aa..4de398cfb577 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> #include <linux/list.h> #include <linux/compiler.h> #include <linux/string.h> @@ -79,7 +81,7 @@ static union perf_event *dup_event(struct ordered_events *oe, static void free_dup_event(struct ordered_events *oe, union perf_event *event) { - if (oe->copy_on_queue) { + if (event && oe->copy_on_queue) { oe->cur_alloc_size -= event->header.size; free(event); } @@ -150,6 +152,7 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve list_move(&event->list, &oe->cache); oe->nr_events--; free_dup_event(oe, event->event); + event->event = NULL; } int ordered_events__queue(struct ordered_events *oe, union perf_event *event, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 3c876b8ba4de..01e779b91c8e 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1,13 +1,18 @@ #include <linux/hw_breakpoint.h> #include <linux/err.h> -#include "util.h" +#include <dirent.h> +#include <errno.h> +#include <sys/ioctl.h> +#include <sys/param.h> +#include "term.h" #include "../perf.h" #include "evlist.h" #include "evsel.h" #include <subcmd/parse-options.h> #include "parse-events.h" #include <subcmd/exec-cmd.h> -#include "string.h" +#include "string2.h" +#include "strlist.h" #include "symbol.h" #include "cache.h" #include "header.h" @@ -211,6 +216,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) closedir(evt_dir); closedir(sys_dir); path = zalloc(sizeof(*path)); + if (!path) + return NULL; path->system = malloc(MAX_EVENT_LENGTH); if (!path->system) { free(path); @@ -252,8 +259,7 @@ struct tracepoint_path *tracepoint_name_to_path(const char *name) if (path->system == NULL || path->name == NULL) { zfree(&path->system); zfree(&path->name); - free(path); - path = NULL; + zfree(&path); } return path; @@ -310,12 +316,14 @@ __add_event(struct list_head *list, int *idx, event_attr_init(attr); - evsel = perf_evsel__new_idx(attr, (*idx)++); + evsel = perf_evsel__new_idx(attr, *idx); if (!evsel) return NULL; - evsel->cpus = cpu_map__get(cpus); - evsel->own_cpus = cpu_map__get(cpus); + (*idx)++; + evsel->cpus = cpu_map__get(cpus); + evsel->own_cpus = cpu_map__get(cpus); + evsel->system_wide = !!cpus; if (name) evsel->name = strdup(name); @@ -1252,11 +1260,59 @@ int parse_events_add_pmu(struct parse_events_evlist *data, evsel->scale = info.scale; evsel->per_pkg = info.per_pkg; evsel->snapshot = info.snapshot; + evsel->metric_expr = info.metric_expr; + evsel->metric_name = info.metric_name; } return evsel ? 0 : -ENOMEM; } +int parse_events_multi_pmu_add(struct parse_events_evlist *data, + char *str, struct list_head **listp) +{ + struct list_head *head; + struct parse_events_term *term; + struct list_head *list; + struct perf_pmu *pmu = NULL; + int ok = 0; + + *listp = NULL; + /* Add it for all PMUs that support the alias */ + list = malloc(sizeof(struct list_head)); + if (!list) + return -1; + INIT_LIST_HEAD(list); + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + struct perf_pmu_alias *alias; + + list_for_each_entry(alias, &pmu->aliases, list) { + if (!strcasecmp(alias->name, str)) { + head = malloc(sizeof(struct list_head)); + if (!head) + return -1; + INIT_LIST_HEAD(head); + if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + str, 1, false, &str, NULL) < 0) + return -1; + list_add_tail(&term->list, head); + + if (!parse_events_add_pmu(data, list, + pmu->name, head)) { + pr_debug("%s -> %s/%s/\n", str, + pmu->name, alias->str); + ok++; + } + + parse_events_terms__delete(head); + } + } + } + if (!ok) + return -1; + *listp = list; + return 0; +} + int parse_events__modifier_group(struct list_head *list, char *event_mod) { @@ -1477,10 +1533,9 @@ static void perf_pmu__parse_cleanup(void) for (i = 0; i < perf_pmu_events_list_num; i++) { p = perf_pmu_events_list + i; - free(p->symbol); + zfree(&p->symbol); } - free(perf_pmu_events_list); - perf_pmu_events_list = NULL; + zfree(&perf_pmu_events_list); perf_pmu_events_list_num = 0; } } @@ -1504,35 +1559,41 @@ static void perf_pmu__parse_init(void) struct perf_pmu_alias *alias; int len = 0; - pmu = perf_pmu__find("cpu"); - if ((pmu == NULL) || list_empty(&pmu->aliases)) { + pmu = NULL; + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + list_for_each_entry(alias, &pmu->aliases, list) { + if (strchr(alias->name, '-')) + len++; + len++; + } + } + + if (len == 0) { perf_pmu_events_list_num = -1; return; } - list_for_each_entry(alias, &pmu->aliases, list) { - if (strchr(alias->name, '-')) - len++; - len++; - } perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len); if (!perf_pmu_events_list) return; perf_pmu_events_list_num = len; len = 0; - list_for_each_entry(alias, &pmu->aliases, list) { - struct perf_pmu_event_symbol *p = perf_pmu_events_list + len; - char *tmp = strchr(alias->name, '-'); - - if (tmp != NULL) { - SET_SYMBOL(strndup(alias->name, tmp - alias->name), - PMU_EVENT_SYMBOL_PREFIX); - p++; - SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX); - len += 2; - } else { - SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL); - len++; + pmu = NULL; + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + list_for_each_entry(alias, &pmu->aliases, list) { + struct perf_pmu_event_symbol *p = perf_pmu_events_list + len; + char *tmp = strchr(alias->name, '-'); + + if (tmp != NULL) { + SET_SYMBOL(strndup(alias->name, tmp - alias->name), + PMU_EVENT_SYMBOL_PREFIX); + p++; + SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX); + len += 2; + } else { + SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL); + len++; + } } } qsort(perf_pmu_events_list, len, @@ -1563,7 +1624,7 @@ perf_pmu__parse_check(const char *name) r = bsearch(&p, perf_pmu_events_list, (size_t) perf_pmu_events_list_num, sizeof(struct perf_pmu_event_symbol), comp_pmu); - free(p.symbol); + zfree(&p.symbol); return r ? r->type : PMU_EVENT_SYMBOL_ERR; } @@ -1710,8 +1771,8 @@ static void parse_events_print_error(struct parse_events_error *err, fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str); if (err->help) fprintf(stderr, "\n%s\n", err->help); - free(err->str); - free(err->help); + zfree(&err->str); + zfree(&err->help); } fprintf(stderr, "Run 'perf list' for a list of valid events\n"); @@ -2013,17 +2074,14 @@ static bool is_event_supported(u8 type, unsigned config) .config = config, .disabled = 1, }; - struct { - struct thread_map map; - int threads[1]; - } tmap = { - .map.nr = 1, - .threads = { 0 }, - }; + struct thread_map *tmap = thread_map__new_by_tid(0); + + if (tmap == NULL) + return false; evsel = perf_evsel__new(&attr); if (evsel) { - open_return = perf_evsel__open(evsel, NULL, &tmap.map); + open_return = perf_evsel__open(evsel, NULL, tmap); ret = open_return >= 0; if (open_return == -EACCES) { @@ -2035,7 +2093,7 @@ static bool is_event_supported(u8 type, unsigned config) * */ evsel->attr.exclude_kernel = 1; - ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0; + ret = perf_evsel__open(evsel, NULL, tmap) >= 0; } perf_evsel__delete(evsel); } @@ -2272,7 +2330,7 @@ out_enomem: * Print the help text for the event symbols: */ void print_events(const char *event_glob, bool name_only, bool quiet_flag, - bool long_desc) + bool long_desc, bool details_flag) { print_symbol_events(event_glob, PERF_TYPE_HARDWARE, event_symbols_hw, PERF_COUNT_HW_MAX, name_only); @@ -2282,7 +2340,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag, print_hwcache_events(event_glob, name_only); - print_pmu_events(event_glob, name_only, quiet_flag, long_desc); + print_pmu_events(event_glob, name_only, quiet_flag, long_desc, + details_flag); if (event_glob != NULL) return; @@ -2314,24 +2373,20 @@ int parse_events__is_hardcoded_term(struct parse_events_term *term) return term->type_term != PARSE_EVENTS__TERM_TYPE_USER; } -static int new_term(struct parse_events_term **_term, int type_val, - int type_term, char *config, - char *str, u64 num, int err_term, int err_val) +static int new_term(struct parse_events_term **_term, + struct parse_events_term *temp, + char *str, u64 num) { struct parse_events_term *term; - term = zalloc(sizeof(*term)); + term = malloc(sizeof(*term)); if (!term) return -ENOMEM; + *term = *temp; INIT_LIST_HEAD(&term->list); - term->type_val = type_val; - term->type_term = type_term; - term->config = config; - term->err_term = err_term; - term->err_val = err_val; - switch (type_val) { + switch (term->type_val) { case PARSE_EVENTS__TERM_TYPE_NUM: term->val.num = num; break; @@ -2349,15 +2404,22 @@ static int new_term(struct parse_events_term **_term, int type_val, int parse_events_term__num(struct parse_events_term **term, int type_term, char *config, u64 num, + bool no_value, void *loc_term_, void *loc_val_) { YYLTYPE *loc_term = loc_term_; YYLTYPE *loc_val = loc_val_; - return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term, - config, NULL, num, - loc_term ? loc_term->first_column : 0, - loc_val ? loc_val->first_column : 0); + struct parse_events_term temp = { + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = type_term, + .config = config, + .no_value = no_value, + .err_term = loc_term ? loc_term->first_column : 0, + .err_val = loc_val ? loc_val->first_column : 0, + }; + + return new_term(term, &temp, NULL, num); } int parse_events_term__str(struct parse_events_term **term, @@ -2367,37 +2429,70 @@ int parse_events_term__str(struct parse_events_term **term, YYLTYPE *loc_term = loc_term_; YYLTYPE *loc_val = loc_val_; - return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term, - config, str, 0, - loc_term ? loc_term->first_column : 0, - loc_val ? loc_val->first_column : 0); + struct parse_events_term temp = { + .type_val = PARSE_EVENTS__TERM_TYPE_STR, + .type_term = type_term, + .config = config, + .err_term = loc_term ? loc_term->first_column : 0, + .err_val = loc_val ? loc_val->first_column : 0, + }; + + return new_term(term, &temp, str, 0); } int parse_events_term__sym_hw(struct parse_events_term **term, char *config, unsigned idx) { struct event_symbol *sym; + struct parse_events_term temp = { + .type_val = PARSE_EVENTS__TERM_TYPE_STR, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, + .config = config ?: (char *) "event", + }; BUG_ON(idx >= PERF_COUNT_HW_MAX); sym = &event_symbols_hw[idx]; - if (config) - return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, - PARSE_EVENTS__TERM_TYPE_USER, config, - (char *) sym->symbol, 0, 0, 0); - else - return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, - PARSE_EVENTS__TERM_TYPE_USER, - (char *) "event", (char *) sym->symbol, - 0, 0, 0); + return new_term(term, &temp, (char *) sym->symbol, 0); } int parse_events_term__clone(struct parse_events_term **new, struct parse_events_term *term) { - return new_term(new, term->type_val, term->type_term, term->config, - term->val.str, term->val.num, - term->err_term, term->err_val); + struct parse_events_term temp = { + .type_val = term->type_val, + .type_term = term->type_term, + .config = term->config, + .err_term = term->err_term, + .err_val = term->err_val, + }; + + return new_term(new, &temp, term->val.str, term->val.num); +} + +int parse_events_copy_term_list(struct list_head *old, + struct list_head **new) +{ + struct parse_events_term *term, *n; + int ret; + + if (!old) { + *new = NULL; + return 0; + } + + *new = malloc(sizeof(struct list_head)); + if (!*new) + return -ENOMEM; + INIT_LIST_HEAD(*new); + + list_for_each_entry (term, old, list) { + ret = parse_events_term__clone(&n, term); + if (ret) + return ret; + list_add_tail(&n->list, *new); + } + return 0; } void parse_events_terms__purge(struct list_head *terms) @@ -2406,7 +2501,7 @@ void parse_events_terms__purge(struct list_head *terms) list_for_each_entry_safe(term, h, terms, list) { if (term->array.nr_ranges) - free(term->array.ranges); + zfree(&term->array.ranges); list_del_init(&term->list); free(term); } @@ -2422,7 +2517,7 @@ void parse_events_terms__delete(struct list_head *terms) void parse_events__clear_array(struct parse_events_array *a) { - free(a->ranges); + zfree(&a->ranges); } void parse_events_evlist_error(struct parse_events_evlist *data, diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index da246a3ddb69..a235f4d6d5e5 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -8,6 +8,7 @@ #include <stdbool.h> #include <linux/types.h> #include <linux/perf_event.h> +#include <string.h> struct list_head; struct perf_evsel; @@ -94,6 +95,7 @@ struct parse_events_term { int type_term; struct list_head list; bool used; + bool no_value; /* error string indexes for within parsed string */ int err_term; @@ -122,6 +124,7 @@ void parse_events__shrink_config_terms(void); int parse_events__is_hardcoded_term(struct parse_events_term *term); int parse_events_term__num(struct parse_events_term **term, int type_term, char *config, u64 num, + bool novalue, void *loc_term, void *loc_val); int parse_events_term__str(struct parse_events_term **term, int type_term, char *config, char *str, @@ -164,6 +167,14 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, int parse_events_add_pmu(struct parse_events_evlist *data, struct list_head *list, char *name, struct list_head *head_config); + +int parse_events_multi_pmu_add(struct parse_events_evlist *data, + char *str, + struct list_head **listp); + +int parse_events_copy_term_list(struct list_head *old, + struct list_head **new); + enum perf_pmu_event_symbol_type perf_pmu__parse_check(const char *name); void parse_events__set_leader(char *name, struct list_head *list); @@ -173,7 +184,7 @@ void parse_events_evlist_error(struct parse_events_evlist *data, int idx, const char *str); void print_events(const char *event_glob, bool name_only, bool quiet, - bool long_desc); + bool long_desc, bool details_flag); struct event_symbol { const char *symbol; @@ -194,4 +205,23 @@ int is_valid_tracepoint(const char *event_string); int valid_event_mount(const char *eventfs); char *parse_events_formats_error_string(char *additional_terms); +#ifdef HAVE_LIBELF_SUPPORT +/* + * If the probe point starts with '%', + * or starts with "sdt_" and has a ':' but no '=', + * then it should be a SDT/cached probe point. + */ +static inline bool is_sdt_event(char *str) +{ + return (str[0] == '%' || + (!strncmp(str, "sdt_", 4) && + !!strchr(str, ':') && !strchr(str, '='))); +} +#else +static inline bool is_sdt_event(char *str __maybe_unused) +{ + return false; +} +#endif /* HAVE_LIBELF_SUPPORT */ + #endif /* __PERF_PARSE_EVENTS_H */ diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 879115f93edc..04fd8c9af9f9 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -12,9 +12,13 @@ #include <linux/list.h> #include <linux/types.h> #include "util.h" +#include "pmu.h" +#include "debug.h" #include "parse-events.h" #include "parse-events-bison.h" +void parse_events_error(YYLTYPE *loc, void *data, void *scanner, char const *msg); + #define ABORT_ON(val) \ do { \ if (val) \ @@ -222,49 +226,55 @@ event_pmu: PE_NAME opt_event_config { struct parse_events_evlist *data = _data; - struct list_head *list; + struct list_head *list, *orig_terms, *terms; + + if (parse_events_copy_term_list($2, &orig_terms)) + YYABORT; ALLOC_LIST(list); - ABORT_ON(parse_events_add_pmu(data, list, $1, $2)); + if (parse_events_add_pmu(data, list, $1, $2)) { + struct perf_pmu *pmu = NULL; + int ok = 0; + + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + char *name = pmu->name; + + if (!strncmp(name, "uncore_", 7) && + strncmp($1, "uncore_", 7)) + name += 7; + if (!strncmp($1, name, strlen($1))) { + if (parse_events_copy_term_list(orig_terms, &terms)) + YYABORT; + if (!parse_events_add_pmu(data, list, pmu->name, terms)) + ok++; + parse_events_terms__delete(terms); + } + } + if (!ok) + YYABORT; + } parse_events_terms__delete($2); + parse_events_terms__delete(orig_terms); $$ = list; } | PE_KERNEL_PMU_EVENT sep_dc { - struct parse_events_evlist *data = _data; - struct list_head *head; - struct parse_events_term *term; struct list_head *list; - ALLOC_LIST(head); - ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, 1, &@1, NULL)); - list_add_tail(&term->list, head); - - ALLOC_LIST(list); - ABORT_ON(parse_events_add_pmu(data, list, "cpu", head)); - parse_events_terms__delete(head); + if (parse_events_multi_pmu_add(_data, $1, &list) < 0) + YYABORT; $$ = list; } | PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc { - struct parse_events_evlist *data = _data; - struct list_head *head; - struct parse_events_term *term; struct list_head *list; char pmu_name[128]; - snprintf(&pmu_name, 128, "%s-%s", $1, $3); - - ALLOC_LIST(head); - ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - &pmu_name, 1, &@1, NULL)); - list_add_tail(&term->list, head); - ALLOC_LIST(list); - ABORT_ON(parse_events_add_pmu(data, list, "cpu", head)); - parse_events_terms__delete(head); + snprintf(&pmu_name, 128, "%s-%s", $1, $3); + if (parse_events_multi_pmu_add(_data, pmu_name, &list) < 0) + YYABORT; $$ = list; } @@ -525,7 +535,7 @@ PE_NAME '=' PE_VALUE struct parse_events_term *term; ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $3, &@1, &@3)); + $1, $3, false, &@1, &@3)); $$ = term; } | @@ -543,7 +553,7 @@ PE_NAME struct parse_events_term *term; ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, 1, &@1, NULL)); + $1, 1, true, &@1, NULL)); $$ = term; } | @@ -568,7 +578,7 @@ PE_TERM '=' PE_VALUE { struct parse_events_term *term; - ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, &@1, &@3)); + ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, false, &@1, &@3)); $$ = term; } | @@ -576,7 +586,7 @@ PE_TERM { struct parse_events_term *term; - ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL)); + ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, true, &@1, NULL)); $$ = term; } | @@ -597,7 +607,7 @@ PE_NAME array '=' PE_VALUE struct parse_events_term *term; ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $4, &@1, &@4)); + $1, $4, false, &@1, &@4)); term->array = $2; $$ = term; } diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index 7c7630be5a89..50ec3bc87a60 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -11,8 +11,13 @@ * which is what it's designed for. */ #include "cache.h" -#include "util.h" +#include "path.h" +#include <linux/kernel.h> #include <limits.h> +#include <stdio.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> static char bad_path[] = "/bad-path/"; /* @@ -50,3 +55,24 @@ char *mkpath(const char *fmt, ...) return bad_path; return cleanup_path(pathname); } + +int path__join(char *bf, size_t size, const char *path1, const char *path2) +{ + return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2); +} + +int path__join3(char *bf, size_t size, const char *path1, const char *path2, const char *path3) +{ + return scnprintf(bf, size, "%s%s%s%s%s", path1, path1[0] ? "/" : "", + path2, path2[0] ? "/" : "", path3); +} + +bool is_regular_file(const char *file) +{ + struct stat st; + + if (stat(file, &st)) + return false; + + return S_ISREG(st.st_mode); +} diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h new file mode 100644 index 000000000000..9a276a58e3c2 --- /dev/null +++ b/tools/perf/util/path.h @@ -0,0 +1,9 @@ +#ifndef _PERF_PATH_H +#define _PERF_PATH_H + +int path__join(char *bf, size_t size, const char *path1, const char *path2); +int path__join3(char *bf, size_t size, const char *path1, const char *path2, const char *path3); + +bool is_regular_file(const char *file); + +#endif /* _PERF_PATH_H */ diff --git a/tools/perf/util/perf-hooks.c b/tools/perf/util/perf-hooks.c index cb368306b12b..d55092964da2 100644 --- a/tools/perf/util/perf-hooks.c +++ b/tools/perf/util/perf-hooks.c @@ -9,6 +9,7 @@ #include <stdlib.h> #include <setjmp.h> #include <linux/err.h> +#include <linux/kernel.h> #include "util/util.h" #include "util/debug.h" #include "util/perf-hooks.h" diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index c4023f22f287..b2ae039eff85 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -6,6 +6,12 @@ const struct sample_reg __weak sample_reg_masks[] = { SMPL_REG_END }; +int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused, + char **new_op __maybe_unused) +{ + return SDT_ARG_SKIP; +} + #ifdef HAVE_PERF_REGS_SUPPORT int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) { diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index 679d6e493962..32b37d19dcc3 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -15,6 +15,13 @@ struct sample_reg { extern const struct sample_reg sample_reg_masks[]; +enum { + SDT_ARG_VALID = 0, + SDT_ARG_SKIP, +}; + +int arch_sdt_arg_parse_op(char *old_op, char **new_op); + #ifdef HAVE_PERF_REGS_SUPPORT #include <perf_regs.h> diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index dc6ccaa4e927..ac16a9db1fb5 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1,6 +1,8 @@ #include <linux/list.h> #include <linux/compiler.h> #include <sys/types.h> +#include <errno.h> +#include <sys/stat.h> #include <unistd.h> #include <stdio.h> #include <stdbool.h> @@ -15,6 +17,7 @@ #include "header.h" #include "pmu-events/pmu-events.h" #include "cache.h" +#include "string2.h" struct perf_pmu_format { char *name; @@ -94,32 +97,10 @@ static int pmu_format(const char *name, struct list_head *format) return 0; } -static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name) +static int convert_scale(const char *scale, char **end, double *sval) { - struct stat st; - ssize_t sret; - char scale[128]; - int fd, ret = -1; - char path[PATH_MAX]; char *lc; - - snprintf(path, PATH_MAX, "%s/%s.scale", dir, name); - - fd = open(path, O_RDONLY); - if (fd == -1) - return -1; - - if (fstat(fd, &st) < 0) - goto error; - - sret = read(fd, scale, sizeof(scale)-1); - if (sret < 0) - goto error; - - if (scale[sret - 1] == '\n') - scale[sret - 1] = '\0'; - else - scale[sret] = '\0'; + int ret = 0; /* * save current locale @@ -134,7 +115,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * lc = strdup(lc); if (!lc) { ret = -ENOMEM; - goto error; + goto out; } /* @@ -144,14 +125,42 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * */ setlocale(LC_NUMERIC, "C"); - alias->scale = strtod(scale, NULL); + *sval = strtod(scale, end); +out: /* restore locale */ setlocale(LC_NUMERIC, lc); - free(lc); + return ret; +} - ret = 0; +static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name) +{ + struct stat st; + ssize_t sret; + char scale[128]; + int fd, ret = -1; + char path[PATH_MAX]; + + snprintf(path, PATH_MAX, "%s/%s.scale", dir, name); + + fd = open(path, O_RDONLY); + if (fd == -1) + return -1; + + if (fstat(fd, &st) < 0) + goto error; + + sret = read(fd, scale, sizeof(scale)-1); + if (sret < 0) + goto error; + + if (scale[sret - 1] == '\n') + scale[sret - 1] = '\0'; + else + scale[sret] = '\0'; + + ret = convert_scale(scale, NULL, &alias->scale); error: close(fd); return ret; @@ -223,11 +232,15 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias, } static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, - char *desc, char *val, char *long_desc, - char *topic) + char *desc, char *val, + char *long_desc, char *topic, + char *unit, char *perpkg, + char *metric_expr, + char *metric_name) { struct perf_pmu_alias *alias; int ret; + int num; alias = malloc(sizeof(*alias)); if (!alias) @@ -257,10 +270,19 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, perf_pmu__parse_snapshot(alias, dir, name); } + alias->metric_expr = metric_expr ? strdup(metric_expr) : NULL; + alias->metric_name = metric_name ? strdup(metric_name): NULL; alias->desc = desc ? strdup(desc) : NULL; alias->long_desc = long_desc ? strdup(long_desc) : desc ? strdup(desc) : NULL; alias->topic = topic ? strdup(topic) : NULL; + if (unit) { + if (convert_scale(unit, &unit, &alias->scale) < 0) + return -1; + snprintf(alias->unit, sizeof(alias->unit), "%s", unit); + } + alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1; + alias->str = strdup(val); list_add_tail(&alias->list, list); @@ -278,7 +300,8 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI buf[ret] = 0; - return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL); + return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL, + NULL, NULL, NULL); } static inline bool pmu_alias_info_file(char *name) @@ -498,7 +521,7 @@ char * __weak get_cpuid_str(void) * to the current running CPU. Then, add all PMU events from that table * as aliases. */ -static void pmu_add_cpu_aliases(struct list_head *head) +static void pmu_add_cpu_aliases(struct list_head *head, const char *name) { int i; struct pmu_events_map *map; @@ -534,14 +557,23 @@ static void pmu_add_cpu_aliases(struct list_head *head) */ i = 0; while (1) { + const char *pname; + pe = &map->table[i++]; if (!pe->name) break; + pname = pe->pmu ? pe->pmu : "cpu"; + if (strncmp(pname, name, strlen(pname))) + continue; + /* need type casts to override 'const' */ __perf_pmu__new_alias(head, NULL, (char *)pe->name, (char *)pe->desc, (char *)pe->event, - (char *)pe->long_desc, (char *)pe->topic); + (char *)pe->long_desc, (char *)pe->topic, + (char *)pe->unit, (char *)pe->perpkg, + (char *)pe->metric_expr, + (char *)pe->metric_name); } out: @@ -569,15 +601,16 @@ static struct perf_pmu *pmu_lookup(const char *name) if (pmu_format(name, &format)) return NULL; - if (pmu_aliases(name, &aliases)) + /* + * Check the type first to avoid unnecessary work. + */ + if (pmu_type(name, &type)) return NULL; - if (!strcmp(name, "cpu")) - pmu_add_cpu_aliases(&aliases); - - if (pmu_type(name, &type)) + if (pmu_aliases(name, &aliases)) return NULL; + pmu_add_cpu_aliases(&aliases, name); pmu = zalloc(sizeof(*pmu)); if (!pmu) return NULL; @@ -721,7 +754,7 @@ static int pmu_resolve_param_term(struct parse_events_term *term, } } - if (verbose) + if (verbose > 0) printf("Required parameter '%s' not specified\n", term->config); return -1; @@ -779,7 +812,7 @@ static int pmu_config_term(struct list_head *formats, format = pmu_find_format(formats, term->config); if (!format) { - if (verbose) + if (verbose > 0) printf("Invalid event/parameter '%s'\n", term->config); if (err) { char *pmu_term = pmu_formats_string(formats); @@ -810,11 +843,20 @@ static int pmu_config_term(struct list_head *formats, * Either directly use a numeric term, or try to translate string terms * using event parameters. */ - if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { + if (term->no_value && + bitmap_weight(format->bits, PERF_PMU_FORMAT_BITS) > 1) { + if (err) { + err->idx = term->err_val; + err->str = strdup("no value assigned for term"); + } + return -EINVAL; + } + val = term->val.num; - else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) { + } else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) { if (strcmp(term->val.str, "?")) { - if (verbose) { + if (verbose > 0) { pr_info("Invalid sysfs entry %s=%s\n", term->config, term->val.str); } @@ -921,12 +963,12 @@ static int check_info_data(struct perf_pmu_alias *alias, * define unit, scale and snapshot, fail * if there's more than one. */ - if ((info->unit && alias->unit) || + if ((info->unit && alias->unit[0]) || (info->scale && alias->scale) || (info->snapshot && alias->snapshot)) return -EINVAL; - if (alias->unit) + if (alias->unit[0]) info->unit = alias->unit; if (alias->scale) @@ -958,6 +1000,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, info->unit = NULL; info->scale = 0.0; info->snapshot = false; + info->metric_expr = NULL; + info->metric_name = NULL; list_for_each_entry_safe(term, h, head_terms, list) { alias = pmu_find_alias(pmu, term); @@ -973,6 +1017,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, if (alias->per_pkg) info->per_pkg = true; + info->metric_expr = alias->metric_expr; + info->metric_name = alias->metric_name; list_del(&term->list); free(term); @@ -1065,6 +1111,10 @@ struct sevent { char *name; char *desc; char *topic; + char *str; + char *pmu; + char *metric_expr; + char *metric_name; }; static int cmp_sevent(const void *a, const void *b) @@ -1101,13 +1151,12 @@ static void wordwrap(char *s, int start, int max, int corr) break; s += wlen; column += n; - while (isspace(*s)) - s++; + s = ltrim(s); } } void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, - bool long_desc) + bool long_desc, bool details_flag) { struct perf_pmu *pmu; struct perf_pmu_alias *alias; @@ -1161,6 +1210,10 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, aliases[j].desc = long_desc ? alias->long_desc : alias->desc; aliases[j].topic = alias->topic; + aliases[j].str = alias->str; + aliases[j].pmu = pmu->name; + aliases[j].metric_expr = alias->metric_expr; + aliases[j].metric_name = alias->metric_name; j++; } if (pmu->selectable && @@ -1175,6 +1228,9 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, len = j; qsort(aliases, len, sizeof(struct sevent), cmp_sevent); for (j = 0; j < len; j++) { + /* Skip duplicates */ + if (j > 0 && !strcmp(aliases[j].name, aliases[j - 1].name)) + continue; if (name_only) { printf("%s ", aliases[j].name); continue; @@ -1192,6 +1248,14 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, printf("%*s", 8, "["); wordwrap(aliases[j].desc, 8, columns, 0); printf("]\n"); + if (details_flag) { + printf("%*s%s/%s/ ", 8, "", aliases[j].pmu, aliases[j].str); + if (aliases[j].metric_name) + printf(" MetricName: %s", aliases[j].metric_name); + if (aliases[j].metric_expr) + printf(" MetricExpr: %s", aliases[j].metric_expr); + putchar('\n'); + } } else printf(" %-50s [Kernel PMU event]\n", aliases[j].name); printed++; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 25712034c815..389e9729331f 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -2,6 +2,7 @@ #define __PMU_H #include <linux/bitmap.h> +#include <linux/compiler.h> #include <linux/perf_event.h> #include <stdbool.h> #include "evsel.h" @@ -31,6 +32,8 @@ struct perf_pmu { struct perf_pmu_info { const char *unit; + const char *metric_expr; + const char *metric_name; double scale; bool per_pkg; bool snapshot; @@ -43,12 +46,15 @@ struct perf_pmu_alias { char *desc; char *long_desc; char *topic; + char *str; struct list_head terms; /* HEAD struct parse_events_term -> list */ struct list_head list; /* ELEM */ char unit[UNIT_MAX_LEN+1]; double scale; bool per_pkg; bool snapshot; + char *metric_expr; + char *metric_name; }; struct perf_pmu *perf_pmu__find(const char *name); @@ -75,11 +81,10 @@ 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 quiet, - bool long_desc); + bool long_desc, bool details_flag); bool pmu_have_event(const char *pname, const char *name); -int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, - ...) __attribute__((format(scanf, 3, 4))); +int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4); int perf_pmu__test(void); diff --git a/tools/perf/util/print_binary.c b/tools/perf/util/print_binary.c new file mode 100644 index 000000000000..e908177b9976 --- /dev/null +++ b/tools/perf/util/print_binary.c @@ -0,0 +1,55 @@ +#include "print_binary.h" +#include <linux/log2.h> +#include "sane_ctype.h" + +void print_binary(unsigned char *data, size_t len, + size_t bytes_per_line, print_binary_t printer, + void *extra) +{ + size_t i, j, mask; + + if (!printer) + return; + + bytes_per_line = roundup_pow_of_two(bytes_per_line); + mask = bytes_per_line - 1; + + printer(BINARY_PRINT_DATA_BEGIN, 0, extra); + for (i = 0; i < len; i++) { + if ((i & mask) == 0) { + printer(BINARY_PRINT_LINE_BEGIN, -1, extra); + printer(BINARY_PRINT_ADDR, i, extra); + } + + printer(BINARY_PRINT_NUM_DATA, data[i], extra); + + if (((i & mask) == mask) || i == len - 1) { + for (j = 0; j < mask-(i & mask); j++) + printer(BINARY_PRINT_NUM_PAD, -1, extra); + + printer(BINARY_PRINT_SEP, i, extra); + for (j = i & ~mask; j <= i; j++) + printer(BINARY_PRINT_CHAR_DATA, data[j], extra); + for (j = 0; j < mask-(i & mask); j++) + printer(BINARY_PRINT_CHAR_PAD, i, extra); + printer(BINARY_PRINT_LINE_END, -1, extra); + } + } + printer(BINARY_PRINT_DATA_END, -1, extra); +} + +int is_printable_array(char *p, unsigned int len) +{ + unsigned int i; + + if (!p || !len || p[len - 1] != 0) + return 0; + + len--; + + for (i = 0; i < len; i++) { + if (!isprint(p[i]) && !isspace(p[i])) + return 0; + } + return 1; +} diff --git a/tools/perf/util/print_binary.h b/tools/perf/util/print_binary.h new file mode 100644 index 000000000000..da0427263d2d --- /dev/null +++ b/tools/perf/util/print_binary.h @@ -0,0 +1,28 @@ +#ifndef PERF_PRINT_BINARY_H +#define PERF_PRINT_BINARY_H + +#include <stddef.h> + +enum binary_printer_ops { + BINARY_PRINT_DATA_BEGIN, + BINARY_PRINT_LINE_BEGIN, + BINARY_PRINT_ADDR, + BINARY_PRINT_NUM_DATA, + BINARY_PRINT_NUM_PAD, + BINARY_PRINT_SEP, + BINARY_PRINT_CHAR_DATA, + BINARY_PRINT_CHAR_PAD, + BINARY_PRINT_LINE_END, + BINARY_PRINT_DATA_END, +}; + +typedef void (*print_binary_t)(enum binary_printer_ops op, + unsigned int val, void *extra); + +void print_binary(unsigned char *data, size_t len, + size_t bytes_per_line, print_binary_t printer, + void *extra); + +int is_printable_array(char *p, unsigned int len); + +#endif /* PERF_PRINT_BINARY_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 6a6f44dd594b..a2670e9d652d 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -19,6 +19,7 @@ * */ +#include <inttypes.h> #include <sys/utsname.h> #include <sys/types.h> #include <sys/stat.h> @@ -35,6 +36,7 @@ #include "util.h" #include "event.h" #include "strlist.h" +#include "strfilter.h" #include "debug.h" #include "cache.h" #include "color.h" @@ -46,8 +48,10 @@ #include "probe-finder.h" #include "probe-file.h" #include "session.h" +#include "string2.h" + +#include "sane_ctype.h" -#define MAX_CMDLEN 256 #define PERFPROBE_GROUP "probe" bool probe_event_dry_run; /* Dry run flag */ @@ -594,7 +598,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, pr_debug("try to find information at %" PRIx64 " in %s\n", addr, tp->module ? : "kernel"); - dinfo = debuginfo_cache__open(tp->module, verbose == 0); + dinfo = debuginfo_cache__open(tp->module, verbose <= 0); if (dinfo) ret = debuginfo__find_probe_point(dinfo, (unsigned long)addr, pp); @@ -615,7 +619,7 @@ static int post_process_probe_trace_point(struct probe_trace_point *tp, struct map *map, unsigned long offs) { struct symbol *sym; - u64 addr = tp->address + tp->offset - offs; + u64 addr = tp->address - offs; sym = map__find_symbol(map, addr); if (!sym) @@ -757,7 +761,9 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, } for (i = 0; i < ntevs; i++) { - if (!tevs[i].point.address || tevs[i].point.retprobe) + if (!tevs[i].point.address) + continue; + if (tevs[i].point.retprobe && !kretprobe_offset_is_supported()) continue; /* If we found a wrong one, mark it by NULL symbol */ if (kprobe_warn_out_range(tevs[i].point.symbol, @@ -1339,14 +1345,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) if (!arg) return -EINVAL; - /* - * If the probe point starts with '%', - * or starts with "sdt_" and has a ':' but no '=', - * then it should be a SDT/cached probe point. - */ - if (arg[0] == '%' || - (!strncmp(arg, "sdt_", 4) && - !!strchr(arg, ':') && !strchr(arg, '='))) { + if (is_sdt_event(arg)) { pev->sdt = true; if (arg[0] == '%') arg++; @@ -1528,11 +1527,6 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) return -EINVAL; } - if (pp->retprobe && !pp->function) { - semantic_error("Return probe requires an entry function.\n"); - return -EINVAL; - } - if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) { semantic_error("Offset/Line/Lazy pattern can't be used with " "return probe.\n"); @@ -2061,7 +2055,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp, bool is_kprobe) { struct symbol *sym = NULL; - struct map *map; + struct map *map = NULL; u64 addr = tp->address; int ret = -ENOENT; @@ -2841,7 +2835,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } /* Note that the symbols in the kmodule are not relocated */ - if (!pev->uprobes && !pp->retprobe && !pev->target) { + if (!pev->uprobes && !pev->target && + (!pp->retprobe || kretprobe_offset_is_supported())) { reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); @@ -3023,20 +3018,17 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev, tev->nargs = pev->nargs; tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); - if (!tev->args) { - err = -ENOMEM; + if (!tev->args) goto errout; - } + for (i = 0; i < tev->nargs; i++) copy_to_probe_trace_arg(&tev->args[i], &pev->args[i]); return 1; errout: - if (*tevs) { - clear_probe_trace_events(*tevs, 1); - *tevs = NULL; - } + clear_probe_trace_events(*tevs, 1); + *tevs = NULL; return err; } @@ -3060,7 +3052,7 @@ concat_probe_trace_events(struct probe_trace_event **tevs, int *ntevs, struct probe_trace_event *new_tevs; int ret = 0; - if (ntevs == 0) { + if (*ntevs == 0) { *tevs = *tevs2; *ntevs = ntevs2; *tevs2 = NULL; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 5d4e94061402..5812947418dd 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -1,10 +1,9 @@ #ifndef _PROBE_EVENT_H #define _PROBE_EVENT_H +#include <linux/compiler.h> #include <stdbool.h> #include "intlist.h" -#include "strlist.h" -#include "strfilter.h" /* Probe related configurations */ struct probe_conf { @@ -107,6 +106,8 @@ struct line_range { struct intlist *line_list; /* Visible lines */ }; +struct strlist; + /* List of variables */ struct variable_list { struct probe_trace_point point; /* Actual probepoint */ @@ -153,6 +154,9 @@ int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs); int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs); int show_probe_trace_events(struct perf_probe_event *pevs, int npevs); void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs); + +struct strfilter; + int del_perf_probe_events(struct strfilter *filter); int show_perf_probe_event(const char *group, const char *event, @@ -168,8 +172,7 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev, struct symbol *sym); /* If there is no space to write, returns -E2BIG. */ -int e_snprintf(char *str, size_t size, const char *format, ...) - __attribute__((format(printf, 3, 4))); +int e_snprintf(char *str, size_t size, const char *format, ...) __printf(3, 4); /* Maximum index number of event-name postfix */ #define MAX_EVENT_INDEX 1024 diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 436b64731f65..d679389e627c 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -14,10 +14,15 @@ * GNU General Public License for more details. * */ +#include <errno.h> +#include <sys/stat.h> +#include <sys/types.h> #include <sys/uio.h> +#include <unistd.h> #include "util.h" #include "event.h" #include "strlist.h" +#include "strfilter.h" #include "debug.h" #include "cache.h" #include "color.h" @@ -27,8 +32,11 @@ #include "probe-event.h" #include "probe-file.h" #include "session.h" +#include "perf_regs.h" +#include "string2.h" -#define MAX_CMDLEN 256 +/* 4096 - 2 ('\n' + '\0') */ +#define MAX_CMDLEN 4094 static void print_open_warning(int err, bool uprobe) { @@ -70,7 +78,7 @@ static void print_both_open_warning(int kerr, int uerr) } } -static int open_probe_events(const char *trace_file, bool readwrite) +int open_trace_file(const char *trace_file, bool readwrite) { char buf[PATH_MAX]; int ret; @@ -92,12 +100,12 @@ static int open_probe_events(const char *trace_file, bool readwrite) static int open_kprobe_events(bool readwrite) { - return open_probe_events("kprobe_events", readwrite); + return open_trace_file("kprobe_events", readwrite); } static int open_uprobe_events(bool readwrite) { - return open_probe_events("uprobe_events", readwrite); + return open_trace_file("uprobe_events", readwrite); } int probe_file__open(int flag) @@ -687,6 +695,110 @@ static unsigned long long sdt_note__get_addr(struct sdt_note *note) : (unsigned long long)note->addr.a64[0]; } +static const char * const type_to_suffix[] = { + ":s64", "", "", "", ":s32", "", ":s16", ":s8", + "", ":u8", ":u16", "", ":u32", "", "", "", ":u64" +}; + +/* + * Isolate the string number and convert it into a decimal value; + * this will be an index to get suffix of the uprobe name (defining + * the type) + */ +static int sdt_arg_parse_size(char *n_ptr, const char **suffix) +{ + long type_idx; + + type_idx = strtol(n_ptr, NULL, 10); + if (type_idx < -8 || type_idx > 8) { + pr_debug4("Failed to get a valid sdt type\n"); + return -1; + } + + *suffix = type_to_suffix[type_idx + 8]; + return 0; +} + +static int synthesize_sdt_probe_arg(struct strbuf *buf, int i, const char *arg) +{ + char *op, *desc = strdup(arg), *new_op = NULL; + const char *suffix = ""; + int ret = -1; + + if (desc == NULL) { + pr_debug4("Allocation error\n"); + return ret; + } + + /* + * Argument is in N@OP format. N is size of the argument and OP is + * the actual assembly operand. N can be omitted; in that case + * argument is just OP(without @). + */ + op = strchr(desc, '@'); + if (op) { + op[0] = '\0'; + op++; + + if (sdt_arg_parse_size(desc, &suffix)) + goto error; + } else { + op = desc; + } + + ret = arch_sdt_arg_parse_op(op, &new_op); + + if (ret < 0) + goto error; + + if (ret == SDT_ARG_VALID) { + ret = strbuf_addf(buf, " arg%d=%s%s", i + 1, new_op, suffix); + if (ret < 0) + goto error; + } + + ret = 0; +error: + free(desc); + free(new_op); + return ret; +} + +static char *synthesize_sdt_probe_command(struct sdt_note *note, + const char *pathname, + const char *sdtgrp) +{ + struct strbuf buf; + char *ret = NULL, **args; + int i, args_count; + + if (strbuf_init(&buf, 32) < 0) + return NULL; + + if (strbuf_addf(&buf, "p:%s/%s %s:0x%llx", + sdtgrp, note->name, pathname, + sdt_note__get_addr(note)) < 0) + goto error; + + if (!note->args) + goto out; + + if (note->args) { + args = argv_split(note->args, &args_count); + + for (i = 0; i < args_count; ++i) { + if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0) + goto error; + } + } + +out: + ret = strbuf_detach(&buf, NULL); +error: + strbuf_release(&buf); + return ret; +} + int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname) { struct probe_cache_entry *entry = NULL; @@ -723,11 +835,12 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname) entry->pev.group = strdup(sdtgrp); list_add_tail(&entry->node, &pcache->entries); } - ret = asprintf(&buf, "p:%s/%s %s:0x%llx", - sdtgrp, note->name, pathname, - sdt_note__get_addr(note)); - if (ret < 0) + buf = synthesize_sdt_probe_command(note, pathname, sdtgrp); + if (!buf) { + ret = -ENOMEM; break; + } + strlist__add(entry->tevlist, buf); free(buf); entry = NULL; @@ -877,59 +990,72 @@ int probe_cache__show_all_caches(struct strfilter *filter) return 0; } +enum ftrace_readme { + FTRACE_README_PROBE_TYPE_X = 0, + FTRACE_README_KRETPROBE_OFFSET, + FTRACE_README_END, +}; + static struct { const char *pattern; - bool avail; - bool checked; -} probe_type_table[] = { -#define DEFINE_TYPE(idx, pat, def_avail) \ - [idx] = {.pattern = pat, .avail = (def_avail)} - DEFINE_TYPE(PROBE_TYPE_U, "* u8/16/32/64,*", true), - DEFINE_TYPE(PROBE_TYPE_S, "* s8/16/32/64,*", true), - DEFINE_TYPE(PROBE_TYPE_X, "* x8/16/32/64,*", false), - DEFINE_TYPE(PROBE_TYPE_STRING, "* string,*", true), - DEFINE_TYPE(PROBE_TYPE_BITFIELD, - "* b<bit-width>@<bit-offset>/<container-size>", true), + bool avail; +} ftrace_readme_table[] = { +#define DEFINE_TYPE(idx, pat) \ + [idx] = {.pattern = pat, .avail = false} + DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"), + DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"), }; -bool probe_type_is_available(enum probe_type type) +static bool scan_ftrace_readme(enum ftrace_readme type) { + int fd; FILE *fp; char *buf = NULL; size_t len = 0; - bool target_line = false; - bool ret = probe_type_table[type].avail; + bool ret = false; + static bool scanned = false; - if (type >= PROBE_TYPE_END) - return false; - /* We don't have to check the type which supported by default */ - if (ret || probe_type_table[type].checked) - return ret; + if (scanned) + goto result; - if (asprintf(&buf, "%s/README", tracing_path) < 0) + fd = open_trace_file("README", false); + if (fd < 0) return ret; - fp = fopen(buf, "r"); - if (!fp) - goto end; - - zfree(&buf); - while (getline(&buf, &len, fp) > 0 && !ret) { - if (!target_line) { - target_line = !!strstr(buf, " type: "); - if (!target_line) - continue; - } else if (strstr(buf, "\t ") != buf) - break; - ret = strglobmatch(buf, probe_type_table[type].pattern); + fp = fdopen(fd, "r"); + if (!fp) { + close(fd); + return ret; } - /* Cache the result */ - probe_type_table[type].checked = true; - probe_type_table[type].avail = ret; + + while (getline(&buf, &len, fp) > 0) + for (enum ftrace_readme i = 0; i < FTRACE_README_END; i++) + if (!ftrace_readme_table[i].avail) + ftrace_readme_table[i].avail = + strglobmatch(buf, ftrace_readme_table[i].pattern); + scanned = true; fclose(fp); -end: free(buf); - return ret; +result: + if (type >= FTRACE_README_END) + return false; + + return ftrace_readme_table[type].avail; +} + +bool probe_type_is_available(enum probe_type type) +{ + if (type >= PROBE_TYPE_END) + return false; + else if (type == PROBE_TYPE_X) + return scan_ftrace_readme(FTRACE_README_PROBE_TYPE_X); + + return true; +} + +bool kretprobe_offset_is_supported(void) +{ + return scan_ftrace_readme(FTRACE_README_KRETPROBE_OFFSET); } diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index eba44c3e9dca..5ecc9d3925db 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -1,10 +1,11 @@ #ifndef __PROBE_FILE_H #define __PROBE_FILE_H -#include "strlist.h" -#include "strfilter.h" #include "probe-event.h" +struct strlist; +struct strfilter; + /* Cache of probe definitions */ struct probe_cache_entry { struct list_head node; @@ -35,11 +36,13 @@ enum probe_type { /* probe-file.c depends on libelf */ #ifdef HAVE_LIBELF_SUPPORT +int open_trace_file(const char *trace_file, bool readwrite); int probe_file__open(int flag); int probe_file__open_both(int *kfd, int *ufd, int flag); struct strlist *probe_file__get_namelist(int fd); struct strlist *probe_file__get_rawlist(int fd); int probe_file__add_event(int fd, struct probe_trace_event *tev); + int probe_file__del_events(int fd, struct strfilter *filter); int probe_file__get_events(int fd, struct strfilter *filter, struct strlist *plist); @@ -64,6 +67,7 @@ struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache, const char *group, const char *event); int probe_cache__show_all_caches(struct strfilter *filter); bool probe_type_is_available(enum probe_type type); +bool kretprobe_offset_is_supported(void); #else /* ! HAVE_LIBELF_SUPPORT */ static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused) { diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 0d9d6e0803b8..a5731de0e5eb 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -19,6 +19,7 @@ * */ +#include <inttypes.h> #include <sys/utsname.h> #include <sys/types.h> #include <sys/stat.h> @@ -37,9 +38,11 @@ #include "debug.h" #include "intlist.h" #include "util.h" +#include "strlist.h" #include "symbol.h" #include "probe-finder.h" #include "probe-file.h" +#include "string2.h" /* Kprobe tracer basic type is up to u64 */ #define MAX_BASIC_TYPE_BITS 64 @@ -464,7 +467,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, /* Verify it is a data structure */ tag = dwarf_tag(&type); if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) { - pr_warning("%s is not a data structure nor an union.\n", + pr_warning("%s is not a data structure nor a union.\n", varname); return -EINVAL; } @@ -479,7 +482,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, } else { /* Verify it is a data structure */ if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) { - pr_warning("%s is not a data structure nor an union.\n", + pr_warning("%s is not a data structure nor a union.\n", varname); return -EINVAL; } diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 2956c5198652..27f061551012 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -2,9 +2,9 @@ #define _PROBE_FINDER_H #include <stdbool.h> -#include "util.h" #include "intlist.h" #include "probe-event.h" +#include "sane_ctype.h" #define MAX_PROBE_BUFFER 1024 #define MAX_PROBES 128 diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 0546a4304347..9f3b0d9754a8 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -21,8 +21,10 @@ util/cgroup.c util/parse-branch-options.c util/rblist.c util/counts.c +util/print_binary.c util/strlist.c util/trace-event.c ../lib/rbtree.c util/string.c util/symbol_fprintf.c +util/units.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index a5fbc012e3df..c129e99114ae 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -4,12 +4,26 @@ #include <poll.h> #include <linux/err.h> #include "evlist.h" +#include "callchain.h" #include "evsel.h" #include "event.h" #include "cpumap.h" +#include "print_binary.h" #include "thread_map.h" /* + * Provide these two so that we don't have to link against callchain.c and + * start dragging hist.c, etc. + */ +struct callchain_param callchain_param; + +int parse_callchain_record(const char *arg __maybe_unused, + struct callchain_param *param __maybe_unused) +{ + return 0; +} + +/* * Support debug printing even though util/debug.c is not linked. That means * implementing 'verbose' and 'eprintf'. */ diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c index 293534c1a474..1ba8920151d8 100644 --- a/tools/perf/util/quote.c +++ b/tools/perf/util/quote.c @@ -1,3 +1,4 @@ +#include <errno.h> #include <stdlib.h> #include "strbuf.h" #include "quote.h" diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 98bf584853ea..d91bdf5a1aa4 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -2,6 +2,7 @@ #include "evsel.h" #include "cpumap.h" #include "parse-events.h" +#include <errno.h> #include <api/fs/fs.h> #include "util.h" #include "cloexec.h" diff --git a/tools/perf/util/sane_ctype.h b/tools/perf/util/sane_ctype.h new file mode 100644 index 000000000000..4308c22c22ad --- /dev/null +++ b/tools/perf/util/sane_ctype.h @@ -0,0 +1,51 @@ +#ifndef _PERF_SANE_CTYPE_H +#define _PERF_SANE_CTYPE_H + +extern const char *graph_line; +extern const char *graph_dotted_line; +extern const char *spaces; +extern const char *dots; + +/* Sane ctype - no locale, and works with signed chars */ +#undef isascii +#undef isspace +#undef isdigit +#undef isxdigit +#undef isalpha +#undef isprint +#undef isalnum +#undef islower +#undef isupper +#undef tolower +#undef toupper + +extern unsigned char sane_ctype[256]; +#define GIT_SPACE 0x01 +#define GIT_DIGIT 0x02 +#define GIT_ALPHA 0x04 +#define GIT_GLOB_SPECIAL 0x08 +#define GIT_REGEX_SPECIAL 0x10 +#define GIT_PRINT_EXTRA 0x20 +#define GIT_PRINT 0x3E +#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0) +#define isascii(x) (((x) & ~0x7f) == 0) +#define isspace(x) sane_istest(x,GIT_SPACE) +#define isdigit(x) sane_istest(x,GIT_DIGIT) +#define isxdigit(x) \ + (sane_istest(toupper(x), GIT_ALPHA | GIT_DIGIT) && toupper(x) < 'G') +#define isalpha(x) sane_istest(x,GIT_ALPHA) +#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT) +#define isprint(x) sane_istest(x,GIT_PRINT) +#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20)) +#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20)) +#define tolower(x) sane_case((unsigned char)(x), 0x20) +#define toupper(x) sane_case((unsigned char)(x), 0) + +static inline int sane_case(int x, int high) +{ + if (sane_istest(x, GIT_ALPHA)) + x = (x & ~0x20) | high; + return x; +} + +#endif /* _PERF_SANE_CTYPE_H */ diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build index 6516e220c247..82d28c67e0f3 100644 --- a/tools/perf/util/scripting-engines/Build +++ b/tools/perf/util/scripting-engines/Build @@ -1,6 +1,6 @@ libperf-$(CONFIG_LIBPERL) += trace-event-perl.o libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o -CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default +CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index e55a132f69b7..7b79c413486b 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -19,6 +19,7 @@ * */ +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -27,7 +28,9 @@ #include <linux/bitmap.h> #include <linux/time64.h> -#include "../util.h" +#include <stdbool.h> +/* perl needs the following define, right after including stdbool.h */ +#define HAS_BOOL #include <EXTERN.h> #include <perl.h> @@ -217,6 +220,7 @@ static void define_event_symbols(struct event_format *event, cur_field_name); break; case PRINT_HEX: + case PRINT_HEX_STR: define_event_symbols(event, ev_name, args->hex.field); define_event_symbols(event, ev_name, args->hex.size); break; @@ -309,10 +313,10 @@ static SV *perl_process_callchain(struct perf_sample *sample, if (node->map) { struct map *map = node->map; const char *dsoname = "[unknown]"; - if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (map && map->dso) { if (symbol_conf.show_kernel_path && map->dso->long_name) dsoname = map->dso->long_name; - else if (map->dso->name) + else dsoname = map->dso->name; } if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) { @@ -350,8 +354,10 @@ static void perl_process_tracepoint(struct perf_sample *sample, if (evsel->attr.type != PERF_TYPE_TRACEPOINT) return; - if (!event) - die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); + if (!event) { + pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); + return; + } pid = raw_field_value(event, "common_pid", data); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 089438da1f7f..57b7a00e6f16 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -21,12 +21,14 @@ #include <Python.h> +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <stdbool.h> #include <errno.h> #include <linux/bitmap.h> +#include <linux/compiler.h> #include <linux/time64.h> #include "../../perf.h" @@ -45,6 +47,7 @@ #include "../call-path.h" #include "thread_map.h" #include "cpumap.h" +#include "print_binary.h" #include "stat.h" PyMODINIT_FUNC initperf_trace_context(void); @@ -82,7 +85,7 @@ struct tables { static struct tables tables_global; -static void handler_call_die(const char *handler_name) NORETURN; +static void handler_call_die(const char *handler_name) __noreturn; static void handler_call_die(const char *handler_name) { PyErr_Print(); @@ -236,6 +239,7 @@ static void define_event_symbols(struct event_format *event, cur_field_name); break; case PRINT_HEX: + case PRINT_HEX_STR: define_event_symbols(event, ev_name, args->hex.field); define_event_symbols(event, ev_name, args->hex.size); break; @@ -368,10 +372,10 @@ static PyObject *python_process_callchain(struct perf_sample *sample, if (node->map) { struct map *map = node->map; const char *dsoname = "[unknown]"; - if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (map && map->dso) { if (symbol_conf.show_kernel_path && map->dso->long_name) dsoname = map->dso->long_name; - else if (map->dso->name) + else dsoname = map->dso->name; } pydict_set_item_string_decref(pyelem, "dso", @@ -1216,7 +1220,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "# be retrieved using Python functions of the form " "common_*(context).\n"); - fprintf(ofp, "# See the perf-trace-python Documentation for the list " + fprintf(ofp, "# See the perf-script-python Documentation for the list " "of available functions.\n\n"); fprintf(ofp, "import os\n"); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index f268201048a0..d19c40a81040 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1,5 +1,8 @@ +#include <errno.h> +#include <inttypes.h> #include <linux/kernel.h> #include <traceevent/event-parse.h> +#include <api/fs/fs.h> #include <byteswap.h> #include <unistd.h> @@ -8,6 +11,7 @@ #include "evlist.h" #include "evsel.h" +#include "memswap.h" #include "session.h" #include "tool.h" #include "sort.h" @@ -16,6 +20,7 @@ #include "perf_regs.h" #include "asm/bug.h" #include "auxtrace.h" +#include "thread.h" #include "thread-stack.h" #include "stat.h" @@ -139,8 +144,14 @@ struct perf_session *perf_session__new(struct perf_data_file *file, if (perf_session__open(session) < 0) goto out_close; - perf_session__set_id_hdr_size(session); - perf_session__set_comm_exec(session); + /* + * set session attributes that are present in perf.data + * but not in pipe-mode. + */ + if (!file->is_pipe) { + perf_session__set_id_hdr_size(session); + perf_session__set_comm_exec(session); + } } } else { session->machines.host.env = &perf_env; @@ -155,7 +166,11 @@ struct perf_session *perf_session__new(struct perf_data_file *file, pr_warning("Cannot read kernel map\n"); } - if (tool && tool->ordering_requires_timestamps && + /* + * In pipe-mode, evlist is empty until PERF_RECORD_HEADER_ATTR is + * processed, so perf_evlist__sample_id_all is not meaningful here. + */ + if ((!file || !file->is_pipe) && tool && tool->ordering_requires_timestamps && tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); tool->ordered_events = false; @@ -932,7 +947,7 @@ static void branch_stack__printf(struct perf_sample *sample) printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n", i, e->from, e->to, - e->flags.cycles, + (unsigned short)e->flags.cycles, e->flags.mispred ? "M" : " ", e->flags.predicted ? "P" : " ", e->flags.abort ? "A" : " ", @@ -1191,7 +1206,7 @@ static int u64 sample_type = evsel->attr.sample_type; u64 read_format = evsel->attr.read_format; - /* Standard sample delievery. */ + /* Standard sample delivery. */ if (!(sample_type & PERF_SAMPLE_READ)) return tool->sample(tool, event, sample, evsel, machine); @@ -1239,6 +1254,8 @@ static int machines__deliver_event(struct machines *machines, return tool->mmap2(tool, event, sample, machine); case PERF_RECORD_COMM: return tool->comm(tool, event, sample, machine); + case PERF_RECORD_NAMESPACES: + return tool->namespaces(tool, event, sample, machine); case PERF_RECORD_FORK: return tool->fork(tool, event, sample, machine); case PERF_RECORD_EXIT: @@ -1258,9 +1275,12 @@ static int machines__deliver_event(struct machines *machines, case PERF_RECORD_UNTHROTTLE: return tool->unthrottle(tool, event, sample, machine); case PERF_RECORD_AUX: - if (tool->aux == perf_event__process_aux && - (event->aux.flags & PERF_AUX_FLAG_TRUNCATED)) - evlist->stats.total_aux_lost += 1; + if (tool->aux == perf_event__process_aux) { + if (event->aux.flags & PERF_AUX_FLAG_TRUNCATED) + evlist->stats.total_aux_lost += 1; + if (event->aux.flags & PERF_AUX_FLAG_PARTIAL) + evlist->stats.total_aux_partial += 1; + } return tool->aux(tool, event, sample, machine); case PERF_RECORD_ITRACE_START: return tool->itrace_start(tool, event, sample, machine); @@ -1494,6 +1514,11 @@ int perf_session__register_idle_thread(struct perf_session *session) err = -1; } + if (thread == NULL || thread__set_namespaces(thread, 0, NULL)) { + pr_err("problem inserting idle task.\n"); + err = -1; + } + /* machine__findnew_thread() got the thread, so put it */ thread__put(thread); return err; @@ -1548,6 +1573,23 @@ static void perf_session__warn_about_errors(const struct perf_session *session) stats->nr_events[PERF_RECORD_AUX]); } + if (session->tool->aux == perf_event__process_aux && + stats->total_aux_partial != 0) { + bool vmm_exclusive = false; + + (void)sysfs__read_bool("module/kvm_intel/parameters/vmm_exclusive", + &vmm_exclusive); + + ui__warning("AUX data had gaps in it %" PRIu64 " times out of %u!\n\n" + "Are you running a KVM guest in the background?%s\n\n", + stats->total_aux_partial, + stats->nr_events[PERF_RECORD_AUX], + vmm_exclusive ? + "\nReloading kvm_intel module with vmm_exclusive=0\n" + "will reduce the gaps to only guest's timeslices." : + ""); + } + if (stats->nr_unknown_events != 0) { ui__warning("Found %u unknown events!\n\n" "Is this an older tool processing a perf.data " @@ -1628,6 +1670,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session) buf = malloc(cur_size); if (!buf) return -errno; + ordered_events__set_copy_on_queue(oe, true); more: event = buf; err = readn(fd, event, sizeof(struct perf_event_header)); @@ -1901,7 +1944,7 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, u64 addr) { char *bracket; - enum map_type i; + int i; struct ref_reloc_sym *ref; ref = zalloc(sizeof(struct ref_reloc_sym)); @@ -1992,7 +2035,7 @@ int perf_session__cpu_bitmap(struct perf_session *session, if (!(evsel->attr.sample_type & PERF_SAMPLE_CPU)) { pr_err("File does not contain CPU events. " - "Remove -c option to proceed.\n"); + "Remove -C option to proceed.\n"); return -1; } } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 4bd758553450..47b5e7dbcb18 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -5,14 +5,14 @@ #include "event.h" #include "header.h" #include "machine.h" -#include "symbol.h" -#include "thread.h" #include "data.h" #include "ordered-events.h" +#include <linux/kernel.h> #include <linux/rbtree.h> #include <linux/perf_event.h> struct ip_callchain; +struct symbol; struct thread; struct auxtrace; diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index c8680984d2d6..af415febbc46 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,8 +1,15 @@ #!/usr/bin/python2 -from distutils.core import setup, Extension from os import getenv +cc = getenv("CC") +if cc == "clang": + from _sysconfigdata import build_time_vars + from re import sub + build_time_vars["CFLAGS"] = sub("-specs=[^ ]+", "", build_time_vars["CFLAGS"]) + +from distutils.core import setup, Extension + from distutils.command.build_ext import build_ext as _build_ext from distutils.command.install_lib import install_lib as _install_lib diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index df622f4e301e..8b327c955a4f 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1,12 +1,18 @@ +#include <errno.h> +#include <inttypes.h> +#include <regex.h> #include <sys/mman.h> #include "sort.h" #include "hist.h" #include "comm.h" #include "symbol.h" +#include "thread.h" #include "evsel.h" #include "evlist.h" +#include "strlist.h" #include <traceevent/event-parse.h> #include "mem-events.h" +#include <linux/kernel.h> regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; @@ -151,7 +157,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) if (!dso_l || !dso_r) return cmp_null(dso_r, dso_l); - if (verbose) { + if (verbose > 0) { dso_name_l = dso_l->long_name; dso_name_r = dso_r->long_name; } else { @@ -172,8 +178,8 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf, size_t size, unsigned int width) { if (map && map->dso) { - const char *dso_name = !verbose ? map->dso->short_name : - map->dso->long_name; + const char *dso_name = verbose > 0 ? map->dso->long_name : + map->dso->short_name; return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name); } @@ -261,7 +267,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, { size_t ret = 0; - if (verbose) { + if (verbose > 0) { char o = map ? dso__symtab_origin(map->dso) : '!'; ret += repsep_snprintf(bf, size, "%-#*llx %c ", BITS_PER_LONG / 4 + 2, ip, o); @@ -323,7 +329,7 @@ char *hist_entry__get_srcline(struct hist_entry *he) return SRCLINE_UNKNOWN; return get_srcline(map->dso, map__rip_2objdump(map, he->ip), - he->ms.sym, true); + he->ms.sym, true, true); } static int64_t @@ -366,7 +372,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right) left->branch_info->srcline_from = get_srcline(map->dso, map__rip_2objdump(map, left->branch_info->from.al_addr), - left->branch_info->from.sym, true); + left->branch_info->from.sym, + true, true); } if (!right->branch_info->srcline_from) { struct map *map = right->branch_info->from.map; @@ -376,7 +383,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right) right->branch_info->srcline_from = get_srcline(map->dso, map__rip_2objdump(map, right->branch_info->from.al_addr), - right->branch_info->from.sym, true); + right->branch_info->from.sym, + true, true); } return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from); } @@ -407,7 +415,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right) left->branch_info->srcline_to = get_srcline(map->dso, map__rip_2objdump(map, left->branch_info->to.al_addr), - left->branch_info->from.sym, true); + left->branch_info->from.sym, + true, true); } if (!right->branch_info->srcline_to) { struct map *map = right->branch_info->to.map; @@ -417,7 +426,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right) right->branch_info->srcline_to = get_srcline(map->dso, map__rip_2objdump(map, right->branch_info->to.al_addr), - right->branch_info->to.sym, true); + right->branch_info->to.sym, + true, true); } return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to); } @@ -448,7 +458,7 @@ static char *hist_entry__get_srcfile(struct hist_entry *e) return no_srcfile; sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip), - e->ms.sym, false, true); + e->ms.sym, false, true, true); if (!strcmp(sf, SRCLINE_UNKNOWN)) return no_srcfile; p = strchr(sf, ':'); @@ -536,6 +546,46 @@ struct sort_entry sort_cpu = { .se_width_idx = HISTC_CPU, }; +/* --sort cgroup_id */ + +static int64_t _sort__cgroup_dev_cmp(u64 left_dev, u64 right_dev) +{ + return (int64_t)(right_dev - left_dev); +} + +static int64_t _sort__cgroup_inode_cmp(u64 left_ino, u64 right_ino) +{ + return (int64_t)(right_ino - left_ino); +} + +static int64_t +sort__cgroup_id_cmp(struct hist_entry *left, struct hist_entry *right) +{ + int64_t ret; + + ret = _sort__cgroup_dev_cmp(right->cgroup_id.dev, left->cgroup_id.dev); + if (ret != 0) + return ret; + + return _sort__cgroup_inode_cmp(right->cgroup_id.ino, + left->cgroup_id.ino); +} + +static int hist_entry__cgroup_id_snprintf(struct hist_entry *he, + char *bf, size_t size, + unsigned int width __maybe_unused) +{ + return repsep_snprintf(bf, size, "%lu/0x%lx", he->cgroup_id.dev, + he->cgroup_id.ino); +} + +struct sort_entry sort_cgroup_id = { + .se_header = "cgroup id (dev/inode)", + .se_cmp = sort__cgroup_id_cmp, + .se_snprintf = hist_entry__cgroup_id_snprintf, + .se_width_idx = HISTC_CGROUP_ID, +}; + /* --sort socket */ static int64_t @@ -846,6 +896,9 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf, static int64_t sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right) { + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + return left->branch_info->flags.cycles - right->branch_info->flags.cycles; } @@ -853,6 +906,8 @@ sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__cycles_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { + if (!he->branch_info) + return scnprintf(bf, size, "%-.*s", width, "N/A"); if (he->branch_info->flags.cycles == 0) return repsep_snprintf(bf, size, "%-*s", width, "-"); return repsep_snprintf(bf, size, "%-*hd", width, @@ -1396,6 +1451,46 @@ struct sort_entry sort_transaction = { .se_width_idx = HISTC_TRANSACTION, }; +/* --sort symbol_size */ + +static int64_t _sort__sym_size_cmp(struct symbol *sym_l, struct symbol *sym_r) +{ + int64_t size_l = sym_l != NULL ? symbol__size(sym_l) : 0; + int64_t size_r = sym_r != NULL ? symbol__size(sym_r) : 0; + + return size_l < size_r ? -1 : + size_l == size_r ? 0 : 1; +} + +static int64_t +sort__sym_size_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return _sort__sym_size_cmp(right->ms.sym, left->ms.sym); +} + +static int _hist_entry__sym_size_snprintf(struct symbol *sym, char *bf, + size_t bf_size, unsigned int width) +{ + if (sym) + return repsep_snprintf(bf, bf_size, "%*d", width, symbol__size(sym)); + + return repsep_snprintf(bf, bf_size, "%*s", width, "unknown"); +} + +static int hist_entry__sym_size_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return _hist_entry__sym_size_snprintf(he->ms.sym, bf, size, width); +} + +struct sort_entry sort_sym_size = { + .se_header = "Symbol size", + .se_cmp = sort__sym_size_cmp, + .se_snprintf = hist_entry__sym_size_snprintf, + .se_width_idx = HISTC_SYM_SIZE, +}; + + struct sort_dimension { const char *name; struct sort_entry *entry; @@ -1418,6 +1513,8 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), DIM(SORT_TRANSACTION, "transaction", sort_transaction), DIM(SORT_TRACE, "trace", sort_trace), + DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size), + DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id), }; #undef DIM @@ -2435,12 +2532,12 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, ret = sort_dimension__add(list, tok, evlist, level); if (ret == -EINVAL) { if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok))) - error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); + pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); else - error("Invalid --sort key: `%s'", tok); + pr_err("Invalid --sort key: `%s'", tok); break; } else if (ret == -ESRCH) { - error("Unknown --sort key: `%s'", tok); + pr_err("Unknown --sort key: `%s'", tok); break; } } @@ -2497,7 +2594,7 @@ static int setup_sort_order(struct perf_evlist *evlist) return 0; if (sort_order[1] == '\0') { - error("Invalid --sort key: `+'"); + pr_err("Invalid --sort key: `+'"); return -EINVAL; } @@ -2507,7 +2604,7 @@ static int setup_sort_order(struct perf_evlist *evlist) */ if (asprintf(&new_sort_order, "%s,%s", get_default_sort_order(evlist), sort_order + 1) < 0) { - error("Not enough memory to set up --sort"); + pr_err("Not enough memory to set up --sort"); return -ENOMEM; } @@ -2571,7 +2668,7 @@ static int __setup_sorting(struct perf_evlist *evlist) str = strdup(sort_keys); if (str == NULL) { - error("Not enough memory to setup sort keys"); + pr_err("Not enough memory to setup sort keys"); return -ENOMEM; } @@ -2581,7 +2678,7 @@ static int __setup_sorting(struct perf_evlist *evlist) if (!is_strict_order(field_order)) { str = setup_overhead(str); if (str == NULL) { - error("Not enough memory to setup overhead keys"); + pr_err("Not enough memory to setup overhead keys"); return -ENOMEM; } } @@ -2737,10 +2834,10 @@ static int setup_output_list(struct perf_hpp_list *list, char *str) tok; tok = strtok_r(NULL, ", ", &tmp)) { ret = output_field_add(list, tok); if (ret == -EINVAL) { - error("Invalid --fields key: `%s'", tok); + pr_err("Invalid --fields key: `%s'", tok); break; } else if (ret == -ESRCH) { - error("Unknown --fields key: `%s'", tok); + pr_err("Unknown --fields key: `%s'", tok); break; } } @@ -2780,7 +2877,7 @@ static int __setup_output_field(void) strp = str = strdup(field_order); if (str == NULL) { - error("Not enough memory to setup output fields"); + pr_err("Not enough memory to setup output fields"); return -ENOMEM; } @@ -2788,7 +2885,7 @@ static int __setup_output_field(void) strp++; if (!strlen(strp)) { - error("Invalid --fields key: `+'"); + pr_err("Invalid --fields key: `+'"); goto out; } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 7aff317fc7c4..b7c75597e18f 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -2,7 +2,7 @@ #define __PERF_SORT_H #include "../builtin.h" -#include "util.h" +#include <regex.h> #include "color.h" #include <linux/list.h> @@ -11,7 +11,6 @@ #include "symbol.h" #include "string.h" #include "callchain.h" -#include "strlist.h" #include "values.h" #include "../perf.h" @@ -21,7 +20,9 @@ #include <subcmd/parse-options.h> #include "parse-events.h" #include "hist.h" -#include "thread.h" +#include "srcline.h" + +struct thread; extern regex_t parent_regex; extern const char *sort_order; @@ -54,6 +55,11 @@ struct he_stat { u32 nr_events; }; +struct namespace_id { + u64 dev; + u64 ino; +}; + struct hist_entry_diff { bool computed; union { @@ -91,6 +97,7 @@ struct hist_entry { struct map_symbol ms; struct thread *thread; struct comm *comm; + struct namespace_id cgroup_id; u64 ip; u64 transaction; s32 socket; @@ -108,7 +115,7 @@ struct hist_entry { /* * Since perf diff only supports the stdio output, TUI * fields are only accessed from perf report (or perf - * top). So make it an union to reduce memory usage. + * top). So make it a union to reduce memory usage. */ struct hist_entry_diff diff; struct /* for TUI */ { @@ -122,6 +129,7 @@ struct hist_entry { }; char *srcline; char *srcfile; + struct inline_node *inline_node; struct symbol *parent; struct branch_info *branch_info; struct hists *hists; @@ -211,6 +219,8 @@ enum sort_type { SORT_GLOBAL_WEIGHT, SORT_TRANSACTION, SORT_TRACE, + SORT_SYM_SIZE, + SORT_CGROUP_ID, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index b4db3f48e3b0..ebc88a74e67b 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -1,3 +1,4 @@ +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -7,11 +8,62 @@ #include "util/dso.h" #include "util/util.h" #include "util/debug.h" +#include "util/callchain.h" +#include "srcline.h" #include "symbol.h" bool srcline_full_filename; +static const char *dso__name(struct dso *dso) +{ + const char *dso_name; + + if (dso->symsrc_filename) + dso_name = dso->symsrc_filename; + else + dso_name = dso->long_name; + + if (dso_name[0] == '[') + return NULL; + + if (!strncmp(dso_name, "/tmp/perf-", 10)) + return NULL; + + return dso_name; +} + +static int inline_list__append(char *filename, char *funcname, int line_nr, + struct inline_node *node, struct dso *dso) +{ + struct inline_list *ilist; + char *demangled; + + ilist = zalloc(sizeof(*ilist)); + if (ilist == NULL) + return -1; + + ilist->filename = filename; + ilist->line_nr = line_nr; + + if (dso != NULL) { + demangled = dso__demangle_sym(dso, 0, funcname); + if (demangled == NULL) { + ilist->funcname = funcname; + } else { + ilist->funcname = demangled; + free(funcname); + } + } + + if (callchain_param.order == ORDER_CALLEE) + list_add_tail(&ilist->list, &node->val); + else + list_add(&ilist->list, &node->val); + + return 0; +} + #ifdef HAVE_LIBBFD_SUPPORT /* @@ -151,9 +203,19 @@ static void addr2line_cleanup(struct a2l_data *a2l) #define MAX_INLINE_NEST 1024 +static int inline_list__append_dso_a2l(struct dso *dso, + struct inline_node *node) +{ + struct a2l_data *a2l = dso->a2l; + char *funcname = a2l->funcname ? strdup(a2l->funcname) : NULL; + char *filename = a2l->filename ? strdup(a2l->filename) : NULL; + + return inline_list__append(filename, funcname, a2l->line, node, dso); +} + static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line, struct dso *dso, - bool unwind_inlines) + bool unwind_inlines, struct inline_node *node) { int ret = 0; struct a2l_data *a2l = dso->a2l; @@ -173,23 +235,36 @@ static int addr2line(const char *dso_name, u64 addr, bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l); - if (a2l->found && unwind_inlines) { + if (!a2l->found) + return 0; + + if (unwind_inlines) { int cnt = 0; + if (node && inline_list__append_dso_a2l(dso, node)) + return 0; + while (bfd_find_inliner_info(a2l->abfd, &a2l->filename, &a2l->funcname, &a2l->line) && - cnt++ < MAX_INLINE_NEST) - ; + cnt++ < MAX_INLINE_NEST) { + + if (node != NULL) { + if (inline_list__append_dso_a2l(dso, node)) + return 0; + // found at least one inline frame + ret = 1; + } + } } - if (a2l->found && a2l->filename) { - *file = strdup(a2l->filename); - *line = a2l->line; - - if (*file) - ret = 1; + if (file) { + *file = a2l->filename ? strdup(a2l->filename) : NULL; + ret = *file ? 1 : 0; } + if (line) + *line = a2l->line; + return ret; } @@ -205,18 +280,66 @@ void dso__free_a2l(struct dso *dso) dso->a2l = NULL; } +static struct inline_node *addr2inlines(const char *dso_name, u64 addr, + struct dso *dso) +{ + struct inline_node *node; + + node = zalloc(sizeof(*node)); + if (node == NULL) { + perror("not enough memory for the inline node"); + return NULL; + } + + INIT_LIST_HEAD(&node->val); + node->addr = addr; + + if (!addr2line(dso_name, addr, NULL, NULL, dso, TRUE, node)) + goto out_free_inline_node; + + if (list_empty(&node->val)) + goto out_free_inline_node; + + return node; + +out_free_inline_node: + inline_node__delete(node); + return NULL; +} + #else /* HAVE_LIBBFD_SUPPORT */ +static int filename_split(char *filename, unsigned int *line_nr) +{ + char *sep; + + sep = strchr(filename, '\n'); + if (sep) + *sep = '\0'; + + if (!strcmp(filename, "??:0")) + return 0; + + sep = strchr(filename, ':'); + if (sep) { + *sep++ = '\0'; + *line_nr = strtoul(sep, NULL, 0); + return 1; + } + + return 0; +} + static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line_nr, struct dso *dso __maybe_unused, - bool unwind_inlines __maybe_unused) + bool unwind_inlines __maybe_unused, + struct inline_node *node __maybe_unused) { 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, @@ -233,23 +356,14 @@ static int addr2line(const char *dso_name, u64 addr, goto out; } - sep = strchr(filename, '\n'); - if (sep) - *sep = '\0'; - - if (!strcmp(filename, "??:0")) { - pr_debug("no debugging info in %s\n", dso_name); + ret = filename_split(filename, line_nr); + if (ret != 1) { free(filename); goto out; } - sep = strchr(filename, ':'); - if (sep) { - *sep++ = '\0'; - *file = filename; - *line_nr = strtoul(sep, NULL, 0); - ret = 1; - } + *file = filename; + out: pclose(fp); return ret; @@ -259,6 +373,58 @@ void dso__free_a2l(struct dso *dso __maybe_unused) { } +static struct inline_node *addr2inlines(const char *dso_name, u64 addr, + struct dso *dso __maybe_unused) +{ + FILE *fp; + char cmd[PATH_MAX]; + struct inline_node *node; + char *filename = NULL; + size_t len; + unsigned int line_nr = 0; + + scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i %016"PRIx64, + dso_name, addr); + + fp = popen(cmd, "r"); + if (fp == NULL) { + pr_err("popen failed for %s\n", dso_name); + return NULL; + } + + node = zalloc(sizeof(*node)); + if (node == NULL) { + perror("not enough memory for the inline node"); + goto out; + } + + INIT_LIST_HEAD(&node->val); + node->addr = addr; + + while (getline(&filename, &len, fp) != -1) { + if (filename_split(filename, &line_nr) != 1) { + free(filename); + goto out; + } + + if (inline_list__append(filename, NULL, line_nr, node, + NULL) != 0) + goto out; + + filename = NULL; + } + +out: + pclose(fp); + + if (list_empty(&node->val)) { + inline_node__delete(node); + return NULL; + } + + return node; +} + #endif /* HAVE_LIBBFD_SUPPORT */ /* @@ -268,7 +434,7 @@ void dso__free_a2l(struct dso *dso __maybe_unused) #define A2L_FAIL_LIMIT 123 char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, - bool show_sym, bool unwind_inlines) + bool show_sym, bool show_addr, bool unwind_inlines) { char *file = NULL; unsigned line = 0; @@ -278,18 +444,11 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, if (!dso->has_srcline) goto out; - if (dso->symsrc_filename) - dso_name = dso->symsrc_filename; - else - dso_name = dso->long_name; - - if (dso_name[0] == '[') - goto out; - - if (!strncmp(dso_name, "/tmp/perf-", 10)) + dso_name = dso__name(dso); + if (dso_name == NULL) goto out; - if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines)) + if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines, NULL)) goto out; if (asprintf(&srcline, "%s:%u", @@ -309,6 +468,11 @@ out: dso->has_srcline = 0; dso__free_a2l(dso); } + + if (!show_addr) + return (show_sym && sym) ? + strndup(sym->name, sym->namelen) : NULL; + if (sym) { if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "", addr - sym->start) < 0) @@ -325,7 +489,32 @@ void free_srcline(char *srcline) } char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, - bool show_sym) + bool show_sym, bool show_addr) +{ + return __get_srcline(dso, addr, sym, show_sym, show_addr, false); +} + +struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr) +{ + const char *dso_name; + + dso_name = dso__name(dso); + if (dso_name == NULL) + return NULL; + + return addr2inlines(dso_name, addr, dso); +} + +void inline_node__delete(struct inline_node *node) { - return __get_srcline(dso, addr, sym, show_sym, false); + struct inline_list *ilist, *tmp; + + list_for_each_entry_safe(ilist, tmp, &node->val, list) { + list_del_init(&ilist->list); + zfree(&ilist->filename); + zfree(&ilist->funcname); + free(ilist); + } + + free(node); } diff --git a/tools/perf/util/srcline.h b/tools/perf/util/srcline.h new file mode 100644 index 000000000000..7b52ba88676e --- /dev/null +++ b/tools/perf/util/srcline.h @@ -0,0 +1,34 @@ +#ifndef PERF_SRCLINE_H +#define PERF_SRCLINE_H + +#include <linux/list.h> +#include <linux/types.h> + +struct dso; +struct symbol; + +extern bool srcline_full_filename; +char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, + bool show_sym, bool show_addr); +char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, + bool show_sym, bool show_addr, bool unwind_inlines); +void free_srcline(char *srcline); + +#define SRCLINE_UNKNOWN ((char *) "??:0") + +struct inline_list { + char *filename; + char *funcname; + unsigned int line_nr; + struct list_head list; +}; + +struct inline_node { + u64 addr; + struct list_head val; +}; + +struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr); +void inline_node__delete(struct inline_node *node); + +#endif /* PERF_SRCLINE_H */ diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 8a2bbd2a4d82..719d6cb86952 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -3,6 +3,9 @@ #include "stat.h" #include "color.h" #include "pmu.h" +#include "rblist.h" +#include "evlist.h" +#include "expr.h" enum { CTX_BIT_USER = 1 << 0, @@ -41,13 +44,75 @@ static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS]; +static struct stats runtime_smi_num_stats[NUM_CTX][MAX_NR_CPUS]; +static struct stats runtime_aperf_stats[NUM_CTX][MAX_NR_CPUS]; +static struct rblist runtime_saved_values; static bool have_frontend_stalled; struct stats walltime_nsecs_stats; +struct saved_value { + struct rb_node rb_node; + struct perf_evsel *evsel; + int cpu; + int ctx; + struct stats stats; +}; + +static int saved_value_cmp(struct rb_node *rb_node, const void *entry) +{ + struct saved_value *a = container_of(rb_node, + struct saved_value, + rb_node); + const struct saved_value *b = entry; + + if (a->ctx != b->ctx) + return a->ctx - b->ctx; + if (a->cpu != b->cpu) + return a->cpu - b->cpu; + return a->evsel - b->evsel; +} + +static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused, + const void *entry) +{ + struct saved_value *nd = malloc(sizeof(struct saved_value)); + + if (!nd) + return NULL; + memcpy(nd, entry, sizeof(struct saved_value)); + return &nd->rb_node; +} + +static struct saved_value *saved_value_lookup(struct perf_evsel *evsel, + int cpu, int ctx, + bool create) +{ + struct rb_node *nd; + struct saved_value dm = { + .cpu = cpu, + .ctx = ctx, + .evsel = evsel, + }; + nd = rblist__find(&runtime_saved_values, &dm); + if (nd) + return container_of(nd, struct saved_value, rb_node); + if (create) { + rblist__add_node(&runtime_saved_values, &dm); + nd = rblist__find(&runtime_saved_values, &dm); + if (nd) + return container_of(nd, struct saved_value, rb_node); + } + return NULL; +} + void perf_stat__init_shadow_stats(void) { have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend"); + rblist__init(&runtime_saved_values); + runtime_saved_values.node_cmp = saved_value_cmp; + runtime_saved_values.node_new = saved_value_new; + /* No delete for now */ } static int evsel_context(struct perf_evsel *evsel) @@ -70,6 +135,8 @@ static int evsel_context(struct perf_evsel *evsel) void perf_stat__reset_shadow_stats(void) { + struct rb_node *pos, *next; + memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats)); memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats)); memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats)); @@ -92,6 +159,17 @@ void perf_stat__reset_shadow_stats(void) memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued)); memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles)); memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles)); + memset(runtime_smi_num_stats, 0, sizeof(runtime_smi_num_stats)); + memset(runtime_aperf_stats, 0, sizeof(runtime_aperf_stats)); + + next = rb_first(&runtime_saved_values.entries); + while (next) { + pos = next; + next = rb_next(pos); + memset(&container_of(pos, struct saved_value, rb_node)->stats, + 0, + sizeof(struct stats)); + } } /* @@ -143,6 +221,16 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]); + else if (perf_stat_evsel__is(counter, SMI_NUM)) + update_stats(&runtime_smi_num_stats[ctx][cpu], count[0]); + else if (perf_stat_evsel__is(counter, APERF)) + update_stats(&runtime_aperf_stats[ctx][cpu], count[0]); + + if (counter->collect_stat) { + struct saved_value *v = saved_value_lookup(counter, cpu, ctx, + true); + update_stats(&v->stats, count[0]); + } } /* used for get_ratio_color() */ @@ -172,6 +260,95 @@ static const char *get_ratio_color(enum grc_type type, double ratio) return color; } +static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list, + const char *name) +{ + struct perf_evsel *c2; + + evlist__for_each_entry (evsel_list, c2) { + if (!strcasecmp(c2->name, name)) + return c2; + } + return NULL; +} + +/* Mark MetricExpr target events and link events using them to them. */ +void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list) +{ + struct perf_evsel *counter, *leader, **metric_events, *oc; + bool found; + const char **metric_names; + int i; + int num_metric_names; + + evlist__for_each_entry(evsel_list, counter) { + bool invalid = false; + + leader = counter->leader; + if (!counter->metric_expr) + continue; + metric_events = counter->metric_events; + if (!metric_events) { + if (expr__find_other(counter->metric_expr, counter->name, + &metric_names, &num_metric_names) < 0) + continue; + + metric_events = calloc(sizeof(struct perf_evsel *), + num_metric_names + 1); + if (!metric_events) + return; + counter->metric_events = metric_events; + } + + for (i = 0; i < num_metric_names; i++) { + found = false; + if (leader) { + /* Search in group */ + for_each_group_member (oc, leader) { + if (!strcasecmp(oc->name, metric_names[i])) { + found = true; + break; + } + } + } + if (!found) { + /* Search ignoring groups */ + oc = perf_stat__find_event(evsel_list, metric_names[i]); + } + if (!oc) { + /* Deduping one is good enough to handle duplicated PMUs. */ + static char *printed; + + /* + * Adding events automatically would be difficult, because + * it would risk creating groups that are not schedulable. + * perf stat doesn't understand all the scheduling constraints + * of events. So we ask the user instead to add the missing + * events. + */ + if (!printed || strcasecmp(printed, metric_names[i])) { + fprintf(stderr, + "Add %s event to groups to get metric expression for %s\n", + metric_names[i], + counter->name); + printed = strdup(metric_names[i]); + } + invalid = true; + continue; + } + metric_events[i] = oc; + oc->collect_stat = true; + } + metric_events[i] = NULL; + free(metric_names); + if (invalid) { + free(metric_events); + counter->metric_events = NULL; + counter->metric_expr = NULL; + } + } +} + static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel, double avg, struct perf_stat_output_ctx *out) @@ -423,6 +600,29 @@ static double td_be_bound(int ctx, int cpu) return sanitize_val(1.0 - sum); } +static void print_smi_cost(int cpu, struct perf_evsel *evsel, + struct perf_stat_output_ctx *out) +{ + double smi_num, aperf, cycles, cost = 0.0; + int ctx = evsel_context(evsel); + const char *color = NULL; + + smi_num = avg_stats(&runtime_smi_num_stats[ctx][cpu]); + aperf = avg_stats(&runtime_aperf_stats[ctx][cpu]); + cycles = avg_stats(&runtime_cycles_stats[ctx][cpu]); + + if ((cycles == 0) || (aperf == 0)) + return; + + if (smi_num) + cost = (aperf - cycles) / aperf * 100.00; + + if (cost > 10) + color = PERF_COLOR_RED; + out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost); + out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num); +} + void perf_stat__print_shadow_stats(struct perf_evsel *evsel, double avg, int cpu, struct perf_stat_output_ctx *out) @@ -614,6 +814,34 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, be_bound * 100.); else print_metric(ctxp, NULL, NULL, name, 0); + } else if (evsel->metric_expr) { + struct parse_ctx pctx; + int i; + + expr__ctx_init(&pctx); + expr__add_id(&pctx, evsel->name, avg); + for (i = 0; evsel->metric_events[i]; i++) { + struct saved_value *v; + + v = saved_value_lookup(evsel->metric_events[i], cpu, ctx, false); + if (!v) + break; + expr__add_id(&pctx, evsel->metric_events[i]->name, + avg_stats(&v->stats)); + } + if (!evsel->metric_events[i]) { + const char *p = evsel->metric_expr; + + if (expr__parse(&ratio, &pctx, &p) == 0) + print_metric(ctxp, NULL, "%8.1f", + evsel->metric_name ? + evsel->metric_name : + out->force_header ? evsel->name : "", + ratio); + else + print_metric(ctxp, NULL, NULL, "", 0); + } else + print_metric(ctxp, NULL, NULL, "", 0); } else if (runtime_nsecs_stats[cpu].n != 0) { char unit = 'M'; char unit_buf[10]; @@ -628,6 +856,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, } snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio); + } else if (perf_stat_evsel__is(evsel, SMI_NUM)) { + print_smi_cost(cpu, evsel, out); } else { print_metric(ctxp, NULL, NULL, NULL, 0); } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 39345c2ddfc2..53b9a994a3dc 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> #include <math.h> #include "stat.h" #include "evlist.h" @@ -84,6 +86,8 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired), ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles), ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles), + ID(SMI_NUM, msr/smi/), + ID(APERF, msr/aperf/), }; #undef ID @@ -344,7 +348,7 @@ int perf_stat_process_counter(struct perf_stat_config *config, for (i = 0; i < 3; i++) update_stats(&ps->res_stats[i], count[i]); - if (verbose) { + if (verbose > 0) { fprintf(config->output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", perf_evsel__name(counter), count[0], count[1], count[2]); } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index c29bb94c48a4..7522bf10b03e 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -22,6 +22,8 @@ enum perf_stat_evsel_id { PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED, PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES, PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES, + PERF_STAT_EVSEL_ID__SMI_NUM, + PERF_STAT_EVSEL_ID__APERF, PERF_STAT_EVSEL_ID__MAX, }; @@ -85,11 +87,13 @@ struct perf_stat_output_ctx { void *ctx; print_metric_t print_metric; new_line_t new_line; + bool force_header; }; void perf_stat__print_shadow_stats(struct perf_evsel *evsel, double avg, int cpu, struct perf_stat_output_ctx *out); +void perf_stat__collect_metric_expr(struct perf_evlist *); int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw); void perf_evlist__free_stats(struct perf_evlist *evlist); diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index 817593908d47..aafe908b82b5 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -1,15 +1,7 @@ #include "debug.h" #include "util.h" #include <linux/kernel.h> - -int prefixcmp(const char *str, const char *prefix) -{ - for (; ; str++, prefix++) - if (!*prefix) - return 0; - else if (*str != *prefix) - return (unsigned char)*prefix - (unsigned char)*str; -} +#include <errno.h> /* * Used as the default ->buf value, so that people can always assume diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h index 318424ea561d..802d743378af 100644 --- a/tools/perf/util/strbuf.h +++ b/tools/perf/util/strbuf.h @@ -42,6 +42,7 @@ #include <stdarg.h> #include <stddef.h> #include <string.h> +#include <linux/compiler.h> #include <sys/types.h> extern char strbuf_slopbuf[]; @@ -85,8 +86,7 @@ static inline int strbuf_addstr(struct strbuf *sb, const char *s) { return strbuf_add(sb, s, strlen(s)); } -__attribute__((format(printf,2,3))) -int strbuf_addf(struct strbuf *sb, const char *fmt, ...); +int strbuf_addf(struct strbuf *sb, const char *fmt, ...) __printf(2, 3); /* XXX: if read fails, any partial read is undone */ ssize_t strbuf_read(struct strbuf *, int fd, ssize_t hint); diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c index bcae659b6546..4dc0af669a30 100644 --- a/tools/perf/util/strfilter.c +++ b/tools/perf/util/strfilter.c @@ -1,7 +1,10 @@ #include "util.h" -#include "string.h" +#include "string2.h" #include "strfilter.h" +#include <errno.h> +#include "sane_ctype.h" + /* Operators */ static const char *OP_and = "&"; /* Logical AND */ static const char *OP_or = "|"; /* Logical OR */ @@ -269,6 +272,7 @@ static int strfilter_node__sprint(struct strfilter_node *node, char *buf) len = strfilter_node__sprint_pt(node->l, buf); if (len < 0) return len; + __fallthrough; case '!': if (buf) { *(buf + len++) = *node->p; diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index d8dfaf64b32e..cca53b693a48 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -1,5 +1,9 @@ -#include "util.h" -#include "linux/string.h" +#include "string2.h" +#include <linux/kernel.h> +#include <linux/string.h> +#include <stdlib.h> + +#include "sane_ctype.h" #define K 1024LL /* @@ -21,6 +25,8 @@ s64 perf_atoll(const char *str) case 'b': case 'B': if (*p) goto out_err; + + __fallthrough; case '\0': return length; default: @@ -97,8 +103,10 @@ static int count_argc(const char *str) void argv_free(char **argv) { char **p; - for (p = argv; *p; p++) - zfree(p); + for (p = argv; *p; p++) { + free(*p); + *p = NULL; + } free(argv); } @@ -118,7 +126,7 @@ void argv_free(char **argv) char **argv_split(const char *str, int *argcp) { int argc = count_argc(str); - char **argv = zalloc(sizeof(*argv) * (argc+1)); + char **argv = calloc(argc + 1, sizeof(*argv)); char **argvp; if (argv == NULL) @@ -320,12 +328,8 @@ char *strxfrchar(char *s, char from, char to) */ char *ltrim(char *s) { - int len = strlen(s); - - while (len && isspace(*s)) { - len--; + while (isspace(*s)) s++; - } return s; } @@ -379,7 +383,7 @@ char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints goto out_err_overflow; if (i > 0) - printed += snprintf(e + printed, size - printed, " %s ", or_and); + printed += scnprintf(e + printed, size - printed, " %s ", or_and); printed += scnprintf(e + printed, size - printed, "%s %s %d", var, eq_neq, ints[i]); } diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h new file mode 100644 index 000000000000..2f619681bd6a --- /dev/null +++ b/tools/perf/util/string2.h @@ -0,0 +1,42 @@ +#ifndef PERF_STRING_H +#define PERF_STRING_H + +#include <linux/types.h> +#include <stddef.h> +#include <string.h> + +s64 perf_atoll(const char *str); +char **argv_split(const char *str, int *argcp); +void argv_free(char **argv); +bool strglobmatch(const char *str, const char *pat); +bool strglobmatch_nocase(const char *str, const char *pat); +bool strlazymatch(const char *str, const char *pat); +static inline bool strisglob(const char *str) +{ + return strpbrk(str, "*?[") != NULL; +} +int strtailcmp(const char *s1, const char *s2); +char *strxfrchar(char *s, char from, char to); + +char *ltrim(char *s); +char *rtrim(char *s); + +static inline char *trim(char *s) +{ + return ltrim(rtrim(s)); +} + +char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints); + +static inline char *asprintf_expr_in_ints(const char *var, size_t nints, int *ints) +{ + return asprintf_expr_inout_ints(var, true, nints, ints); +} + +static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int *ints) +{ + return asprintf_expr_inout_ints(var, false, nints, ints); +} + + +#endif /* PERF_STRING_H */ diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c index 0d3dfcb919b4..9de5434bb49e 100644 --- a/tools/perf/util/strlist.c +++ b/tools/perf/util/strlist.c @@ -10,6 +10,7 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <unistd.h> static struct rb_node *strlist__node_new(struct rblist *rblist, const void *entry) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index adbc6c02c3aa..502505cf236a 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -10,8 +10,9 @@ #include "demangle-rust.h" #include "machine.h" #include "vdso.h" -#include <symbol/kallsyms.h> #include "debug.h" +#include "sane_ctype.h" +#include <symbol/kallsyms.h> #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ @@ -213,7 +214,7 @@ static bool want_demangle(bool is_kernel_sym) static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) { - int demangle_flags = verbose ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS; + int demangle_flags = verbose > 0 ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS; char *demangled = NULL; /* @@ -390,6 +391,11 @@ out_elf_end: return 0; } +char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name) +{ + return demangle_sym(dso, kmodule, elf_name); +} + /* * Align offset to 4 bytes as needed for note name and descriptor data. */ @@ -631,43 +637,6 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata) return 0; } -static int decompress_kmodule(struct dso *dso, const char *name, - enum dso_binary_type type) -{ - int fd = -1; - char tmpbuf[] = "/tmp/perf-kmod-XXXXXX"; - struct kmod_path m; - - if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP && - type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP && - type != DSO_BINARY_TYPE__BUILD_ID_CACHE) - return -1; - - if (type == DSO_BINARY_TYPE__BUILD_ID_CACHE) - name = dso->long_name; - - if (kmod_path__parse_ext(&m, name) || !m.comp) - return -1; - - fd = mkstemp(tmpbuf); - if (fd < 0) { - dso->load_errno = errno; - goto out; - } - - if (!decompress_to_file(m.ext, name, fd)) { - dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE; - close(fd); - fd = -1; - } - - unlink(tmpbuf); - -out: - free(m.ext); - return fd; -} - bool symsrc__possibly_runtime(struct symsrc *ss) { return ss->dynsym || ss->opdsec; @@ -699,9 +668,11 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, int fd; if (dso__needs_decompress(dso)) { - fd = decompress_kmodule(dso, name, type); + fd = dso__decompress_kmodule_fd(dso, name); if (fd < 0) return -1; + + type = dso->symtab_type; } else { fd = open(name, O_RDONLY); if (fd < 0) { @@ -1828,7 +1799,7 @@ void kcore_extract__delete(struct kcore_extract *kce) static int populate_sdt_note(Elf **elf, const char *data, size_t len, struct list_head *sdt_notes) { - const char *provider, *name; + const char *provider, *name, *args; struct sdt_note *tmp = NULL; GElf_Ehdr ehdr; GElf_Addr base_off = 0; @@ -1887,6 +1858,25 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len, goto out_free_prov; } + args = memchr(name, '\0', data + len - name); + + /* + * There is no argument if: + * - We reached the end of the note; + * - There is not enough room to hold a potential string; + * - The argument string is empty or just contains ':'. + */ + if (args == NULL || data + len - args < 2 || + args[1] == ':' || args[1] == '\0') + tmp->args = NULL; + else { + tmp->args = strdup(++args); + if (!tmp->args) { + ret = -ENOMEM; + goto out_free_name; + } + } + if (gelf_getclass(*elf) == ELFCLASS32) { memcpy(&tmp->addr, &buf, 3 * sizeof(Elf32_Addr)); tmp->bit32 = true; @@ -1898,7 +1888,7 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len, if (!gelf_getehdr(*elf, &ehdr)) { pr_debug("%s : cannot get elf header.\n", __func__); ret = -EBADF; - goto out_free_name; + goto out_free_args; } /* Adjust the prelink effect : @@ -1923,6 +1913,8 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len, list_add_tail(&tmp->note_list, sdt_notes); return 0; +out_free_args: + free(tmp->args); out_free_name: free(tmp->name); out_free_prov: diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index 11cdde980545..40bf5d4c0bfd 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -1,6 +1,7 @@ #include "symbol.h" #include "util.h" +#include <errno.h> #include <stdio.h> #include <fcntl.h> #include <string.h> @@ -373,3 +374,10 @@ int kcore_copy(const char *from_dir __maybe_unused, void symbol__elf_init(void) { } + +char *dso__demangle_sym(struct dso *dso __maybe_unused, + int kmodule __maybe_unused, + char *elf_name __maybe_unused) +{ + return NULL; +} diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index dc93940de351..e7a98dbd2aed 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -3,6 +3,7 @@ #include <stdlib.h> #include <stdio.h> #include <string.h> +#include <linux/kernel.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/param.h> @@ -18,6 +19,8 @@ #include "strlist.h" #include "intlist.h" #include "header.h" +#include "path.h" +#include "sane_ctype.h" #include <elf.h> #include <limits.h> @@ -87,6 +90,17 @@ static int prefix_underscores_count(const char *str) return tail - str; } +int __weak arch__compare_symbol_names(const char *namea, const char *nameb) +{ + return strcmp(namea, nameb); +} + +int __weak arch__compare_symbol_names_n(const char *namea, const char *nameb, + unsigned int n) +{ + return strncmp(namea, nameb, n); +} + int __weak arch__choose_best_symbol(struct symbol *syma, struct symbol *symb __maybe_unused) { @@ -202,7 +216,7 @@ void symbols__fixup_end(struct rb_root *symbols) /* Last entry */ if (curr->end == curr->start) - curr->end = roundup(curr->start, 4096); + curr->end = roundup(curr->start, 4096) + 4096; } void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) @@ -396,8 +410,26 @@ static void symbols__sort_by_name(struct rb_root *symbols, } } +int symbol__match_symbol_name(const char *name, const char *str, + enum symbol_tag_include includes) +{ + const char *versioning; + + if (includes == SYMBOL_TAG_INCLUDE__DEFAULT_ONLY && + (versioning = strstr(name, "@@"))) { + int len = strlen(str); + + if (len < versioning - name) + len = versioning - name; + + return arch__compare_symbol_names_n(name, str, len); + } else + return arch__compare_symbol_names(name, str); +} + static struct symbol *symbols__find_by_name(struct rb_root *symbols, - const char *name) + const char *name, + enum symbol_tag_include includes) { struct rb_node *n; struct symbol_name_rb_node *s = NULL; @@ -411,11 +443,11 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, int cmp; s = rb_entry(n, struct symbol_name_rb_node, rb_node); - cmp = arch__compare_symbol_names(name, s->sym.name); + cmp = symbol__match_symbol_name(s->sym.name, name, includes); - if (cmp < 0) + if (cmp > 0) n = n->rb_left; - else if (cmp > 0) + else if (cmp < 0) n = n->rb_right; else break; @@ -424,16 +456,17 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, if (n == NULL) return NULL; - /* return first symbol that has same name (if any) */ - for (n = rb_prev(n); n; n = rb_prev(n)) { - struct symbol_name_rb_node *tmp; + if (includes != SYMBOL_TAG_INCLUDE__DEFAULT_ONLY) + /* return first symbol that has same name (if any) */ + for (n = rb_prev(n); n; n = rb_prev(n)) { + struct symbol_name_rb_node *tmp; - tmp = rb_entry(n, struct symbol_name_rb_node, rb_node); - if (arch__compare_symbol_names(tmp->sym.name, s->sym.name)) - break; + tmp = rb_entry(n, struct symbol_name_rb_node, rb_node); + if (arch__compare_symbol_names(tmp->sym.name, s->sym.name)) + break; - s = tmp; - } + s = tmp; + } return &s->sym; } @@ -463,7 +496,7 @@ void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym) struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr) { - if (dso->last_find_result[type].addr != addr) { + if (dso->last_find_result[type].addr != addr || dso->last_find_result[type].symbol == NULL) { dso->last_find_result[type].addr = addr; dso->last_find_result[type].symbol = symbols__find(&dso->symbols[type], addr); } @@ -500,7 +533,12 @@ struct symbol *symbol__next_by_name(struct symbol *sym) struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name) { - return symbols__find_by_name(&dso->symbol_names[type], name); + struct symbol *s = symbols__find_by_name(&dso->symbol_names[type], name, + SYMBOL_TAG_INCLUDE__NONE); + if (!s) + s = symbols__find_by_name(&dso->symbol_names[type], name, + SYMBOL_TAG_INCLUDE__DEFAULT_ONLY); + return s; } void dso__sort_by_name(struct dso *dso, enum map_type type) @@ -1072,8 +1110,9 @@ static int validate_kcore_addresses(const char *kallsyms_filename, if (kmap->ref_reloc_sym && kmap->ref_reloc_sym->name) { u64 start; - start = kallsyms__get_function_start(kallsyms_filename, - kmap->ref_reloc_sym->name); + if (kallsyms__get_function_start(kallsyms_filename, + kmap->ref_reloc_sym->name, &start)) + return -ENOENT; if (start != kmap->ref_reloc_sym->addr) return -EINVAL; } @@ -1245,9 +1284,7 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta) if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name) return 0; - addr = kallsyms__get_function_start(filename, - kmap->ref_reloc_sym->name); - if (!addr) + if (kallsyms__get_function_start(filename, kmap->ref_reloc_sym->name, &addr)) return -1; *delta = addr - kmap->ref_reloc_sym->addr; @@ -1460,9 +1497,11 @@ int dso__load(struct dso *dso, struct map *map) * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work */ if (!dso->has_build_id && - is_regular_file(dso->long_name) && - filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) + is_regular_file(dso->long_name)) { + __symbol__join_symfs(name, PATH_MAX, dso->long_name); + if (filename__read_build_id(name, build_id, BUILD_ID_SIZE) > 0) dso__set_build_id(dso, build_id); + } /* * Iterate over candidate debug images. @@ -1523,10 +1562,6 @@ int dso__load(struct dso *dso, struct map *map) if (!runtime_ss && syms_ss) runtime_ss = syms_ss; - if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE) - if (dso__build_id_is_kmod(dso, name, PATH_MAX)) - kmod = true; - if (syms_ss) ret = dso__load_sym(dso, map, syms_ss, runtime_ss, kmod); else diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 6c358b7ed336..41ebba9a2eb2 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -13,7 +13,7 @@ #include <libgen.h> #include "build-id.h" #include "event.h" -#include "util.h" +#include "path.h" #ifdef HAVE_LIBELF_SUPPORT #include <libelf.h> @@ -118,7 +118,8 @@ struct symbol_conf { show_ref_callgraph, hide_unresolved, raw_trace, - report_hierarchy; + report_hierarchy, + inline_name; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -305,6 +306,8 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map); +char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name); + void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel); void symbols__insert(struct rb_root *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root *symbols); @@ -345,12 +348,24 @@ void arch__sym_update(struct symbol *s, GElf_Sym *sym); #define SYMBOL_A 0 #define SYMBOL_B 1 +int arch__compare_symbol_names(const char *namea, const char *nameb); +int arch__compare_symbol_names_n(const char *namea, const char *nameb, + unsigned int n); int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb); +enum symbol_tag_include { + SYMBOL_TAG_INCLUDE__NONE = 0, + SYMBOL_TAG_INCLUDE__DEFAULT_ONLY +}; + +int symbol__match_symbol_name(const char *namea, const char *nameb, + enum symbol_tag_include includes); + /* structure containing an SDT note's info */ struct sdt_note { char *name; /* name of the note*/ char *provider; /* provider name */ + char *args; bool bit32; /* whether the location is 32 bits? */ union { /* location, base and semaphore addrs */ Elf64_Addr a64[3]; diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c index 7c6b33e8e2d2..63694e174e5c 100644 --- a/tools/perf/util/symbol_fprintf.c +++ b/tools/perf/util/symbol_fprintf.c @@ -21,7 +21,7 @@ size_t __symbol__fprintf_symname_offs(const struct symbol *sym, unsigned long offset; size_t length; - if (sym && sym->name) { + if (sym) { length = fprintf(fp, "%s", sym->name); if (al && print_offsets) { if (al->addr < sym->end) diff --git a/tools/perf/util/term.c b/tools/perf/util/term.c index 90b47d8aa19c..8f254a74d97d 100644 --- a/tools/perf/util/term.c +++ b/tools/perf/util/term.c @@ -1,4 +1,8 @@ -#include "util.h" +#include "term.h" +#include <stdlib.h> +#include <termios.h> +#include <unistd.h> +#include <sys/ioctl.h> void get_term_dimensions(struct winsize *ws) { diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index d3301529f6a7..dd17d6a38d3a 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -15,6 +15,7 @@ #include <linux/rbtree.h> #include <linux/list.h> +#include <errno.h> #include "thread.h" #include "event.h" #include "machine.h" diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index f5af87f66663..378c418ca0c1 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -1,12 +1,15 @@ #include "../perf.h" +#include <errno.h> #include <stdlib.h> #include <stdio.h> #include <string.h> +#include <linux/kernel.h> #include "session.h" #include "thread.h" #include "thread-stack.h" #include "util.h" #include "debug.h" +#include "namespaces.h" #include "comm.h" #include "unwind.h" @@ -40,6 +43,7 @@ struct thread *thread__new(pid_t pid, pid_t tid) thread->tid = tid; thread->ppid = -1; thread->cpu = -1; + INIT_LIST_HEAD(&thread->namespaces_list); INIT_LIST_HEAD(&thread->comm_list); comm_str = malloc(32); @@ -53,7 +57,7 @@ struct thread *thread__new(pid_t pid, pid_t tid) goto err_thread; list_add(&comm->list, &thread->comm_list); - atomic_set(&thread->refcnt, 1); + refcount_set(&thread->refcnt, 1); RB_CLEAR_NODE(&thread->rb_node); } @@ -66,7 +70,8 @@ err_thread: void thread__delete(struct thread *thread) { - struct comm *comm, *tmp; + struct namespaces *namespaces, *tmp_namespaces; + struct comm *comm, *tmp_comm; BUG_ON(!RB_EMPTY_NODE(&thread->rb_node)); @@ -76,7 +81,12 @@ void thread__delete(struct thread *thread) map_groups__put(thread->mg); thread->mg = NULL; } - list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) { + list_for_each_entry_safe(namespaces, tmp_namespaces, + &thread->namespaces_list, list) { + list_del(&namespaces->list); + namespaces__free(namespaces); + } + list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) { list_del(&comm->list); comm__free(comm); } @@ -88,13 +98,13 @@ void thread__delete(struct thread *thread) struct thread *thread__get(struct thread *thread) { if (thread) - atomic_inc(&thread->refcnt); + refcount_inc(&thread->refcnt); return thread; } void thread__put(struct thread *thread) { - if (thread && atomic_dec_and_test(&thread->refcnt)) { + if (thread && refcount_dec_and_test(&thread->refcnt)) { /* * Remove it from the dead_threads list, as last reference * is gone. @@ -104,6 +114,38 @@ void thread__put(struct thread *thread) } } +struct namespaces *thread__namespaces(const struct thread *thread) +{ + if (list_empty(&thread->namespaces_list)) + return NULL; + + return list_first_entry(&thread->namespaces_list, struct namespaces, list); +} + +int thread__set_namespaces(struct thread *thread, u64 timestamp, + struct namespaces_event *event) +{ + struct namespaces *new, *curr = thread__namespaces(thread); + + new = namespaces__new(event); + if (!new) + return -ENOMEM; + + list_add(&new->list, &thread->namespaces_list); + + if (timestamp && curr) { + /* + * setns syscall must have changed few or all the namespaces + * of this thread. Update end time for the namespaces + * previously used. + */ + curr = list_next_entry(new, list); + curr->end_time = timestamp; + } + + return 0; +} + struct comm *thread__comm(const struct thread *thread) { if (list_empty(&thread->comm_list)) diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 99263cb6e6b6..4eb849e9098f 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -1,7 +1,7 @@ #ifndef __PERF_THREAD_H #define __PERF_THREAD_H -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/rbtree.h> #include <linux/list.h> #include <unistd.h> @@ -23,11 +23,12 @@ struct thread { pid_t tid; pid_t ppid; int cpu; - atomic_t refcnt; + refcount_t refcnt; char shortname[3]; bool comm_set; int comm_len; bool dead; /* if set thread has exited */ + struct list_head namespaces_list; struct list_head comm_list; u64 db_id; @@ -40,6 +41,7 @@ struct thread { }; struct machine; +struct namespaces; struct comm; struct thread *thread__new(pid_t pid, pid_t tid); @@ -62,6 +64,10 @@ static inline void thread__exited(struct thread *thread) thread->dead = true; } +struct namespaces *thread__namespaces(const struct thread *thread); +int thread__set_namespaces(struct thread *thread, u64 timestamp, + struct namespaces_event *event); + int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp, bool exec); static inline int thread__set_comm(struct thread *thread, const char *comm, diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index f9eab200fd75..63ead7b06324 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -1,4 +1,5 @@ #include <dirent.h> +#include <errno.h> #include <limits.h> #include <stdbool.h> #include <stdlib.h> @@ -6,6 +7,7 @@ #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> +#include "string2.h" #include "strlist.h" #include <string.h> #include <api/fs/fs.h> @@ -66,7 +68,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid) for (i = 0; i < items; i++) thread_map__set_pid(threads, i, atoi(namelist[i]->d_name)); threads->nr = items; - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); } for (i=0; i<items; i++) @@ -83,7 +85,7 @@ struct thread_map *thread_map__new_by_tid(pid_t tid) if (threads != NULL) { thread_map__set_pid(threads, 0, tid); threads->nr = 1; - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); } return threads; @@ -93,7 +95,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) { DIR *proc; int max_threads = 32, items, i; - char path[256]; + char path[NAME_MAX + 1 + 6]; struct dirent *dirent, **namelist = NULL; struct thread_map *threads = thread_map__alloc(max_threads); @@ -105,7 +107,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) goto out_free_threads; threads->nr = 0; - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); while ((dirent = readdir(proc)) != NULL) { char *end; @@ -235,7 +237,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) out: strlist__delete(slist); if (threads) - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); return threads; out_free_namelist: @@ -255,7 +257,7 @@ struct thread_map *thread_map__new_dummy(void) if (threads != NULL) { thread_map__set_pid(threads, 0, -1); threads->nr = 1; - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); } return threads; } @@ -300,7 +302,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str) } out: if (threads) - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); return threads; out_free_threads: @@ -326,7 +328,7 @@ static void thread_map__delete(struct thread_map *threads) if (threads) { int i; - WARN_ONCE(atomic_read(&threads->refcnt) != 0, + WARN_ONCE(refcount_read(&threads->refcnt) != 0, "thread map refcnt unbalanced\n"); for (i = 0; i < threads->nr; i++) free(thread_map__comm(threads, i)); @@ -337,13 +339,13 @@ static void thread_map__delete(struct thread_map *threads) struct thread_map *thread_map__get(struct thread_map *map) { if (map) - atomic_inc(&map->refcnt); + refcount_inc(&map->refcnt); return map; } void thread_map__put(struct thread_map *map) { - if (map && atomic_dec_and_test(&map->refcnt)) + if (map && refcount_dec_and_test(&map->refcnt)) thread_map__delete(map); } @@ -423,7 +425,7 @@ static void thread_map__copy_event(struct thread_map *threads, threads->map[i].comm = strndup(event->entries[i].comm, 16); } - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); } struct thread_map *thread_map__new_event(struct thread_map_event *event) diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index ea0ef08c6303..bd34d7a0b9fa 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -3,7 +3,7 @@ #include <sys/types.h> #include <stdio.h> -#include <linux/atomic.h> +#include <linux/refcount.h> struct thread_map_data { pid_t pid; @@ -11,7 +11,7 @@ struct thread_map_data { }; struct thread_map { - atomic_t refcnt; + refcount_t refcnt; int nr; struct thread_map_data map[]; }; diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c index d1b21c72206d..5b5d0214debd 100644 --- a/tools/perf/util/time-utils.c +++ b/tools/perf/util/time-utils.c @@ -117,3 +117,28 @@ bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp) return false; } + +int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz) +{ + u64 sec = timestamp / NSEC_PER_SEC; + u64 usec = (timestamp % NSEC_PER_SEC) / NSEC_PER_USEC; + + return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec); +} + +int fetch_current_timestamp(char *buf, 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(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000); + + return 0; +} diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h index c1f197c4af6c..8656be08513b 100644 --- a/tools/perf/util/time-utils.h +++ b/tools/perf/util/time-utils.h @@ -1,6 +1,9 @@ #ifndef _TIME_UTILS_H_ #define _TIME_UTILS_H_ +#include <stddef.h> +#include <linux/types.h> + struct perf_time_interval { u64 start, end; }; @@ -11,4 +14,8 @@ int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr); bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp); +int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz); + +int fetch_current_timestamp(char *buf, size_t sz); + #endif diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index ac2590a3de2d..829471a1c6d7 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -40,6 +40,7 @@ struct perf_tool { event_op mmap, mmap2, comm, + namespaces, fork, exit, lost, @@ -66,6 +67,7 @@ struct perf_tool { event_op3 auxtrace; bool ordered_events; bool ordering_requires_timestamps; + bool namespace_events; }; #endif /* __PERF_TOOL_H */ diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index b2940c88734a..9bdfb78a9a35 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -5,7 +5,7 @@ #include <linux/types.h> #include <stddef.h> #include <stdbool.h> -#include <termios.h> +#include <sys/ioctl.h> struct perf_evlist; struct perf_evsel; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index d995743cb673..e7d60d05596d 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -42,7 +42,7 @@ #include "evsel.h" #include "debug.h" -#define VERSION "0.5" +#define VERSION "0.6" static int output_fd; @@ -170,6 +170,12 @@ static bool name_in_tp_list(char *sys, struct tracepoint_path *tps) return false; } +#define for_each_event(dir, dent, tps) \ + while ((dent = readdir(dir))) \ + if (dent->d_type == DT_DIR && \ + (strcmp(dent->d_name, ".")) && \ + (strcmp(dent->d_name, ".."))) \ + static int copy_event_system(const char *sys, struct tracepoint_path *tps) { struct dirent *dent; @@ -186,12 +192,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps) return -errno; } - while ((dent = readdir(dir))) { - if (dent->d_type != DT_DIR || - strcmp(dent->d_name, ".") == 0 || - strcmp(dent->d_name, "..") == 0 || - !name_in_tp_list(dent->d_name, tps)) + for_each_event(dir, dent, tps) { + if (!name_in_tp_list(dent->d_name, tps)) continue; + if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) { err = -ENOMEM; goto out; @@ -210,12 +214,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps) } rewinddir(dir); - while ((dent = readdir(dir))) { - if (dent->d_type != DT_DIR || - strcmp(dent->d_name, ".") == 0 || - strcmp(dent->d_name, "..") == 0 || - !name_in_tp_list(dent->d_name, tps)) + for_each_event(dir, dent, tps) { + if (!name_in_tp_list(dent->d_name, tps)) continue; + if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) { err = -ENOMEM; goto out; @@ -290,13 +292,11 @@ static int record_event_files(struct tracepoint_path *tps) goto out; } - while ((dent = readdir(dir))) { - if (dent->d_type != DT_DIR || - strcmp(dent->d_name, ".") == 0 || - strcmp(dent->d_name, "..") == 0 || - strcmp(dent->d_name, "ftrace") == 0 || + for_each_event(dir, dent, tps) { + if (strcmp(dent->d_name, "ftrace") == 0 || !system_in_tp_list(dent->d_name, tps)) continue; + count++; } @@ -307,13 +307,11 @@ static int record_event_files(struct tracepoint_path *tps) } rewinddir(dir); - while ((dent = readdir(dir))) { - if (dent->d_type != DT_DIR || - strcmp(dent->d_name, ".") == 0 || - strcmp(dent->d_name, "..") == 0 || - strcmp(dent->d_name, "ftrace") == 0 || + for_each_event(dir, dent, tps) { + if (strcmp(dent->d_name, "ftrace") == 0 || !system_in_tp_list(dent->d_name, tps)) continue; + if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) { err = -ENOMEM; goto out; @@ -379,6 +377,34 @@ out: return err; } +static int record_saved_cmdline(void) +{ + unsigned int size; + char *path; + struct stat st; + int ret, err = 0; + + path = get_tracing_file("saved_cmdlines"); + if (!path) { + pr_debug("can't get tracing/saved_cmdline"); + return -ENOMEM; + } + + ret = stat(path, &st); + if (ret < 0) { + /* not found */ + size = 0; + if (write(output_fd, &size, 8) != 8) + err = -EIO; + goto out; + } + err = record_file(path, 8); + +out: + put_tracing_file(path); + return err; +} + static void put_tracepoints_path(struct tracepoint_path *tps) { @@ -539,6 +565,9 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs, if (err) goto out; err = record_ftrace_printk(); + if (err) + goto out; + err = record_saved_cmdline(); out: /* diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 33b52eaa39db..e0a6e9a6a053 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -21,13 +21,14 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <ctype.h> #include <errno.h> #include "../perf.h" -#include "util.h" +#include "debug.h" #include "trace-event.h" +#include "sane_ctype.h" + static int get_common_field(struct scripting_context *context, int *offset, int *size, const char *type) { @@ -149,7 +150,7 @@ void parse_ftrace_printk(struct pevent *pevent, while (line) { addr_str = strtok_r(line, ":", &fmt); if (!addr_str) { - warning("printk format with empty entry"); + pr_warning("printk format with empty entry"); break; } addr = strtoull(addr_str, NULL, 16); @@ -160,6 +161,23 @@ void parse_ftrace_printk(struct pevent *pevent, } } +void parse_saved_cmdline(struct pevent *pevent, + char *file, unsigned int size __maybe_unused) +{ + char *comm; + char *line; + char *next = NULL; + int pid; + + line = strtok_r(file, "\n", &next); + while (line) { + sscanf(line, "%d %ms", &pid, &comm); + pevent_register_comm(pevent, comm, pid); + free(comm); + line = strtok_r(NULL, "\n", &next); + } +} + int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size) { return pevent_parse_event(pevent, buf, size, "ftrace"); diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index b67a0ccf5ab9..8a9a677f7576 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -192,7 +192,7 @@ static int read_ftrace_printk(struct pevent *pevent) if (!size) return 0; - buf = malloc(size); + buf = malloc(size + 1); if (buf == NULL) return -1; @@ -201,6 +201,8 @@ static int read_ftrace_printk(struct pevent *pevent) return -1; } + buf[size] = '\0'; + parse_ftrace_printk(pevent, buf, size); free(buf); @@ -260,39 +262,53 @@ static int read_header_files(struct pevent *pevent) static int read_ftrace_file(struct pevent *pevent, unsigned long long size) { + int ret; char *buf; buf = malloc(size); - if (buf == NULL) + if (buf == NULL) { + pr_debug("memory allocation failure\n"); return -1; + } - if (do_read(buf, size) < 0) { - free(buf); - return -1; + ret = do_read(buf, size); + if (ret < 0) { + pr_debug("error reading ftrace file.\n"); + goto out; } - parse_ftrace_file(pevent, buf, size); + ret = parse_ftrace_file(pevent, buf, size); + if (ret < 0) + pr_debug("error parsing ftrace file.\n"); +out: free(buf); - return 0; + return ret; } static int read_event_file(struct pevent *pevent, char *sys, unsigned long long size) { + int ret; char *buf; buf = malloc(size); - if (buf == NULL) + if (buf == NULL) { + pr_debug("memory allocation failure\n"); return -1; + } - if (do_read(buf, size) < 0) { + ret = do_read(buf, size); + if (ret < 0) { free(buf); - return -1; + goto out; } - parse_event_file(pevent, buf, size, sys); + ret = parse_event_file(pevent, buf, size, sys); + if (ret < 0) + pr_debug("error parsing event file.\n"); +out: free(buf); - return 0; + return ret; } static int read_ftrace_files(struct pevent *pevent) @@ -341,6 +357,36 @@ static int read_event_files(struct pevent *pevent) return 0; } +static int read_saved_cmdline(struct pevent *pevent) +{ + unsigned long long size; + char *buf; + int ret; + + /* it can have 0 size */ + size = read8(pevent); + if (!size) + return 0; + + buf = malloc(size + 1); + if (buf == NULL) { + pr_debug("memory allocation failure\n"); + return -1; + } + + ret = do_read(buf, size); + if (ret < 0) { + pr_debug("error reading saved cmdlines\n"); + goto out; + } + + parse_saved_cmdline(pevent, buf, size); + ret = 0; +out: + free(buf); + return ret; +} + ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) { char buf[BUFSIZ]; @@ -379,10 +425,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) return -1; if (show_version) printf("version = %s\n", version); - free(version); - if (do_read(buf, 1) < 0) + if (do_read(buf, 1) < 0) { + free(version); return -1; + } file_bigendian = buf[0]; host_bigendian = bigendian(); @@ -423,6 +470,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) err = read_ftrace_printk(pevent); if (err) goto out; + if (atof(version) >= 0.6) { + err = read_saved_cmdline(pevent); + if (err) + goto out; + } size = trace_data_size; repipe = false; @@ -438,5 +490,6 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) out: if (pevent) trace_event__cleanup(tevent); + free(version); return size; } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index b0af9c81bb0d..1fbc044f9eb0 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -42,6 +42,7 @@ raw_field_value(struct event_format *event, const char *name, void *data); void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size); void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size); +void parse_saved_cmdline(struct pevent *pevent, char *file, unsigned int size); ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe); diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c new file mode 100644 index 000000000000..4767ec2c5ef6 --- /dev/null +++ b/tools/perf/util/units.c @@ -0,0 +1,68 @@ +#include "units.h" +#include <inttypes.h> +#include <limits.h> +#include <stdlib.h> +#include <string.h> +#include <linux/kernel.h> +#include <linux/time64.h> + +unsigned long parse_tag_value(const char *str, struct parse_tag *tags) +{ + struct parse_tag *i = tags; + + while (i->tag) { + char *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; +} + +unsigned long convert_unit(unsigned long value, char *unit) +{ + *unit = ' '; + + if (value > 1000) { + value /= 1000; + *unit = 'K'; + } + + if (value > 1000) { + value /= 1000; + *unit = 'M'; + } + + if (value > 1000) { + value /= 1000; + *unit = 'G'; + } + + return value; +} + +int unit_number__scnprintf(char *buf, size_t size, u64 n) +{ + char unit[4] = "BKMG"; + int i = 0; + + while (((n / 1024) > 1) && (i < 3)) { + n /= 1024; + i++; + } + + return scnprintf(buf, size, "%" PRIu64 "%c", n, unit[i]); +} diff --git a/tools/perf/util/units.h b/tools/perf/util/units.h new file mode 100644 index 000000000000..f02c87317150 --- /dev/null +++ b/tools/perf/util/units.h @@ -0,0 +1,17 @@ +#ifndef PERF_UNIT_H +#define PERF_UNIT_H + +#include <stddef.h> +#include <linux/types.h> + +struct parse_tag { + char tag; + int mult; +}; + +unsigned long parse_tag_value(const char *str, struct parse_tag *tags); + +unsigned long convert_unit(unsigned long value, char *unit); +int unit_number__scnprintf(char *buf, size_t size, u64 n); + +#endif /* PERF_UNIT_H */ diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 783a53fb7a4e..7755a5e0fe5e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -12,6 +12,7 @@ #include "event.h" #include "perf_regs.h" #include "callchain.h" +#include "util.h" static char *debuginfo_path; @@ -38,6 +39,14 @@ static int __report_module(struct addr_location *al, u64 ip, return 0; mod = dwfl_addrmodule(ui->dwfl, ip); + if (mod) { + Dwarf_Addr s; + + dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL); + if (s != al->map->start) + mod = 0; + } + if (!mod) mod = dwfl_report_elf(ui->dwfl, dso->short_name, dso->long_name, -1, al->map->start, @@ -167,12 +176,24 @@ frame_callback(Dwfl_Frame *state, void *arg) { struct unwind_info *ui = arg; Dwarf_Addr pc; + bool isactivation; if (!dwfl_frame_pc(state, &pc, NULL)) { pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } + // report the module before we query for isactivation + report_module(pc, ui); + + if (!dwfl_frame_pc(state, &pc, &isactivation)) { + pr_err("%s", dwfl_errmsg(-1)); + return DWARF_CB_ABORT; + } + + if (!isactivation) + --pc; + return entry(pc, ui) || !(--ui->max_stack) ? DWARF_CB_ABORT : DWARF_CB_OK; } @@ -219,7 +240,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui); - if (err && !ui->max_stack) + if (err && ui->max_stack != max_stack) err = 0; /* diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h index 58328669ed16..4a2b269a7b3b 100644 --- a/tools/perf/util/unwind-libdw.h +++ b/tools/perf/util/unwind-libdw.h @@ -2,10 +2,12 @@ #define __PERF_UNWIND_LIBDW_H #include <elfutils/libdwfl.h> -#include "event.h" -#include "thread.h" #include "unwind.h" +struct machine; +struct perf_sample; +struct thread; + bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg); struct unwind_info { diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 6fec84dff3f7..672c2ada9357 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -16,8 +16,10 @@ */ #include <elf.h> +#include <errno.h> #include <gelf.h> #include <fcntl.h> +#include <inttypes.h> #include <string.h> #include <unistd.h> #include <sys/mman.h> @@ -35,6 +37,7 @@ #include "util.h" #include "debug.h" #include "asm/bug.h" +#include "dso.h" extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, @@ -297,15 +300,58 @@ static int read_unwind_spec_debug_frame(struct dso *dso, int fd; u64 ofs = dso->data.debug_frame_offset; + /* debug_frame can reside in: + * - dso + * - debug pointed by symsrc_filename + * - gnu_debuglink, which doesn't necessary + * has to be pointed by symsrc_filename + */ if (ofs == 0) { fd = dso__data_get_fd(dso, machine); - if (fd < 0) - return -EINVAL; + if (fd >= 0) { + ofs = elf_section_offset(fd, ".debug_frame"); + dso__data_put_fd(dso); + } + + if (ofs <= 0) { + fd = open(dso->symsrc_filename, O_RDONLY); + if (fd >= 0) { + ofs = elf_section_offset(fd, ".debug_frame"); + close(fd); + } + } + + if (ofs <= 0) { + char *debuglink = malloc(PATH_MAX); + int ret = 0; + + ret = dso__read_binary_type_filename( + dso, DSO_BINARY_TYPE__DEBUGLINK, + machine->root_dir, debuglink, PATH_MAX); + if (!ret) { + fd = open(debuglink, O_RDONLY); + if (fd >= 0) { + ofs = elf_section_offset(fd, + ".debug_frame"); + close(fd); + } + } + if (ofs > 0) { + if (dso->symsrc_filename != NULL) { + pr_warning( + "%s: overwrite symsrc(%s,%s)\n", + __func__, + dso->symsrc_filename, + debuglink); + free(dso->symsrc_filename); + } + dso->symsrc_filename = debuglink; + } else { + free(debuglink); + } + } - /* Check the .debug_frame section for unwinding info */ - ofs = elf_section_offset(fd, ".debug_frame"); dso->data.debug_frame_offset = ofs; - dso__data_put_fd(dso); } *offset = ofs; @@ -646,6 +692,17 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, while (!ret && (unw_step(&c) > 0) && i < max_stack) { unw_get_reg(&c, UNW_REG_IP, &ips[i]); + + /* + * Decrement the IP for any non-activation frames. + * this is required to properly find the srcline + * for caller frames. + * See also the documentation for dwfl_frame_pc(), + * which this code tries to replicate. + */ + if (unw_is_signal_frame(&c) <= 0) + --ips[i]; + ++i; } diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 6d542a4e0648..8aef572d0889 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -50,7 +50,7 @@ int unwind__prepare_access(struct thread *thread, struct map *map, if (!ops) { pr_err("unwind: target platform=%s is not supported\n", arch); - return -1; + return 0; } out_register: unwind__register_ops(thread, ops); diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index 61fb1e90ff51..bfbdcc6198c9 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -1,10 +1,13 @@ #ifndef __UNWIND_H #define __UNWIND_H +#include <linux/compiler.h> #include <linux/types.h> -#include "event.h" -#include "symbol.h" -#include "thread.h" + +struct map; +struct perf_sample; +struct symbol; +struct thread; struct unwind_entry { struct map *map; diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c index 996046a66fe5..6cc9d9888ce0 100644 --- a/tools/perf/util/usage.c +++ b/tools/perf/util/usage.c @@ -9,75 +9,17 @@ #include "util.h" #include "debug.h" -static void report(const char *prefix, const char *err, va_list params) -{ - char msg[1024]; - vsnprintf(msg, sizeof(msg), err, params); - fprintf(stderr, " %s%s\n", prefix, msg); -} - -static NORETURN void usage_builtin(const char *err) +static __noreturn void usage_builtin(const char *err) { fprintf(stderr, "\n Usage: %s\n", err); exit(129); } -static NORETURN void die_builtin(const char *err, va_list params) -{ - report(" Fatal: ", err, params); - exit(128); -} - -static void error_builtin(const char *err, va_list params) -{ - report(" Error: ", err, params); -} - -static void warn_builtin(const char *warn, va_list params) -{ - report(" Warning: ", warn, params); -} - /* If we are in a dlopen()ed .so write to a global variable would segfault * (ugh), so keep things static. */ -static void (*usage_routine)(const char *err) NORETURN = usage_builtin; -static void (*error_routine)(const char *err, va_list params) = error_builtin; -static void (*warn_routine)(const char *err, va_list params) = warn_builtin; - -void set_warning_routine(void (*routine)(const char *err, va_list params)) -{ - warn_routine = routine; -} +static void (*usage_routine)(const char *err) __noreturn = usage_builtin; void usage(const char *err) { usage_routine(err); } - -void die(const char *err, ...) -{ - va_list params; - - va_start(params, err); - die_builtin(err, params); - va_end(params); -} - -int error(const char *err, ...) -{ - va_list params; - - va_start(params, err); - error_routine(err, params); - va_end(params); - return -1; -} - -void warning(const char *warn, ...) -{ - va_list params; - - va_start(params, warn); - warn_routine(warn, params); - va_end(params); -} diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 9ddd98827d12..988111e0bab5 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -3,38 +3,22 @@ #include "debug.h" #include <api/fs/fs.h> #include <sys/mman.h> +#include <sys/stat.h> #include <sys/utsname.h> -#ifdef HAVE_BACKTRACE_SUPPORT -#include <execinfo.h> -#endif +#include <dirent.h> +#include <inttypes.h> +#include <signal.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <errno.h> #include <limits.h> -#include <byteswap.h> #include <linux/kernel.h> #include <linux/log2.h> #include <linux/time64.h> #include <unistd.h> -#include "callchain.h" #include "strlist.h" -#define CALLCHAIN_PARAM_DEFAULT \ - .mode = CHAIN_GRAPH_ABS, \ - .min_percent = 0.5, \ - .order = ORDER_CALLEE, \ - .key = CCKEY_FUNCTION, \ - .value = CCVAL_PERCENT, \ - -struct callchain_param callchain_param = { - CALLCHAIN_PARAM_DEFAULT -}; - -struct callchain_param callchain_param_default = { - CALLCHAIN_PARAM_DEFAULT -}; - /* * XXX We need to find a better place for these things... */ @@ -85,7 +69,7 @@ int mkdir_p(char *path, mode_t mode) return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0; } -int rm_rf(char *path) +int rm_rf(const char *path) { DIR *dir; int ret = 0; @@ -269,28 +253,6 @@ int copyfile(const char *from, const char *to) return copyfile_mode(from, to, 0755); } -unsigned long convert_unit(unsigned long value, char *unit) -{ - *unit = ' '; - - if (value > 1000) { - value /= 1000; - *unit = 'K'; - } - - if (value > 1000) { - value /= 1000; - *unit = 'M'; - } - - if (value > 1000) { - value /= 1000; - *unit = 'G'; - } - - return value; -} - static ssize_t ion(bool is_read, int fd, void *buf, size_t n) { void *buf_start = buf; @@ -372,171 +334,6 @@ int hex2u64(const char *ptr, u64 *long_val) return p - ptr; } -/* Obtain a backtrace and print it to stdout. */ -#ifdef HAVE_BACKTRACE_SUPPORT -void dump_stack(void) -{ - void *array[16]; - size_t size = backtrace(array, ARRAY_SIZE(array)); - char **strings = backtrace_symbols(array, size); - size_t i; - - printf("Obtained %zd stack frames.\n", size); - - for (i = 0; i < size; i++) - printf("%s\n", strings[i]); - - free(strings); -} -#else -void dump_stack(void) {} -#endif - -void sighandler_dump_stack(int sig) -{ - psignal(sig, "perf"); - dump_stack(); - signal(sig, SIG_DFL); - raise(sig); -} - -int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz) -{ - u64 sec = timestamp / NSEC_PER_SEC; - u64 usec = (timestamp % NSEC_PER_SEC) / NSEC_PER_USEC; - - return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec); -} - -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 get_stack_size(const char *str, unsigned long *_size) -{ - char *endptr; - unsigned long size; - unsigned long max_size = round_down(USHRT_MAX, sizeof(u64)); - - size = strtoul(str, &endptr, 0); - - do { - if (*endptr) - break; - - size = round_up(size, sizeof(u64)); - if (!size || size > max_size) - break; - - *_size = size; - return 0; - - } while (0); - - pr_err("callchain: Incorrect stack dump size (max %ld): %s\n", - max_size, str); - return -1; -} - -int parse_callchain_record(const char *arg, struct callchain_param *param) -{ - char *tok, *name, *saveptr = NULL; - char *buf; - int ret = -1; - - /* We need buffer that we know we can write to. */ - buf = malloc(strlen(arg) + 1); - if (!buf) - return -ENOMEM; - - strcpy(buf, arg); - - tok = strtok_r((char *)buf, ",", &saveptr); - name = tok ? : (char *)buf; - - do { - /* Framepointer style */ - if (!strncmp(name, "fp", sizeof("fp"))) { - if (!strtok_r(NULL, ",", &saveptr)) { - param->record_mode = CALLCHAIN_FP; - ret = 0; - } else - pr_err("callchain: No more arguments " - "needed for --call-graph fp\n"); - break; - - /* Dwarf style */ - } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { - const unsigned long default_stack_dump_size = 8192; - - ret = 0; - param->record_mode = CALLCHAIN_DWARF; - param->dump_size = default_stack_dump_size; - - tok = strtok_r(NULL, ",", &saveptr); - if (tok) { - unsigned long size = 0; - - ret = get_stack_size(tok, &size); - param->dump_size = size; - } - } else if (!strncmp(name, "lbr", sizeof("lbr"))) { - if (!strtok_r(NULL, ",", &saveptr)) { - param->record_mode = CALLCHAIN_LBR; - ret = 0; - } else - pr_err("callchain: No more arguments " - "needed for --call-graph lbr\n"); - break; - } else { - pr_err("callchain: Unknown --call-graph option " - "value: %s\n", arg); - break; - } - - } while (0); - - free(buf); - return ret; -} - -const char *get_filename_for_perf_kvm(void) -{ - const char *filename; - - if (perf_host && !perf_guest) - filename = strdup("perf.data.host"); - else if (!perf_host && perf_guest) - filename = strdup("perf.data.guest"); - else - filename = strdup("perf.data.kvm"); - - return filename; -} - int perf_event_paranoid(void) { int value; @@ -546,64 +343,6 @@ int perf_event_paranoid(void) return value; } - -void mem_bswap_32(void *src, int byte_size) -{ - u32 *m = src; - while (byte_size > 0) { - *m = bswap_32(*m); - byte_size -= sizeof(u32); - ++m; - } -} - -void mem_bswap_64(void *src, int byte_size) -{ - u64 *m = src; - - while (byte_size > 0) { - *m = bswap_64(*m); - byte_size -= sizeof(u64); - ++m; - } -} - -bool find_process(const char *name) -{ - size_t len = strlen(name); - DIR *dir; - struct dirent *d; - int ret = -1; - - dir = opendir(procfs__mountpoint()); - if (!dir) - return false; - - /* Walk through the directory. */ - while (ret && (d = readdir(dir)) != NULL) { - char path[PATH_MAX]; - char *data; - size_t size; - - if ((d->d_type != DT_DIR) || - !strcmp(".", d->d_name) || - !strcmp("..", d->d_name)) - continue; - - scnprintf(path, sizeof(path), "%s/%s/comm", - procfs__mountpoint(), d->d_name); - - if (filename__read_str(path, &data, &size)) - continue; - - ret = strncmp(name, data, len); - free(data); - } - - closedir(dir); - return ret ? false : true; -} - static int fetch_ubuntu_kernel_version(unsigned int *puint) { @@ -611,8 +350,12 @@ fetch_ubuntu_kernel_version(unsigned int *puint) size_t line_len = 0; char *ptr, *line = NULL; int version, patchlevel, sublevel, err; - FILE *vsig = fopen("/proc/version_signature", "r"); + FILE *vsig; + + if (!puint) + return 0; + vsig = fopen("/proc/version_signature", "r"); if (!vsig) { pr_debug("Open /proc/version_signature failed: %s\n", strerror(errno)); @@ -642,8 +385,7 @@ fetch_ubuntu_kernel_version(unsigned int *puint) goto errout; } - if (puint) - *puint = (version << 16) + (patchlevel << 8) + sublevel; + *puint = (version << 16) + (patchlevel << 8) + sublevel; err = 0; errout: free(line); @@ -670,6 +412,9 @@ fetch_kernel_version(unsigned int *puint, char *str, str[str_size - 1] = '\0'; } + if (!puint || int_ver_ready) + return 0; + err = sscanf(utsname.release, "%d.%d.%d", &version, &patchlevel, &sublevel); @@ -679,8 +424,7 @@ fetch_kernel_version(unsigned int *puint, char *str, return -1; } - if (puint && !int_ver_ready) - *puint = (version << 16) + (patchlevel << 8) + sublevel; + *puint = (version << 16) + (patchlevel << 8) + sublevel; return 0; } @@ -696,7 +440,8 @@ const char *perf_tip(const char *dirpath) tips = strlist__new("tips.txt", &conf); if (tips == NULL) - return errno == ENOENT ? NULL : "Tip: get more memory! ;-p"; + return errno == ENOENT ? NULL : + "Tip: check path of tips.txt or get more memory! ;-p"; if (strlist__nr_entries(tips) == 0) goto out; @@ -710,82 +455,3 @@ out: return tip; } - -bool is_regular_file(const char *file) -{ - struct stat st; - - if (stat(file, &st)) - return false; - - return S_ISREG(st.st_mode); -} - -int fetch_current_timestamp(char *buf, 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(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000); - - return 0; -} - -void print_binary(unsigned char *data, size_t len, - size_t bytes_per_line, print_binary_t printer, - void *extra) -{ - size_t i, j, mask; - - if (!printer) - return; - - bytes_per_line = roundup_pow_of_two(bytes_per_line); - mask = bytes_per_line - 1; - - printer(BINARY_PRINT_DATA_BEGIN, 0, extra); - for (i = 0; i < len; i++) { - if ((i & mask) == 0) { - printer(BINARY_PRINT_LINE_BEGIN, -1, extra); - printer(BINARY_PRINT_ADDR, i, extra); - } - - printer(BINARY_PRINT_NUM_DATA, data[i], extra); - - if (((i & mask) == mask) || i == len - 1) { - for (j = 0; j < mask-(i & mask); j++) - printer(BINARY_PRINT_NUM_PAD, -1, extra); - - printer(BINARY_PRINT_SEP, i, extra); - for (j = i & ~mask; j <= i; j++) - printer(BINARY_PRINT_CHAR_DATA, data[j], extra); - for (j = 0; j < mask-(i & mask); j++) - printer(BINARY_PRINT_CHAR_PAD, i, extra); - printer(BINARY_PRINT_LINE_END, -1, extra); - } - } - printer(BINARY_PRINT_DATA_END, -1, extra); -} - -int is_printable_array(char *p, unsigned int len) -{ - unsigned int i; - - if (!p || !len || p[len - 1] != 0) - return 0; - - len--; - - for (i = 0; i < len; i++) { - if (!isprint(p[i]) && !isspace(p[i])) - return 0; - } - return 1; -} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 1d639e38aa82..2c9e58a45310 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -1,163 +1,21 @@ #ifndef GIT_COMPAT_UTIL_H #define GIT_COMPAT_UTIL_H -#ifndef FLEX_ARRAY -/* - * See if our compiler is known to support flexible array members. - */ -#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) -# define FLEX_ARRAY /* empty */ -#elif defined(__GNUC__) -# if (__GNUC__ >= 3) -# define FLEX_ARRAY /* empty */ -# else -# define FLEX_ARRAY 0 /* older GNU extension */ -# endif -#endif - -/* - * Otherwise, default to safer but a bit wasteful traditional style - */ -#ifndef FLEX_ARRAY -# define FLEX_ARRAY 1 -#endif -#endif - -#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0])) - -#ifdef __GNUC__ -#define TYPEOF(x) (__typeof__(x)) -#else -#define TYPEOF(x) -#endif - -#define MSB(x, bits) ((x) & TYPEOF(x)(~0ULL << (sizeof(x) * 8 - (bits)))) -#define HAS_MULTI_BITS(i) ((i) & ((i) - 1)) /* checks if an integer has more than 1 bit set */ - -/* Approximation of the length of the decimal representation of this type. */ -#define decimal_length(x) ((int)(sizeof(x) * 2.56 + 0.5) + 1) - -#define _ALL_SOURCE 1 #define _BSD_SOURCE 1 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */ #define _DEFAULT_SOURCE 1 -#define HAS_BOOL -#include <unistd.h> -#include <stdio.h> -#include <sys/stat.h> -#include <sys/statfs.h> #include <fcntl.h> #include <stdbool.h> #include <stddef.h> #include <stdlib.h> #include <stdarg.h> -#include <string.h> -#include <term.h> -#include <errno.h> -#include <limits.h> -#include <sys/param.h> -#include <sys/types.h> -#include <dirent.h> -#include <sys/time.h> -#include <time.h> -#include <signal.h> -#include <fnmatch.h> -#include <assert.h> -#include <regex.h> -#include <utime.h> -#include <sys/wait.h> -#include <poll.h> -#include <sys/socket.h> -#include <sys/ioctl.h> -#include <inttypes.h> -#include <linux/kernel.h> +#include <linux/compiler.h> #include <linux/types.h> -#include <sys/ttydefaults.h> -#include <api/fs/tracing_path.h> -#include <termios.h> -#include <linux/bitops.h> -#include <termios.h> -#include "strlist.h" - -extern const char *graph_line; -extern const char *graph_dotted_line; -extern const char *spaces; -extern const char *dots; -extern char buildid_dir[]; - -/* On most systems <limits.h> would have given us this, but - * not on some systems (e.g. GNU/Hurd). - */ -#ifndef PATH_MAX -#define PATH_MAX 4096 -#endif - -#ifndef PRIuMAX -#define PRIuMAX "llu" -#endif - -#ifndef PRIu32 -#define PRIu32 "u" -#endif - -#ifndef PRIx32 -#define PRIx32 "x" -#endif - -#ifndef PATH_SEP -#define PATH_SEP ':' -#endif - -#ifndef STRIP_EXTENSION -#define STRIP_EXTENSION "" -#endif - -#ifndef has_dos_drive_prefix -#define has_dos_drive_prefix(path) 0 -#endif - -#ifndef is_dir_sep -#define is_dir_sep(c) ((c) == '/') -#endif - -#ifdef __GNUC__ -#define NORETURN __attribute__((__noreturn__)) -#else -#define NORETURN -#ifndef __attribute__ -#define __attribute__(x) -#endif -#endif - -#define PERF_GTK_DSO "libperf-gtk.so" /* General helper functions */ -void usage(const char *err) NORETURN; -void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2))); -int error(const char *err, ...) __attribute__((format (printf, 1, 2))); -void warning(const char *err, ...) __attribute__((format (printf, 1, 2))); - -void set_warning_routine(void (*routine)(const char *err, va_list params)); - -int prefixcmp(const char *str, const char *prefix); -void set_buildid_dir(const char *dir); - -#ifdef __GLIBC_PREREQ -#if __GLIBC_PREREQ(2, 1) -#define HAVE_STRCHRNUL -#endif -#endif - -#ifndef HAVE_STRCHRNUL -#define strchrnul gitstrchrnul -static inline char *gitstrchrnul(const char *s, int c) -{ - while (*s && *s != c) - s++; - return (char *)s; -} -#endif +void usage(const char *err) __noreturn; +void die(const char *err, ...) __noreturn __printf(1, 2); static inline void *zalloc(size_t size) { @@ -166,161 +24,25 @@ static inline void *zalloc(size_t size) #define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) -/* Sane ctype - no locale, and works with signed chars */ -#undef isascii -#undef isspace -#undef isdigit -#undef isxdigit -#undef isalpha -#undef isprint -#undef isalnum -#undef islower -#undef isupper -#undef tolower -#undef toupper - -extern unsigned char sane_ctype[256]; -#define GIT_SPACE 0x01 -#define GIT_DIGIT 0x02 -#define GIT_ALPHA 0x04 -#define GIT_GLOB_SPECIAL 0x08 -#define GIT_REGEX_SPECIAL 0x10 -#define GIT_PRINT_EXTRA 0x20 -#define GIT_PRINT 0x3E -#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0) -#define isascii(x) (((x) & ~0x7f) == 0) -#define isspace(x) sane_istest(x,GIT_SPACE) -#define isdigit(x) sane_istest(x,GIT_DIGIT) -#define isxdigit(x) \ - (sane_istest(toupper(x), GIT_ALPHA | GIT_DIGIT) && toupper(x) < 'G') -#define isalpha(x) sane_istest(x,GIT_ALPHA) -#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT) -#define isprint(x) sane_istest(x,GIT_PRINT) -#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20)) -#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20)) -#define tolower(x) sane_case((unsigned char)(x), 0x20) -#define toupper(x) sane_case((unsigned char)(x), 0) - -static inline int sane_case(int x, int high) -{ - if (sane_istest(x, GIT_ALPHA)) - x = (x & ~0x20) | high; - return x; -} +struct dirent; +struct strlist; int mkdir_p(char *path, mode_t mode); -int rm_rf(char *path); +int rm_rf(const char *path); struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *)); bool lsdir_no_dot_filter(const char *name, struct dirent *d); int copyfile(const char *from, const char *to); int copyfile_mode(const char *from, const char *to, mode_t mode); int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size); -s64 perf_atoll(const char *str); -char **argv_split(const char *str, int *argcp); -void argv_free(char **argv); -bool strglobmatch(const char *str, const char *pat); -bool strglobmatch_nocase(const char *str, const char *pat); -bool strlazymatch(const char *str, const char *pat); -static inline bool strisglob(const char *str) -{ - return strpbrk(str, "*?[") != NULL; -} -int strtailcmp(const char *s1, const char *s2); -char *strxfrchar(char *s, char from, char to); -unsigned long convert_unit(unsigned long value, char *unit); ssize_t readn(int fd, void *buf, size_t n); ssize_t writen(int fd, void *buf, size_t n); -struct perf_event_attr; - -void event_attr_init(struct perf_event_attr *attr); - -#define _STR(x) #x -#define STR(x) _STR(x) - size_t hex_width(u64 v); int hex2u64(const char *ptr, u64 *val); -char *ltrim(char *s); -char *rtrim(char *s); - -static inline char *trim(char *s) -{ - return ltrim(rtrim(s)); -} - -void dump_stack(void); -void sighandler_dump_stack(int sig); - extern unsigned int page_size; extern int cacheline_size; -extern int sysctl_perf_event_max_stack; -extern int sysctl_perf_event_max_contexts_per_stack; - -struct parse_tag { - char tag; - int mult; -}; - -unsigned long parse_tag_value(const char *str, struct parse_tag *tags); - -#define SRCLINE_UNKNOWN ((char *) "??:0") - -static inline int path__join(char *bf, size_t size, - const char *path1, const char *path2) -{ - return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2); -} - -static inline int path__join3(char *bf, size_t size, - const char *path1, const char *path2, - const char *path3) -{ - return scnprintf(bf, size, "%s%s%s%s%s", - path1, path1[0] ? "/" : "", - path2, path2[0] ? "/" : "", path3); -} - -struct dso; -struct symbol; - -extern bool srcline_full_filename; -char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, - bool show_sym); -char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, - bool show_sym, bool unwind_inlines); -void free_srcline(char *srcline); - -int perf_event_paranoid(void); - -void mem_bswap_64(void *src, int byte_size); -void mem_bswap_32(void *src, int byte_size); - -const char *get_filename_for_perf_kvm(void); -bool find_process(const char *name); - -#ifdef HAVE_ZLIB_SUPPORT -int gzip_decompress_to_file(const char *input, int output_fd); -#endif - -#ifdef HAVE_LZMA_SUPPORT -int lzma_decompress_to_file(const char *input, int output_fd); -#endif - -char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints); - -static inline char *asprintf_expr_in_ints(const char *var, size_t nints, int *ints) -{ - return asprintf_expr_inout_ints(var, true, nints, ints); -} - -static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int *ints) -{ - return asprintf_expr_inout_ints(var, false, nints, ints); -} - -int get_stack_size(const char *str, unsigned long *_size); int fetch_kernel_version(unsigned int *puint, char *str, size_t str_sz); @@ -331,36 +53,9 @@ int fetch_kernel_version(unsigned int *puint, #define KVER_PARAM(x) KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x) const char *perf_tip(const char *dirpath); -bool is_regular_file(const char *file); -int fetch_current_timestamp(char *buf, size_t sz); -enum binary_printer_ops { - BINARY_PRINT_DATA_BEGIN, - BINARY_PRINT_LINE_BEGIN, - BINARY_PRINT_ADDR, - BINARY_PRINT_NUM_DATA, - BINARY_PRINT_NUM_PAD, - BINARY_PRINT_SEP, - BINARY_PRINT_CHAR_DATA, - BINARY_PRINT_CHAR_PAD, - BINARY_PRINT_LINE_END, - BINARY_PRINT_DATA_END, -}; - -typedef void (*print_binary_t)(enum binary_printer_ops, - unsigned int val, - void *extra); - -void print_binary(unsigned char *data, size_t len, - size_t bytes_per_line, print_binary_t printer, - void *extra); - -#if !defined(__GLIBC__) && !defined(__ANDROID__) -extern int sched_getcpu(void); +#ifndef HAVE_SCHED_GETCPU_SUPPORT +int sched_getcpu(void); #endif -int is_printable_array(char *p, unsigned int len); - -int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz); - #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index 5074be4ed467..5de2e15e2eda 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -1,4 +1,7 @@ +#include <inttypes.h> +#include <stdio.h> #include <stdlib.h> +#include <errno.h> #include "util.h" #include "values.h" @@ -108,24 +111,45 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values, return i; } -static void perf_read_values__enlarge_counters(struct perf_read_values *values) +static int perf_read_values__enlarge_counters(struct perf_read_values *values) { - int i; + char **countername; + int i, counters_max = values->counters_max * 2; + u64 *counterrawid = realloc(values->counterrawid, counters_max * sizeof(*values->counterrawid)); + + if (!counterrawid) { + pr_debug("failed to enlarge read_values rawid array"); + goto out_enomem; + } - values->counters_max *= 2; - values->counterrawid = realloc(values->counterrawid, - values->counters_max * sizeof(*values->counterrawid)); - values->countername = realloc(values->countername, - values->counters_max * sizeof(*values->countername)); - if (!values->counterrawid || !values->countername) - die("failed to enlarge read_values counters arrays"); + countername = realloc(values->countername, counters_max * sizeof(*values->countername)); + if (!countername) { + pr_debug("failed to enlarge read_values rawid array"); + goto out_free_rawid; + } for (i = 0; i < values->threads; i++) { - values->value[i] = realloc(values->value[i], - values->counters_max * sizeof(**values->value)); - if (!values->value[i]) - die("failed to enlarge read_values counters arrays"); + u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value)); + + if (value) { + pr_debug("failed to enlarge read_values ->values array"); + goto out_free_name; + } + + values->value[i] = value; } + + values->counters_max = counters_max; + values->counterrawid = counterrawid; + values->countername = countername; + + return 0; +out_free_name: + free(countername); +out_free_rawid: + free(counterrawid); +out_enomem: + return -ENOMEM; } static int perf_read_values__findnew_counter(struct perf_read_values *values, @@ -137,8 +161,11 @@ static int perf_read_values__findnew_counter(struct perf_read_values *values, if (values->counterrawid[i] == rawid) return i; - if (values->counters == values->counters_max) - perf_read_values__enlarge_counters(values); + if (values->counters == values->counters_max) { + i = perf_read_values__enlarge_counters(values); + if (i) + return i; + } i = values->counters++; values->counterrawid[i] = rawid; @@ -172,8 +199,10 @@ static void perf_read_values__display_pretty(FILE *fp, int *counterwidth; counterwidth = malloc(values->counters * sizeof(*counterwidth)); - if (!counterwidth) - die("failed to allocate counterwidth array"); + if (!counterwidth) { + fprintf(fp, "INTERNAL ERROR: Failed to allocate counterwidth array\n"); + return; + } tidwidth = 3; pidwidth = 3; for (j = 0; j < values->counters; j++) diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 7bdcad484225..d3c39eec89a8 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -1,4 +1,4 @@ - +#include <errno.h> #include <unistd.h> #include <stdio.h> #include <string.h> diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c index c10ba41ef3f6..7251fdbabced 100644 --- a/tools/perf/util/xyarray.c +++ b/tools/perf/util/xyarray.c @@ -1,5 +1,7 @@ #include "xyarray.h" #include "util.h" +#include <stdlib.h> +#include <string.h> struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size) { diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c index 495a449fc25c..1329d843eb7b 100644 --- a/tools/perf/util/zlib.c +++ b/tools/perf/util/zlib.c @@ -4,6 +4,7 @@ #include <sys/mman.h> #include <zlib.h> +#include "util/compress.h" #include "util/util.h" #include "util/debug.h" |
