diff options
Diffstat (limited to 'tools/perf')
295 files changed, 10836 insertions, 3017 deletions
diff --git a/tools/perf/Documentation/intel-hybrid.txt b/tools/perf/Documentation/intel-hybrid.txt index e7a776ad25d7..0379903673a4 100644 --- a/tools/perf/Documentation/intel-hybrid.txt +++ b/tools/perf/Documentation/intel-hybrid.txt @@ -8,15 +8,15 @@ Part of events are available on core cpu, part of events are available on atom cpu and even part of events are available on both. Kernel exports two new cpu pmus via sysfs: -/sys/devices/cpu_core -/sys/devices/cpu_atom +/sys/bus/event_source/devices/cpu_core +/sys/bus/event_source/devices/cpu_atom The 'cpus' files are created under the directories. For example, -cat /sys/devices/cpu_core/cpus +cat /sys/bus/event_source/devices/cpu_core/cpus 0-15 -cat /sys/devices/cpu_atom/cpus +cat /sys/bus/event_source/devices/cpu_atom/cpus 16-23 It indicates cpu0-cpu15 are core cpus and cpu16-cpu23 are atom cpus. @@ -60,8 +60,8 @@ can't carry pmu information. So now this type is extended to be PMU aware type. The PMU type ID is stored at attr.config[63:32]. PMU type ID is retrieved from sysfs. -/sys/devices/cpu_atom/type -/sys/devices/cpu_core/type +/sys/bus/event_source/devices/cpu_atom/type +/sys/bus/event_source/devices/cpu_core/type The new attr.config layout for PERF_TYPE_HARDWARE: diff --git a/tools/perf/Documentation/perf-arm-spe.txt b/tools/perf/Documentation/perf-arm-spe.txt index de2b0b479249..37afade4f1b2 100644 --- a/tools/perf/Documentation/perf-arm-spe.txt +++ b/tools/perf/Documentation/perf-arm-spe.txt @@ -150,6 +150,7 @@ arm_spe/load_filter=1,min_latency=10/' pct_enable=1 - collect physical timestamp instead of virtual timestamp (PMSCR.PCT) - requires privilege store_filter=1 - collect stores only (PMSFCR.ST) ts_enable=1 - enable timestamping with value of generic timer (PMSCR.TS) + discard=1 - enable SPE PMU events but don't collect sample data - see 'Discard mode' (PMBLIMITR.FM = DISCARD) +++*+++ Latency is the total latency from the point at which sampling started on that instruction, rather than only the execution latency. @@ -220,6 +221,31 @@ Common errors Increase sampling interval (see above) +PMU events +~~~~~~~~~~ + +SPE has events that can be counted on core PMUs. These are prefixed with +SAMPLE_, for example SAMPLE_POP, SAMPLE_FEED, SAMPLE_COLLISION and +SAMPLE_FEED_BR. + +These events will only count when an SPE event is running on the same core that +the PMU event is opened on, otherwise they read as 0. There are various ways to +ensure that the PMU event and SPE event are scheduled together depending on the +way the event is opened. For example opening both events as per-process events +on the same process, although it's not guaranteed that the PMU event is enabled +first when context switching. For that reason it may be better to open the PMU +event as a systemwide event and then open SPE on the process of interest. + +Discard mode +~~~~~~~~~~~~ + +SPE related (SAMPLE_* etc) core PMU events can be used without the overhead of +collecting sample data if discard mode is supported (optional from Armv8.6). +First run a system wide SPE session (or on the core of interest) using options +to minimize output. Then run perf stat: + + perf record -e arm_spe/discard/ -a -N -B --no-bpf-event -o - > /dev/null & + perf stat -e SAMPLE_FEED_LD SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-check.txt b/tools/perf/Documentation/perf-check.txt index 31741499e786..a764a4629220 100644 --- a/tools/perf/Documentation/perf-check.txt +++ b/tools/perf/Documentation/perf-check.txt @@ -51,7 +51,6 @@ feature:: dwarf_getlocations / HAVE_LIBDW_SUPPORT dwarf-unwind / HAVE_DWARF_UNWIND_SUPPORT auxtrace / HAVE_AUXTRACE_SUPPORT - libaudit / HAVE_LIBAUDIT_SUPPORT libbfd / HAVE_LIBBFD_SUPPORT libcapstone / HAVE_LIBCAPSTONE_SUPPORT libcrypto / HAVE_LIBCRYPTO_SUPPORT @@ -67,7 +66,6 @@ feature:: libunwind / HAVE_LIBUNWIND_SUPPORT lzma / HAVE_LZMA_SUPPORT numa_num_possible_cpus / HAVE_LIBNUMA_SUPPORT - syscall_table / HAVE_SYSCALL_TABLE_SUPPORT zlib / HAVE_ZLIB_SUPPORT zstd / HAVE_ZSTD_SUPPORT diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 1f668d4724e3..36ebebc875ea 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -40,7 +40,7 @@ The '$HOME/.perfconfig' file is used to store a per-user configuration. The file '$(sysconfdir)/perfconfig' can be used to store a system-wide default configuration. -One an disable reading config files by setting the PERF_CONFIG environment +One can disable reading config files by setting the PERF_CONFIG environment variable to /dev/null, or provide an alternate config file by setting that variable. diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt index eaec8253be68..b77f58c4d2fd 100644 --- a/tools/perf/Documentation/perf-ftrace.txt +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -148,6 +148,17 @@ OPTIONS for 'perf ftrace latency' --use-nsec:: Use nano-second instead of micro-second as a base unit of the histogram. +--bucket-range=:: + Bucket range in ms or ns (according to -n/--use-nsec), default is log2() mode. + +--min-latency=:: + Minimum latency for the start of the first bucket, in ms or ns (according to + -n/--use-nsec). + +--max-latency=:: + Maximum latency for the start of the last bucket, in ms or ns (according to + -n/--use-nsec). The setting is ignored if the value results in more than + 22 buckets. OPTIONS for 'perf ftrace profile' --------------------------------- @@ -190,6 +201,14 @@ OPTIONS for 'perf ftrace profile' Sort the result by the given field. Available values are: total, avg, max, count, name. Default is 'total'. +--graph-opts:: + List of options allowed to set: + + - nosleep-time - Measure on-CPU time only for function_graph tracer. + - noirqs - Ignore functions that happen inside interrupt. + - thresh=<n> - Setup trace duration threshold in microseconds. + - depth=<n> - Set max depth for function graph tracer to follow. + SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index 59ab1ff9d75f..cc0f37f0fa5a 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -151,7 +151,7 @@ displayed as follows: There are two ways that instructions-per-cycle (IPC) can be calculated depending on the recording. -If the 'cyc' config term (see config terms section below) was used, then IPC +If the 'cyc' config term (see <<_config_terms,config terms>> section below) was used, then IPC and cycle events are calculated using the cycle count from CYC packets, otherwise MTC packets are used - refer to the 'mtc' config term. When MTC is used, however, the values are less accurate because the timing is less accurate. @@ -239,7 +239,7 @@ which is the same as -e intel_pt/tsc=1,noretcomp=0/ -Note there are now new config terms - see section 'config terms' further below. +Note there are other config terms - see section <<_config_terms,config terms>> further below. The config terms are listed in /sys/devices/intel_pt/format. They are bit fields within the config member of the struct perf_event_attr which is @@ -311,218 +311,271 @@ perf_event_attr is displayed if the -vv option is used e.g. config terms ~~~~~~~~~~~~ -The June 2015 version of Intel 64 and IA-32 Architectures Software Developer -Manuals, Chapter 36 Intel Processor Trace, defined new Intel PT features. -Some of the features are reflect in new config terms. All the config terms are -described below. - -tsc Always supported. Produces TSC timestamp packets to provide - timing information. In some cases it is possible to decode - without timing information, for example a per-thread context - that does not overlap executable memory maps. - - The default config selects tsc (i.e. tsc=1). - -noretcomp Always supported. Disables "return compression" so a TIP packet - is produced when a function returns. Causes more packets to be - produced but might make decoding more reliable. - - The default config does not select noretcomp (i.e. noretcomp=0). - -psb_period Allows the frequency of PSB packets to be specified. - - The PSB packet is a synchronization packet that provides a - starting point for decoding or recovery from errors. - - Support for psb_period is indicated by: - - /sys/bus/event_source/devices/intel_pt/caps/psb_cyc - - which contains "1" if the feature is supported and "0" - otherwise. - - Valid values are given by: - - /sys/bus/event_source/devices/intel_pt/caps/psb_periods - - which contains a hexadecimal value, the bits of which represent - valid values e.g. bit 2 set means value 2 is valid. - - The psb_period value is converted to the approximate number of - trace bytes between PSB packets as: - - 2 ^ (value + 11) - - e.g. value 3 means 16KiB bytes between PSBs - - If an invalid value is entered, the error message - will give a list of valid values e.g. - - $ perf record -e intel_pt/psb_period=15/u uname - Invalid psb_period for intel_pt. Valid values are: 0-5 - - If MTC packets are selected, the default config selects a value - of 3 (i.e. psb_period=3) or the nearest lower value that is - supported (0 is always supported). Otherwise the default is 0. - - If decoding is expected to be reliable and the buffer is large - then a large PSB period can be used. - - Because a TSC packet is produced with PSB, the PSB period can - also affect the granularity to timing information in the absence - of MTC or CYC. - -mtc Produces MTC timing packets. - - MTC packets provide finer grain timestamp information than TSC - packets. MTC packets record time using the hardware crystal - clock (CTC) which is related to TSC packets using a TMA packet. - - Support for this feature is indicated by: - - /sys/bus/event_source/devices/intel_pt/caps/mtc - - which contains "1" if the feature is supported and - "0" otherwise. - - The frequency of MTC packets can also be specified - see - mtc_period below. - -mtc_period Specifies how frequently MTC packets are produced - see mtc - above for how to determine if MTC packets are supported. - - Valid values are given by: - - /sys/bus/event_source/devices/intel_pt/caps/mtc_periods - - which contains a hexadecimal value, the bits of which represent - valid values e.g. bit 2 set means value 2 is valid. - - The mtc_period value is converted to the MTC frequency as: - - CTC-frequency / (2 ^ value) - - e.g. value 3 means one eighth of CTC-frequency - - Where CTC is the hardware crystal clock, the frequency of which - can be related to TSC via values provided in cpuid leaf 0x15. - - If an invalid value is entered, the error message - will give a list of valid values e.g. - - $ perf record -e intel_pt/mtc_period=15/u uname - Invalid mtc_period for intel_pt. Valid values are: 0,3,6,9 - - The default value is 3 or the nearest lower value - that is supported (0 is always supported). - -cyc Produces CYC timing packets. - - CYC packets provide even finer grain timestamp information than - MTC and TSC packets. A CYC packet contains the number of CPU - cycles since the last CYC packet. Unlike MTC and TSC packets, - CYC packets are only sent when another packet is also sent. - - Support for this feature is indicated by: - - /sys/bus/event_source/devices/intel_pt/caps/psb_cyc - - which contains "1" if the feature is supported and - "0" otherwise. - - The number of CYC packets produced can be reduced by specifying - a threshold - see cyc_thresh below. - -cyc_thresh Specifies how frequently CYC packets are produced - see cyc - above for how to determine if CYC packets are supported. - - Valid cyc_thresh values are given by: - - /sys/bus/event_source/devices/intel_pt/caps/cycle_thresholds - - which contains a hexadecimal value, the bits of which represent - valid values e.g. bit 2 set means value 2 is valid. - - The cyc_thresh value represents the minimum number of CPU cycles - that must have passed before a CYC packet can be sent. The - number of CPU cycles is: - - 2 ^ (value - 1) - - e.g. value 4 means 8 CPU cycles must pass before a CYC packet - can be sent. Note a CYC packet is still only sent when another - packet is sent, not at, e.g. every 8 CPU cycles. - - If an invalid value is entered, the error message - will give a list of valid values e.g. - - $ perf record -e intel_pt/cyc,cyc_thresh=15/u uname - Invalid cyc_thresh for intel_pt. Valid values are: 0-12 - - 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. - - As an alternative, refer to "Emulated PTWRITE" further below. - -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. - -event Enable Event Trace. The events provide information about asynchronous - events. - - Support for this feature is indicated by: - - /sys/bus/event_source/devices/intel_pt/caps/event_trace - - which contains "1" if the feature is supported and - "0" otherwise. - -notnt Disable TNT packets. Without TNT packets, it is not possible to walk - executable code to reconstruct control flow, however FUP, TIP, TIP.PGE - and TIP.PGD packets still indicate asynchronous control flow, and (if - return compression is disabled - see noretcomp) return statements. - The advantage of eliminating TNT packets is reducing the size of the - trace and corresponding tracing overhead. - - Support for this feature is indicated by: - - /sys/bus/event_source/devices/intel_pt/caps/tnt_disable - - which contains "1" if the feature is supported and - "0" otherwise. - +Config terms are parameters specified with the -e intel_pt// event option, +for example: + + -e intel_pt/cyc/ + +which selects cycle accurate mode. Each config term can have a value which +defaults to 1, so the above is the same as: + + -e intel_pt/cyc=1/ + +Some terms are set by default, so must be set to 0 to turn them off. For +example, to turn off branch tracing: + + -e intel_pt/branch=0/ + +Multiple config terms are separated by commas, for example: + + -e intel_pt/cyc,mtc_period=9/ + +There are also common config terms, see linkperf:perf-record[1] documentation. + +Intel PT config terms are described below. + +*tsc*:: +Always supported. Produces TSC timestamp packets to provide +timing information. In some cases it is possible to decode +without timing information, for example a per-thread context +that does not overlap executable memory maps. ++ +The default config selects tsc (i.e. tsc=1). + +*noretcomp*:: +Always supported. Disables "return compression" so a TIP packet +is produced when a function returns. Causes more packets to be +produced but might make decoding more reliable. ++ +The default config does not select noretcomp (i.e. noretcomp=0). + +*psb_period*:: +Allows the frequency of PSB packets to be specified. ++ +The PSB packet is a synchronization packet that provides a +starting point for decoding or recovery from errors. ++ +Support for psb_period is indicated by: ++ + /sys/bus/event_source/devices/intel_pt/caps/psb_cyc ++ +which contains "1" if the feature is supported and "0" +otherwise. ++ +Valid values are given by: ++ + /sys/bus/event_source/devices/intel_pt/caps/psb_periods ++ +which contains a hexadecimal value, the bits of which represent +valid values e.g. bit 2 set means value 2 is valid. ++ +The psb_period value is converted to the approximate number of +trace bytes between PSB packets as: ++ + 2 ^ (value + 11) ++ +e.g. value 3 means 16KiB bytes between PSBs ++ +If an invalid value is entered, the error message +will give a list of valid values e.g. ++ + $ perf record -e intel_pt/psb_period=15/u uname + Invalid psb_period for intel_pt. Valid values are: 0-5 ++ +If MTC packets are selected, the default config selects a value +of 3 (i.e. psb_period=3) or the nearest lower value that is +supported (0 is always supported). Otherwise the default is 0. ++ +If decoding is expected to be reliable and the buffer is large +then a large PSB period can be used. ++ +Because a TSC packet is produced with PSB, the PSB period can +also affect the granularity to timing information in the absence +of MTC or CYC. + +*mtc*:: +Produces MTC timing packets. ++ +MTC packets provide finer grain timestamp information than TSC +packets. MTC packets record time using the hardware crystal +clock (CTC) which is related to TSC packets using a TMA packet. ++ +Support for this feature is indicated by: ++ + /sys/bus/event_source/devices/intel_pt/caps/mtc ++ +which contains "1" if the feature is supported and +"0" otherwise. ++ +The frequency of MTC packets can also be specified - see +mtc_period below. + +*mtc_period*:: +Specifies how frequently MTC packets are produced - see mtc +above for how to determine if MTC packets are supported. ++ +Valid values are given by: ++ + /sys/bus/event_source/devices/intel_pt/caps/mtc_periods ++ +which contains a hexadecimal value, the bits of which represent +valid values e.g. bit 2 set means value 2 is valid. ++ +The mtc_period value is converted to the MTC frequency as: + + CTC-frequency / (2 ^ value) ++ +e.g. value 3 means one eighth of CTC-frequency ++ +Where CTC is the hardware crystal clock, the frequency of which +can be related to TSC via values provided in cpuid leaf 0x15. ++ +If an invalid value is entered, the error message +will give a list of valid values e.g. ++ + $ perf record -e intel_pt/mtc_period=15/u uname + Invalid mtc_period for intel_pt. Valid values are: 0,3,6,9 ++ +The default value is 3 or the nearest lower value +that is supported (0 is always supported). + +*cyc*:: +Produces CYC timing packets. ++ +CYC packets provide even finer grain timestamp information than +MTC and TSC packets. A CYC packet contains the number of CPU +cycles since the last CYC packet. Unlike MTC and TSC packets, +CYC packets are only sent when another packet is also sent. ++ +Support for this feature is indicated by: ++ + /sys/bus/event_source/devices/intel_pt/caps/psb_cyc ++ +which contains "1" if the feature is supported and +"0" otherwise. ++ +The number of CYC packets produced can be reduced by specifying +a threshold - see cyc_thresh below. + +*cyc_thresh*:: +Specifies how frequently CYC packets are produced - see cyc +above for how to determine if CYC packets are supported. ++ +Valid cyc_thresh values are given by: ++ + /sys/bus/event_source/devices/intel_pt/caps/cycle_thresholds ++ +which contains a hexadecimal value, the bits of which represent +valid values e.g. bit 2 set means value 2 is valid. ++ +The cyc_thresh value represents the minimum number of CPU cycles +that must have passed before a CYC packet can be sent. The +number of CPU cycles is: ++ + 2 ^ (value - 1) ++ +e.g. value 4 means 8 CPU cycles must pass before a CYC packet +can be sent. Note a CYC packet is still only sent when another +packet is sent, not at, e.g. every 8 CPU cycles. ++ +If an invalid value is entered, the error message +will give a list of valid values e.g. ++ + $ perf record -e intel_pt/cyc,cyc_thresh=15/u uname + Invalid cyc_thresh for intel_pt. Valid values are: 0-12 ++ +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. ++ +As an alternative, refer to "Emulated PTWRITE" further below. + +*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. + +*event*:: +Enable Event Trace. The events provide information about asynchronous +events. ++ +Support for this feature is indicated by: ++ + /sys/bus/event_source/devices/intel_pt/caps/event_trace ++ +which contains "1" if the feature is supported and +"0" otherwise. + +*notnt*:: +Disable TNT packets. Without TNT packets, it is not possible to walk +executable code to reconstruct control flow, however FUP, TIP, TIP.PGE +and TIP.PGD packets still indicate asynchronous control flow, and (if +return compression is disabled - see noretcomp) return statements. +The advantage of eliminating TNT packets is reducing the size of the +trace and corresponding tracing overhead. ++ +Support for this feature is indicated by: ++ + /sys/bus/event_source/devices/intel_pt/caps/tnt_disable ++ +which contains "1" if the feature is supported and +"0" otherwise. + +*aux-action=start-paused*:: +Start tracing paused, refer to the section <<_pause_or_resume_tracing,Pause or Resume Tracing>> + + +config terms on other events +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Some Intel PT features work with other events, features such as AUX area sampling +and PEBS-via-PT. In those cases, the other events can have config terms below: + +*aux-sample-size*:: + Used to set the AUX area sample size, refer to the section + <<_aux_area_sampling_option,AUX area sampling option>> + +*aux-output*:: + Used to select PEBS-via-PT, refer to the + section <<_pebs_via_intel_pt,PEBS via Intel PT>> + +*aux-action*:: + Used to pause or resume tracing, refer to the section + <<_pause_or_resume_tracing,Pause or Resume Tracing>> AUX area sampling option ~~~~~~~~~~~~~~~~~~~~~~~~ @@ -596,7 +649,8 @@ The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap s nor snapshot size is specified, then the default is 4MiB for privileged users (or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users. If an unprivileged user does not specify mmap pages, the mmap pages will be -reduced as described in the 'new auxtrace mmap size option' section below. +reduced as described in the <<_new_auxtrace_mmap_size_option,new auxtrace mmap size option>> +section below. The snapshot size is displayed if the option -vv is used e.g. @@ -952,11 +1006,11 @@ transaction start, commit or abort. Note that "instructions", "cycles", "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. +"branch=0". Refer to the <<_config_terms,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 +recorded only if the "ptw" config term was used. Refer to the <<_config_terms,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. @@ -964,7 +1018,7 @@ 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 +the <<_config_terms,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: @@ -1120,7 +1174,7 @@ What *will* be decoded with the (single) q option: - asynchronous branches such as interrupts - indirect branches - function return target address *if* the noretcomp config term (refer - config terms section) was used + <<_config_terms,config terms>> section) was used - start of (control-flow) tracing - end of (control-flow) tracing, if it is not out of context - power events, ptwrite, transaction start and abort @@ -1133,7 +1187,7 @@ Repeating the q option (double-q i.e. qq) results in even faster decoding and ev less detail. The decoder decodes only extended PSB (PSB+) packets, getting the instruction pointer if there is a FUP packet within PSB+ (i.e. between PSB and PSBEND). Note PSB packets occur regularly in the trace based on the psb_period -config term (refer config terms section). There will be a FUP packet if the +config term (refer <<_config_terms,config terms>> section). There will be a FUP packet if the PSB+ occurs while control flow is being traced. What will *not* be decoded with the qq option: @@ -1867,6 +1921,108 @@ For pipe mode, the order of events and timestamps can presumably be messed up. +Pause or Resume Tracing +----------------------- + +With newer Kernels, it is possible to use other selected events to pause +or resume Intel PT tracing. This is configured by using the "aux-action" +config term: + +"aux-action=pause" is used with events that are to pause Intel PT tracing. + +"aux-action=resume" is used with events that are to resume Intel PT tracing. + +"aux-action=start-paused" is used with the Intel PT event to start in a +paused state. + +For example, to trace only the uname system call (sys_newuname) when running the +command line utility uname: + + $ perf record --kcore -e intel_pt/aux-action=start-paused/k,syscalls:sys_enter_newuname/aux-action=resume/,syscalls:sys_exit_newuname/aux-action=pause/ uname + Linux + [ perf record: Woken up 1 times to write data ] + [ perf record: Captured and wrote 0.043 MB perf.data ] + $ perf script --call-trace + uname 30805 [000] 24001.058782799: name: 0x7ffc9c1865b0 + uname 30805 [000] 24001.058784424: psb offs: 0 + uname 30805 [000] 24001.058784424: cbr: 39 freq: 3904 MHz (139%) + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) debug_smp_processor_id + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __x64_sys_newuname + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) down_read + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __cond_resched + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) in_lock_functions + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_sub + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) up_read + uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) in_lock_functions + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) preempt_count_sub + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) _copy_to_user + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_to_user_mode + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_work + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) perf_syscall_exit + uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) debug_smp_processor_id + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_alloc + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_get_recursion_context + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_tp_event + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_update + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) tracing_gen_ctx_irq_test + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_event + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __perf_event_account_interrupt + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __this_cpu_preempt_check + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_output_forward + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_aux_pause + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) ring_buffer_get + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_lock + uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_unlock + uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) pt_event_stop + uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id + uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id + uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) native_write_msr + uname 30805 [000] 24001.058785463: ([kernel.kallsyms]) native_write_msr + uname 30805 [000] 24001.058785639: 0x0 + +The example above uses tracepoints, but any kind of sampled event can be used. + +For example: + + Tracing between arch_cpu_idle_enter() and arch_cpu_idle_exit() using breakpoint events: + + $ sudo cat /proc/kallsyms | sort | grep ' arch_cpu_idle_enter\| arch_cpu_idle_exit' + ffffffffb605bf60 T arch_cpu_idle_enter + ffffffffb614d8a0 W arch_cpu_idle_exit + $ sudo perf record --kcore -a -e intel_pt/aux-action=start-paused/k -e mem:0xffffffffb605bf60:x/aux-action=resume/ -e mem:0xffffffffb614d8a0:x/aux-action=pause/ -- sleep 1 + [ perf record: Woken up 1 times to write data ] + [ perf record: Captured and wrote 1.387 MB perf.data ] + + Tracing __alloc_pages() using kprobes: + + $ sudo perf probe --add '__alloc_pages order' + Added new event: probe:__alloc_pages (on __alloc_pages with order) + $ sudo perf probe --add __alloc_pages%return + Added new event: probe:__alloc_pages__return (on __alloc_pages%return) + $ sudo perf record --kcore -aR -e intel_pt/aux-action=start-paused/k -e probe:__alloc_pages/aux-action=resume/ -e probe:__alloc_pages__return/aux-action=pause/ -- sleep 1 + [ perf record: Woken up 1 times to write data ] + [ perf record: Captured and wrote 1.490 MB perf.data ] + + Tracing starting at main() using a uprobe event: + + $ sudo perf probe -x /usr/bin/uname main + Added new event: probe_uname:main (on main in /usr/bin/uname) + $ sudo perf record -e intel_pt/-aux-action=start-paused/u -e probe_uname:main/aux-action=resume/ -- uname + Linux + [ perf record: Woken up 1 times to write data ] + [ perf record: Captured and wrote 0.031 MB perf.data ] + + Tracing occasionally using cycles events with different periods: + + $ perf record --kcore -a -m,64M -e intel_pt/aux-action=start-paused/k -e cycles/aux-action=pause,period=1000000/Pk -e cycles/aux-action=resume,period=10500000/Pk -- firefox + [ perf record: Woken up 19 times to write data ] + [ perf record: Captured and wrote 16.561 MB perf.data ] + + EXAMPLE ------- diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index d0c65fad419a..c3ffd93f94d7 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -188,7 +188,7 @@ in the CPU vendor specific documentation. The available PMUs and their raw parameters can be listed with - ls /sys/devices/*/format + ls /sys/bus/event_source/devices/*/format For example the raw event "LSD.UOPS" core pmu event above could be specified as diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index 57a940399de0..d3793054f7d3 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -187,8 +187,8 @@ CONTENTION OPTIONS Show lock contention only for given lock types (comma separated list). Available values are: semaphore, spinlock, rwlock, rwlock:R, rwlock:W, rwsem, rwsem:R, rwsem:W, - rtmutex, rwlock-rt, rwlock-rt:R, rwlock-rt:W, pcpu-sem, pcpu-sem:R, pcpu-sem:W, - mutex + rtmutex, rwlock-rt, rwlock-rt:R, rwlock-rt:W, percpu-rwmem, pcpu-sem, + pcpu-sem:R, pcpu-sem:W, mutex Note that RW-variant of locks have :R and :W suffix. Names without the suffix are shortcuts for the both variants. Ex) rwsem = rwsem:R + rwsem:W. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 242223240a08..80686d590de2 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -68,6 +68,10 @@ OPTIONS like this: name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\'. - 'aux-output': Generate AUX records instead of events. This requires that an AUX area event is also provided. + - 'aux-action': "pause" or "resume" to pause or resume an AUX + area event (the group leader) when this event occurs. + "start-paused" on an AUX area event itself, will + start in a paused state. - 'aux-sample-size': Set sample size for AUX area sampling. If the '--aux-sample' option has been used, set aux-sample-size=0 to disable AUX area sampling for the event. diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt index efcdec528a8f..32da0d1fa86a 100644 --- a/tools/perf/Documentation/perf-test.txt +++ b/tools/perf/Documentation/perf-test.txt @@ -28,18 +28,22 @@ OPTIONS Tests to skip (comma separated numeric list). -v:: +-vv:: +-vvv:: --verbose:: - Be more verbose. + With a single '-v', verbose level 1, only failing test output + is displayed. With '-vv' and higher all test output is shown. -S:: --sequential:: - Run tests one after the other, this is the default mode. - --p:: ---parallel:: - Run tests in parallel, speeds up the whole process but is not safe with - the current infrastructure, where some tests that compete for some resources, - for instance, 'perf probe' tests that add/remove probes or clean all probes, etc. + Run all tests one after the other. By default "exclusive" + tests are run sequentially, but other tests are run in + parallel to speed execution. + +-r:: +--runs-per-test:: + Run each test the given number of times, by default once. This + option can be useful to determine if a test is flaky. -F:: --dont-fork:: diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 6e0cc50bbc13..fb3d2af33844 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -241,6 +241,11 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. printing using the existing 'perf trace' syscall arg beautifiers to map integer arguments to strings (pid to comm, syscall id to syscall name, etc). +--force-btf:: + Use btf_dump to pretty print syscall argument data, instead of using hand-crafted pretty + printers. This option is intended for testing BTF integration in perf trace. btf_dump-based + pretty-printing serves as a fallback to hand-crafted pretty printers, as the latter can + better pretty-print integer flags and struct pointers. PAGEFAULTS ---------- diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 908165fcec7d..364b55b00b48 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,3 +1,5 @@ +COPYING +LICENSES/preferred/GPL-2.0 arch/arm64/tools/gen-sysreg.awk arch/arm64/tools/sysreg arch/*/include/uapi/asm/bpf_perf_event.h diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0e4f6a860ae2..23dbb6bb91cf 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -28,21 +28,10 @@ include $(srctree)/tools/scripts/Makefile.arch $(call detected_var,SRCARCH) -ifneq ($(NO_SYSCALL_TABLE),1) - NO_SYSCALL_TABLE := 1 - - ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 powerpc arm64 s390 mips loongarch riscv)) - NO_SYSCALL_TABLE := 0 - endif - - ifneq ($(NO_SYSCALL_TABLE),1) - CFLAGS += -DHAVE_SYSCALL_TABLE_SUPPORT - endif -endif +CFLAGS += -I$(OUTPUT)arch/$(SRCARCH)/include/generated # Additional ARCH settings for ppc ifeq ($(SRCARCH),powerpc) - CFLAGS += -I$(OUTPUT)arch/powerpc/include/generated ifndef NO_LIBUNWIND LIBUNWIND_LIBS := -lunwind -lunwind-ppc64 endif @@ -51,7 +40,6 @@ endif # Additional ARCH settings for x86 ifeq ($(SRCARCH),x86) $(call detected,CONFIG_X86) - CFLAGS += -I$(OUTPUT)arch/x86/include/generated ifeq (${IS_64_BIT}, 1) CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S @@ -73,34 +61,27 @@ ifeq ($(SRCARCH),arm) endif ifeq ($(SRCARCH),arm64) - CFLAGS += -I$(OUTPUT)arch/arm64/include/generated ifndef NO_LIBUNWIND LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 endif endif ifeq ($(SRCARCH),loongarch) - CFLAGS += -I$(OUTPUT)arch/loongarch/include/generated ifndef NO_LIBUNWIND LIBUNWIND_LIBS = -lunwind -lunwind-loongarch64 endif endif ifeq ($(ARCH),s390) - CFLAGS += -fPIC -I$(OUTPUT)arch/s390/include/generated + CFLAGS += -fPIC endif ifeq ($(ARCH),mips) - CFLAGS += -I$(OUTPUT)arch/mips/include/generated ifndef NO_LIBUNWIND LIBUNWIND_LIBS = -lunwind -lunwind-mips endif endif -ifeq ($(ARCH),riscv) - CFLAGS += -I$(OUTPUT)arch/riscv/include/generated -endif - # So far there's only x86 and arm libdw unwind support merged in perf. # Disable it on all other architectures in case libdw unwind # support is detected in system. Add supported architectures @@ -171,7 +152,7 @@ ifdef LIBDW_DIR endif DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) - DWARFLIBS += -lelf -lz -llzma -lbz2 -lzstd + DWARFLIBS += -lelf -lz -llzma -lbz2 LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw).0.0 LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION))) @@ -516,13 +497,14 @@ ifeq ($(feature-setns), 1) $(call detected,CONFIG_SETNS) endif +ifeq ($(feature-reallocarray), 0) + CFLAGS += -DCOMPAT_NEED_REALLOCARRAY +endif + ifdef CORESIGHT $(call feature_check,libopencsd) ifeq ($(feature-libopencsd), 1) CFLAGS += -DHAVE_CSTRACE_SUPPORT $(LIBOPENCSD_CFLAGS) - ifeq ($(feature-reallocarray), 0) - CFLAGS += -DCOMPAT_NEED_REALLOCARRAY - endif LDFLAGS += $(LIBOPENCSD_LDFLAGS) EXTLIBS += $(OPENCSDLIBS) $(call detected,CONFIG_LIBOPENCSD) @@ -566,6 +548,12 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_ELF_GETSHDRSTRNDX_SUPPORT endif + ifeq ($(feature-libelf-zstd), 1) + ifdef NO_LIBZSTD + $(error Error: libzstd is required by libelf, please do not set NO_LIBZSTD) + endif + endif + ifndef NO_LIBDEBUGINFOD $(call feature_check,libdebuginfod) ifeq ($(feature-libdebuginfod), 1) @@ -776,21 +764,7 @@ ifndef NO_LIBUNWIND endif ifneq ($(NO_LIBTRACEEVENT),1) - ifeq ($(NO_SYSCALL_TABLE),0) - $(call detected,CONFIG_TRACE) - else - ifndef NO_LIBAUDIT - $(call feature_check,libaudit) - ifneq ($(feature-libaudit), 1) - $(warning No libaudit.h found, disables 'trace' tool, please install audit-libs-devel or libaudit-dev) - NO_LIBAUDIT := 1 - else - CFLAGS += -DHAVE_LIBAUDIT_SUPPORT - EXTLIBS += -laudit - $(call detected,CONFIG_TRACE) - endif - endif - endif + $(call detected,CONFIG_TRACE) endif ifndef NO_LIBCRYPTO @@ -1130,9 +1104,6 @@ ifndef NO_AUXTRACE ifndef NO_AUXTRACE $(call detected,CONFIG_AUXTRACE) CFLAGS += -DHAVE_AUXTRACE_SUPPORT - ifeq ($(feature-reallocarray), 0) - CFLAGS += -DCOMPAT_NEED_REALLOCARRAY - endif endif endif @@ -1187,7 +1158,6 @@ endif # libtraceevent is a recommended dependency picked up from the system. ifneq ($(NO_LIBTRACEEVENT),1) - $(call feature_check,libtraceevent) ifeq ($(feature-libtraceevent), 1) CFLAGS += -DHAVE_LIBTRACEEVENT $(shell $(PKG_CONFIG) --cflags libtraceevent) LDFLAGS += $(shell $(PKG_CONFIG) --libs-only-L libtraceevent) @@ -1203,7 +1173,6 @@ ifneq ($(NO_LIBTRACEEVENT),1) $(error ERROR: libtraceevent is missing. Please install libtraceevent-dev/libtraceevent-devel and/or set LIBTRACEEVENT_DIR or build with NO_LIBTRACEEVENT=1) endif - $(call feature_check,libtracefs) ifeq ($(feature-libtracefs), 1) CFLAGS += $(shell $(PKG_CONFIG) --cflags libtracefs) LDFLAGS += $(shell $(PKG_CONFIG) --libs-only-L libtracefs) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index d74241a15131..eea8877c7cba 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -59,8 +59,6 @@ include ../scripts/utilities.mak # # Define NO_LIBNUMA if you do not want numa perf benchmark # -# Define NO_LIBAUDIT if you do not want libaudit support -# # Define NO_LIBBIONIC if you do not want bionic support # # Define NO_LIBCRYPTO if you do not want libcrypto (openssl) support @@ -119,10 +117,6 @@ include ../scripts/utilities.mak # # Define LIBBPF_DYNAMIC to enable libbpf dynamic linking. # -# Define NO_SYSCALL_TABLE=1 to disable the use of syscall id to/from name tables -# generated from the kernel .tbl or unistd.h files and use, if available, libaudit -# for doing the conversions to/from strings/id. -# # Define NO_LIBPFM4 to disable libpfm4 events extension. # # Define NO_LIBDEBUGINFOD if you do not want support debuginfod @@ -164,13 +158,7 @@ ifneq ($(OUTPUT),) VPATH += $(OUTPUT) export VPATH # create symlink to the original source -SOURCE := $(shell ln -sf $(srctree)/tools/perf $(OUTPUT)/source) -endif - -ifeq ($(V),1) - Q = -else - Q = @ +SOURCE := $(shell ln -sfn $(srctree)/tools/perf $(OUTPUT)/source) endif # Do not use make's built-in rules @@ -310,6 +298,7 @@ ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump) FEATURE_TESTS := all endif endif +include $(srctree)/tools/perf/scripts/Makefile.syscalls include Makefile.config endif @@ -487,6 +476,9 @@ endif EXTLIBS := $(call filter-out,$(EXCLUDE_EXTLIBS),$(EXTLIBS)) LIBS = -Wl,--whole-archive $(PERFLIBS) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group +PERFLIBS_PY := $(call filter-out,$(LIBPERF_BENCH) $(LIBPERF_TEST),$(PERFLIBS)) +LIBS_PY = -Wl,--whole-archive $(PERFLIBS_PY) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group + export INSTALL SHELL_PATH ### Build rules @@ -735,9 +727,9 @@ all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS) # Create python binding output directory if not already present $(shell [ -d '$(OUTPUT)python' ] || mkdir -p '$(OUTPUT)python') -$(OUTPUT)python/perf$(PYTHON_EXTENSION_SUFFIX): util/python.c util/setup.py $(PERFLIBS) +$(OUTPUT)python/perf$(PYTHON_EXTENSION_SUFFIX): util/python.c util/setup.py $(PERFLIBS_PY) $(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \ - CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBS)' \ + CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBS_PY)' \ $(PYTHON_WORD) util/setup.py \ --quiet build_ext; \ cp $(PYTHON_EXTBUILD_LIB)perf*.so $(OUTPUT)python/ @@ -1094,11 +1086,6 @@ endif $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' $(call QUIET_INSTALL, perf-iostat) \ $(INSTALL) $(OUTPUT)perf-iostat -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' -ifndef NO_LIBAUDIT - $(call QUIET_INSTALL, strace/groups) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)'; \ - $(INSTALL) trace/strace/groups/* -m 644 -t '$(DESTDIR_SQ)$(STRACE_GROUPS_INSTDIR_SQ)' -endif ifndef NO_LIBPERL $(call QUIET_INSTALL, perl-scripts) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \ diff --git a/tools/perf/arch/alpha/entry/syscalls/Kbuild b/tools/perf/arch/alpha/entry/syscalls/Kbuild new file mode 100644 index 000000000000..9a41e3572c3a --- /dev/null +++ b/tools/perf/arch/alpha/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/alpha/entry/syscalls/Makefile.syscalls b/tools/perf/arch/alpha/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..690168aac34d --- /dev/null +++ b/tools/perf/arch/alpha/entry/syscalls/Makefile.syscalls @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_64 += + +syscalltbl = $(srctree)/tools/perf/arch/alpha/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/alpha/entry/syscalls/syscall.tbl b/tools/perf/arch/alpha/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..74720667fe09 --- /dev/null +++ b/tools/perf/arch/alpha/entry/syscalls/syscall.tbl @@ -0,0 +1,504 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# system call numbers and entry vectors for alpha +# +# The format is: +# <number> <abi> <name> <entry point> +# +# The <abi> is always "common" for this file +# +0 common osf_syscall alpha_syscall_zero +1 common exit sys_exit +2 common fork alpha_fork +3 common read sys_read +4 common write sys_write +5 common osf_old_open sys_ni_syscall +6 common close sys_close +7 common osf_wait4 sys_osf_wait4 +8 common osf_old_creat sys_ni_syscall +9 common link sys_link +10 common unlink sys_unlink +11 common osf_execve sys_ni_syscall +12 common chdir sys_chdir +13 common fchdir sys_fchdir +14 common mknod sys_mknod +15 common chmod sys_chmod +16 common chown sys_chown +17 common brk sys_osf_brk +18 common osf_getfsstat sys_ni_syscall +19 common lseek sys_lseek +20 common getxpid sys_getxpid +21 common osf_mount sys_osf_mount +22 common umount2 sys_umount +23 common setuid sys_setuid +24 common getxuid sys_getxuid +25 common exec_with_loader sys_ni_syscall +26 common ptrace sys_ptrace +27 common osf_nrecvmsg sys_ni_syscall +28 common osf_nsendmsg sys_ni_syscall +29 common osf_nrecvfrom sys_ni_syscall +30 common osf_naccept sys_ni_syscall +31 common osf_ngetpeername sys_ni_syscall +32 common osf_ngetsockname sys_ni_syscall +33 common access sys_access +34 common osf_chflags sys_ni_syscall +35 common osf_fchflags sys_ni_syscall +36 common sync sys_sync +37 common kill sys_kill +38 common osf_old_stat sys_ni_syscall +39 common setpgid sys_setpgid +40 common osf_old_lstat sys_ni_syscall +41 common dup sys_dup +42 common pipe sys_alpha_pipe +43 common osf_set_program_attributes sys_osf_set_program_attributes +44 common osf_profil sys_ni_syscall +45 common open sys_open +46 common osf_old_sigaction sys_ni_syscall +47 common getxgid sys_getxgid +48 common osf_sigprocmask sys_osf_sigprocmask +49 common osf_getlogin sys_ni_syscall +50 common osf_setlogin sys_ni_syscall +51 common acct sys_acct +52 common sigpending sys_sigpending +54 common ioctl sys_ioctl +55 common osf_reboot sys_ni_syscall +56 common osf_revoke sys_ni_syscall +57 common symlink sys_symlink +58 common readlink sys_readlink +59 common execve sys_execve +60 common umask sys_umask +61 common chroot sys_chroot +62 common osf_old_fstat sys_ni_syscall +63 common getpgrp sys_getpgrp +64 common getpagesize sys_getpagesize +65 common osf_mremap sys_ni_syscall +66 common vfork alpha_vfork +67 common stat sys_newstat +68 common lstat sys_newlstat +69 common osf_sbrk sys_ni_syscall +70 common osf_sstk sys_ni_syscall +71 common mmap sys_osf_mmap +72 common osf_old_vadvise sys_ni_syscall +73 common munmap sys_munmap +74 common mprotect sys_mprotect +75 common madvise sys_madvise +76 common vhangup sys_vhangup +77 common osf_kmodcall sys_ni_syscall +78 common osf_mincore sys_ni_syscall +79 common getgroups sys_getgroups +80 common setgroups sys_setgroups +81 common osf_old_getpgrp sys_ni_syscall +82 common setpgrp sys_setpgid +83 common osf_setitimer compat_sys_setitimer +84 common osf_old_wait sys_ni_syscall +85 common osf_table sys_ni_syscall +86 common osf_getitimer compat_sys_getitimer +87 common gethostname sys_gethostname +88 common sethostname sys_sethostname +89 common getdtablesize sys_getdtablesize +90 common dup2 sys_dup2 +91 common fstat sys_newfstat +92 common fcntl sys_fcntl +93 common osf_select sys_osf_select +94 common poll sys_poll +95 common fsync sys_fsync +96 common setpriority sys_setpriority +97 common socket sys_socket +98 common connect sys_connect +99 common accept sys_accept +100 common getpriority sys_osf_getpriority +101 common send sys_send +102 common recv sys_recv +103 common sigreturn sys_sigreturn +104 common bind sys_bind +105 common setsockopt sys_setsockopt +106 common listen sys_listen +107 common osf_plock sys_ni_syscall +108 common osf_old_sigvec sys_ni_syscall +109 common osf_old_sigblock sys_ni_syscall +110 common osf_old_sigsetmask sys_ni_syscall +111 common sigsuspend sys_sigsuspend +112 common osf_sigstack sys_osf_sigstack +113 common recvmsg sys_recvmsg +114 common sendmsg sys_sendmsg +115 common osf_old_vtrace sys_ni_syscall +116 common osf_gettimeofday sys_osf_gettimeofday +117 common osf_getrusage sys_osf_getrusage +118 common getsockopt sys_getsockopt +120 common readv sys_readv +121 common writev sys_writev +122 common osf_settimeofday sys_osf_settimeofday +123 common fchown sys_fchown +124 common fchmod sys_fchmod +125 common recvfrom sys_recvfrom +126 common setreuid sys_setreuid +127 common setregid sys_setregid +128 common rename sys_rename +129 common truncate sys_truncate +130 common ftruncate sys_ftruncate +131 common flock sys_flock +132 common setgid sys_setgid +133 common sendto sys_sendto +134 common shutdown sys_shutdown +135 common socketpair sys_socketpair +136 common mkdir sys_mkdir +137 common rmdir sys_rmdir +138 common osf_utimes sys_osf_utimes +139 common osf_old_sigreturn sys_ni_syscall +140 common osf_adjtime sys_ni_syscall +141 common getpeername sys_getpeername +142 common osf_gethostid sys_ni_syscall +143 common osf_sethostid sys_ni_syscall +144 common getrlimit sys_getrlimit +145 common setrlimit sys_setrlimit +146 common osf_old_killpg sys_ni_syscall +147 common setsid sys_setsid +148 common quotactl sys_quotactl +149 common osf_oldquota sys_ni_syscall +150 common getsockname sys_getsockname +153 common osf_pid_block sys_ni_syscall +154 common osf_pid_unblock sys_ni_syscall +156 common sigaction sys_osf_sigaction +157 common osf_sigwaitprim sys_ni_syscall +158 common osf_nfssvc sys_ni_syscall +159 common osf_getdirentries sys_osf_getdirentries +160 common osf_statfs sys_osf_statfs +161 common osf_fstatfs sys_osf_fstatfs +163 common osf_asynch_daemon sys_ni_syscall +164 common osf_getfh sys_ni_syscall +165 common osf_getdomainname sys_osf_getdomainname +166 common setdomainname sys_setdomainname +169 common osf_exportfs sys_ni_syscall +181 common osf_alt_plock sys_ni_syscall +184 common osf_getmnt sys_ni_syscall +187 common osf_alt_sigpending sys_ni_syscall +188 common osf_alt_setsid sys_ni_syscall +199 common osf_swapon sys_swapon +200 common msgctl sys_old_msgctl +201 common msgget sys_msgget +202 common msgrcv sys_msgrcv +203 common msgsnd sys_msgsnd +204 common semctl sys_old_semctl +205 common semget sys_semget +206 common semop sys_semop +207 common osf_utsname sys_osf_utsname +208 common lchown sys_lchown +209 common shmat sys_shmat +210 common shmctl sys_old_shmctl +211 common shmdt sys_shmdt +212 common shmget sys_shmget +213 common osf_mvalid sys_ni_syscall +214 common osf_getaddressconf sys_ni_syscall +215 common osf_msleep sys_ni_syscall +216 common osf_mwakeup sys_ni_syscall +217 common msync sys_msync +218 common osf_signal sys_ni_syscall +219 common osf_utc_gettime sys_ni_syscall +220 common osf_utc_adjtime sys_ni_syscall +222 common osf_security sys_ni_syscall +223 common osf_kloadcall sys_ni_syscall +224 common osf_stat sys_osf_stat +225 common osf_lstat sys_osf_lstat +226 common osf_fstat sys_osf_fstat +227 common osf_statfs64 sys_osf_statfs64 +228 common osf_fstatfs64 sys_osf_fstatfs64 +233 common getpgid sys_getpgid +234 common getsid sys_getsid +235 common sigaltstack sys_sigaltstack +236 common osf_waitid sys_ni_syscall +237 common osf_priocntlset sys_ni_syscall +238 common osf_sigsendset sys_ni_syscall +239 common osf_set_speculative sys_ni_syscall +240 common osf_msfs_syscall sys_ni_syscall +241 common osf_sysinfo sys_osf_sysinfo +242 common osf_uadmin sys_ni_syscall +243 common osf_fuser sys_ni_syscall +244 common osf_proplist_syscall sys_osf_proplist_syscall +245 common osf_ntp_adjtime sys_ni_syscall +246 common osf_ntp_gettime sys_ni_syscall +247 common osf_pathconf sys_ni_syscall +248 common osf_fpathconf sys_ni_syscall +250 common osf_uswitch sys_ni_syscall +251 common osf_usleep_thread sys_osf_usleep_thread +252 common osf_audcntl sys_ni_syscall +253 common osf_audgen sys_ni_syscall +254 common sysfs sys_sysfs +255 common osf_subsys_info sys_ni_syscall +256 common osf_getsysinfo sys_osf_getsysinfo +257 common osf_setsysinfo sys_osf_setsysinfo +258 common osf_afs_syscall sys_ni_syscall +259 common osf_swapctl sys_ni_syscall +260 common osf_memcntl sys_ni_syscall +261 common osf_fdatasync sys_ni_syscall +300 common bdflush sys_ni_syscall +301 common sethae sys_sethae +302 common mount sys_mount +303 common old_adjtimex sys_old_adjtimex +304 common swapoff sys_swapoff +305 common getdents sys_getdents +306 common create_module sys_ni_syscall +307 common init_module sys_init_module +308 common delete_module sys_delete_module +309 common get_kernel_syms sys_ni_syscall +310 common syslog sys_syslog +311 common reboot sys_reboot +312 common clone alpha_clone +313 common uselib sys_uselib +314 common mlock sys_mlock +315 common munlock sys_munlock +316 common mlockall sys_mlockall +317 common munlockall sys_munlockall +318 common sysinfo sys_sysinfo +319 common _sysctl sys_ni_syscall +# 320 was sys_idle +321 common oldumount sys_oldumount +322 common swapon sys_swapon +323 common times sys_times +324 common personality sys_personality +325 common setfsuid sys_setfsuid +326 common setfsgid sys_setfsgid +327 common ustat sys_ustat +328 common statfs sys_statfs +329 common fstatfs sys_fstatfs +330 common sched_setparam sys_sched_setparam +331 common sched_getparam sys_sched_getparam +332 common sched_setscheduler sys_sched_setscheduler +333 common sched_getscheduler sys_sched_getscheduler +334 common sched_yield sys_sched_yield +335 common sched_get_priority_max sys_sched_get_priority_max +336 common sched_get_priority_min sys_sched_get_priority_min +337 common sched_rr_get_interval sys_sched_rr_get_interval +338 common afs_syscall sys_ni_syscall +339 common uname sys_newuname +340 common nanosleep sys_nanosleep +341 common mremap sys_mremap +342 common nfsservctl sys_ni_syscall +343 common setresuid sys_setresuid +344 common getresuid sys_getresuid +345 common pciconfig_read sys_pciconfig_read +346 common pciconfig_write sys_pciconfig_write +347 common query_module sys_ni_syscall +348 common prctl sys_prctl +349 common pread64 sys_pread64 +350 common pwrite64 sys_pwrite64 +351 common rt_sigreturn sys_rt_sigreturn +352 common rt_sigaction sys_rt_sigaction +353 common rt_sigprocmask sys_rt_sigprocmask +354 common rt_sigpending sys_rt_sigpending +355 common rt_sigtimedwait sys_rt_sigtimedwait +356 common rt_sigqueueinfo sys_rt_sigqueueinfo +357 common rt_sigsuspend sys_rt_sigsuspend +358 common select sys_select +359 common gettimeofday sys_gettimeofday +360 common settimeofday sys_settimeofday +361 common getitimer sys_getitimer +362 common setitimer sys_setitimer +363 common utimes sys_utimes +364 common getrusage sys_getrusage +365 common wait4 sys_wait4 +366 common adjtimex sys_adjtimex +367 common getcwd sys_getcwd +368 common capget sys_capget +369 common capset sys_capset +370 common sendfile sys_sendfile64 +371 common setresgid sys_setresgid +372 common getresgid sys_getresgid +373 common dipc sys_ni_syscall +374 common pivot_root sys_pivot_root +375 common mincore sys_mincore +376 common pciconfig_iobase sys_pciconfig_iobase +377 common getdents64 sys_getdents64 +378 common gettid sys_gettid +379 common readahead sys_readahead +# 380 is unused +381 common tkill sys_tkill +382 common setxattr sys_setxattr +383 common lsetxattr sys_lsetxattr +384 common fsetxattr sys_fsetxattr +385 common getxattr sys_getxattr +386 common lgetxattr sys_lgetxattr +387 common fgetxattr sys_fgetxattr +388 common listxattr sys_listxattr +389 common llistxattr sys_llistxattr +390 common flistxattr sys_flistxattr +391 common removexattr sys_removexattr +392 common lremovexattr sys_lremovexattr +393 common fremovexattr sys_fremovexattr +394 common futex sys_futex +395 common sched_setaffinity sys_sched_setaffinity +396 common sched_getaffinity sys_sched_getaffinity +397 common tuxcall sys_ni_syscall +398 common io_setup sys_io_setup +399 common io_destroy sys_io_destroy +400 common io_getevents sys_io_getevents +401 common io_submit sys_io_submit +402 common io_cancel sys_io_cancel +405 common exit_group sys_exit_group +406 common lookup_dcookie sys_ni_syscall +407 common epoll_create sys_epoll_create +408 common epoll_ctl sys_epoll_ctl +409 common epoll_wait sys_epoll_wait +410 common remap_file_pages sys_remap_file_pages +411 common set_tid_address sys_set_tid_address +412 common restart_syscall sys_restart_syscall +413 common fadvise64 sys_fadvise64 +414 common timer_create sys_timer_create +415 common timer_settime sys_timer_settime +416 common timer_gettime sys_timer_gettime +417 common timer_getoverrun sys_timer_getoverrun +418 common timer_delete sys_timer_delete +419 common clock_settime sys_clock_settime +420 common clock_gettime sys_clock_gettime +421 common clock_getres sys_clock_getres +422 common clock_nanosleep sys_clock_nanosleep +423 common semtimedop sys_semtimedop +424 common tgkill sys_tgkill +425 common stat64 sys_stat64 +426 common lstat64 sys_lstat64 +427 common fstat64 sys_fstat64 +428 common vserver sys_ni_syscall +429 common mbind sys_ni_syscall +430 common get_mempolicy sys_ni_syscall +431 common set_mempolicy sys_ni_syscall +432 common mq_open sys_mq_open +433 common mq_unlink sys_mq_unlink +434 common mq_timedsend sys_mq_timedsend +435 common mq_timedreceive sys_mq_timedreceive +436 common mq_notify sys_mq_notify +437 common mq_getsetattr sys_mq_getsetattr +438 common waitid sys_waitid +439 common add_key sys_add_key +440 common request_key sys_request_key +441 common keyctl sys_keyctl +442 common ioprio_set sys_ioprio_set +443 common ioprio_get sys_ioprio_get +444 common inotify_init sys_inotify_init +445 common inotify_add_watch sys_inotify_add_watch +446 common inotify_rm_watch sys_inotify_rm_watch +447 common fdatasync sys_fdatasync +448 common kexec_load sys_kexec_load +449 common migrate_pages sys_migrate_pages +450 common openat sys_openat +451 common mkdirat sys_mkdirat +452 common mknodat sys_mknodat +453 common fchownat sys_fchownat +454 common futimesat sys_futimesat +455 common fstatat64 sys_fstatat64 +456 common unlinkat sys_unlinkat +457 common renameat sys_renameat +458 common linkat sys_linkat +459 common symlinkat sys_symlinkat +460 common readlinkat sys_readlinkat +461 common fchmodat sys_fchmodat +462 common faccessat sys_faccessat +463 common pselect6 sys_pselect6 +464 common ppoll sys_ppoll +465 common unshare sys_unshare +466 common set_robust_list sys_set_robust_list +467 common get_robust_list sys_get_robust_list +468 common splice sys_splice +469 common sync_file_range sys_sync_file_range +470 common tee sys_tee +471 common vmsplice sys_vmsplice +472 common move_pages sys_move_pages +473 common getcpu sys_getcpu +474 common epoll_pwait sys_epoll_pwait +475 common utimensat sys_utimensat +476 common signalfd sys_signalfd +477 common timerfd sys_ni_syscall +478 common eventfd sys_eventfd +479 common recvmmsg sys_recvmmsg +480 common fallocate sys_fallocate +481 common timerfd_create sys_timerfd_create +482 common timerfd_settime sys_timerfd_settime +483 common timerfd_gettime sys_timerfd_gettime +484 common signalfd4 sys_signalfd4 +485 common eventfd2 sys_eventfd2 +486 common epoll_create1 sys_epoll_create1 +487 common dup3 sys_dup3 +488 common pipe2 sys_pipe2 +489 common inotify_init1 sys_inotify_init1 +490 common preadv sys_preadv +491 common pwritev sys_pwritev +492 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +493 common perf_event_open sys_perf_event_open +494 common fanotify_init sys_fanotify_init +495 common fanotify_mark sys_fanotify_mark +496 common prlimit64 sys_prlimit64 +497 common name_to_handle_at sys_name_to_handle_at +498 common open_by_handle_at sys_open_by_handle_at +499 common clock_adjtime sys_clock_adjtime +500 common syncfs sys_syncfs +501 common setns sys_setns +502 common accept4 sys_accept4 +503 common sendmmsg sys_sendmmsg +504 common process_vm_readv sys_process_vm_readv +505 common process_vm_writev sys_process_vm_writev +506 common kcmp sys_kcmp +507 common finit_module sys_finit_module +508 common sched_setattr sys_sched_setattr +509 common sched_getattr sys_sched_getattr +510 common renameat2 sys_renameat2 +511 common getrandom sys_getrandom +512 common memfd_create sys_memfd_create +513 common execveat sys_execveat +514 common seccomp sys_seccomp +515 common bpf sys_bpf +516 common userfaultfd sys_userfaultfd +517 common membarrier sys_membarrier +518 common mlock2 sys_mlock2 +519 common copy_file_range sys_copy_file_range +520 common preadv2 sys_preadv2 +521 common pwritev2 sys_pwritev2 +522 common statx sys_statx +523 common io_pgetevents sys_io_pgetevents +524 common pkey_mprotect sys_pkey_mprotect +525 common pkey_alloc sys_pkey_alloc +526 common pkey_free sys_pkey_free +527 common rseq sys_rseq +528 common statfs64 sys_statfs64 +529 common fstatfs64 sys_fstatfs64 +530 common getegid sys_getegid +531 common geteuid sys_geteuid +532 common getppid sys_getppid +# all other architectures have common numbers for new syscall, alpha +# is the exception. +534 common pidfd_send_signal sys_pidfd_send_signal +535 common io_uring_setup sys_io_uring_setup +536 common io_uring_enter sys_io_uring_enter +537 common io_uring_register sys_io_uring_register +538 common open_tree sys_open_tree +539 common move_mount sys_move_mount +540 common fsopen sys_fsopen +541 common fsconfig sys_fsconfig +542 common fsmount sys_fsmount +543 common fspick sys_fspick +544 common pidfd_open sys_pidfd_open +545 common clone3 alpha_clone3 +546 common close_range sys_close_range +547 common openat2 sys_openat2 +548 common pidfd_getfd sys_pidfd_getfd +549 common faccessat2 sys_faccessat2 +550 common process_madvise sys_process_madvise +551 common epoll_pwait2 sys_epoll_pwait2 +552 common mount_setattr sys_mount_setattr +553 common quotactl_fd sys_quotactl_fd +554 common landlock_create_ruleset sys_landlock_create_ruleset +555 common landlock_add_rule sys_landlock_add_rule +556 common landlock_restrict_self sys_landlock_restrict_self +# 557 reserved for memfd_secret +558 common process_mrelease sys_process_mrelease +559 common futex_waitv sys_futex_waitv +560 common set_mempolicy_home_node sys_ni_syscall +561 common cachestat sys_cachestat +562 common fchmodat2 sys_fchmodat2 +563 common map_shadow_stack sys_map_shadow_stack +564 common futex_wake sys_futex_wake +565 common futex_wait sys_futex_wait +566 common futex_requeue sys_futex_requeue +567 common statmount sys_statmount +568 common listmount sys_listmount +569 common lsm_get_self_attr sys_lsm_get_self_attr +570 common lsm_set_self_attr sys_lsm_set_self_attr +571 common lsm_list_modules sys_lsm_list_modules +572 common mseal sys_mseal diff --git a/tools/perf/arch/alpha/include/syscall_table.h b/tools/perf/arch/alpha/include/syscall_table.h new file mode 100644 index 000000000000..b53e31c15805 --- /dev/null +++ b/tools/perf/arch/alpha/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_64.h> diff --git a/tools/perf/arch/arc/entry/syscalls/Kbuild b/tools/perf/arch/arc/entry/syscalls/Kbuild new file mode 100644 index 000000000000..11707c481a24 --- /dev/null +++ b/tools/perf/arch/arc/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h diff --git a/tools/perf/arch/arc/entry/syscalls/Makefile.syscalls b/tools/perf/arch/arc/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..391d30ab7a83 --- /dev/null +++ b/tools/perf/arch/arc/entry/syscalls/Makefile.syscalls @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += arc time32 renameat stat64 rlimit diff --git a/tools/perf/arch/arc/include/syscall_table.h b/tools/perf/arch/arc/include/syscall_table.h new file mode 100644 index 000000000000..4c942821662d --- /dev/null +++ b/tools/perf/arch/arc/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_32.h> diff --git a/tools/perf/arch/arm/entry/syscalls/Kbuild b/tools/perf/arch/arm/entry/syscalls/Kbuild new file mode 100644 index 000000000000..9d777540f089 --- /dev/null +++ b/tools/perf/arch/arm/entry/syscalls/Kbuild @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += oabi +syscalltbl = $(srctree)/tools/perf/arch/arm/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/arm/entry/syscalls/Makefile.syscalls b/tools/perf/arch/arm/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..11707c481a24 --- /dev/null +++ b/tools/perf/arch/arm/entry/syscalls/Makefile.syscalls @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..49eeb2ad8dbd --- /dev/null +++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl @@ -0,0 +1,483 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# Linux system call numbers and entry vectors +# +# The format is: +# <num> <abi> <name> [<entry point> [<oabi compat entry point>]] +# +# Where abi is: +# common - for system calls shared between oabi and eabi (may have compat) +# oabi - for oabi-only system calls (may have compat) +# eabi - for eabi-only system calls +# +# For each syscall number, "common" is mutually exclusive with oabi and eabi +# +0 common restart_syscall sys_restart_syscall +1 common exit sys_exit +2 common fork sys_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open +6 common close sys_close +# 7 was sys_waitpid +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 common execve sys_execve +12 common chdir sys_chdir +13 oabi time sys_time32 +14 common mknod sys_mknod +15 common chmod sys_chmod +16 common lchown sys_lchown16 +# 17 was sys_break +# 18 was sys_stat +19 common lseek sys_lseek +20 common getpid sys_getpid +21 common mount sys_mount +22 oabi umount sys_oldumount +23 common setuid sys_setuid16 +24 common getuid sys_getuid16 +25 oabi stime sys_stime32 +26 common ptrace sys_ptrace +27 oabi alarm sys_alarm +# 28 was sys_fstat +29 common pause sys_pause +30 oabi utime sys_utime32 +# 31 was sys_stty +# 32 was sys_gtty +33 common access sys_access +34 common nice sys_nice +# 35 was sys_ftime +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_pipe +43 common times sys_times +# 44 was sys_prof +45 common brk sys_brk +46 common setgid sys_setgid16 +47 common getgid sys_getgid16 +# 48 was sys_signal +49 common geteuid sys_geteuid16 +50 common getegid sys_getegid16 +51 common acct sys_acct +52 common umount2 sys_umount +# 53 was sys_lock +54 common ioctl sys_ioctl +55 common fcntl sys_fcntl +# 56 was sys_mpx +57 common setpgid sys_setpgid +# 58 was sys_ulimit +# 59 was sys_olduname +60 common umask sys_umask +61 common chroot sys_chroot +62 common ustat sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 common sigaction sys_sigaction +# 68 was sys_sgetmask +# 69 was sys_ssetmask +70 common setreuid sys_setreuid16 +71 common setregid sys_setregid16 +72 common sigsuspend sys_sigsuspend +73 common sigpending sys_sigpending +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit +# Back compat 2GB limited rlimit +76 oabi getrlimit sys_old_getrlimit +77 common getrusage sys_getrusage +78 common gettimeofday sys_gettimeofday +79 common settimeofday sys_settimeofday +80 common getgroups sys_getgroups16 +81 common setgroups sys_setgroups16 +82 oabi select sys_old_select +83 common symlink sys_symlink +# 84 was sys_lstat +85 common readlink sys_readlink +86 common uselib sys_uselib +87 common swapon sys_swapon +88 common reboot sys_reboot +89 oabi readdir sys_old_readdir +90 oabi mmap sys_old_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate +93 common ftruncate sys_ftruncate +94 common fchmod sys_fchmod +95 common fchown sys_fchown16 +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +# 98 was sys_profil +99 common statfs sys_statfs +100 common fstatfs sys_fstatfs +# 101 was sys_ioperm +102 oabi socketcall sys_socketcall sys_oabi_socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer +105 common getitimer sys_getitimer +106 common stat sys_newstat +107 common lstat sys_newlstat +108 common fstat sys_newfstat +# 109 was sys_uname +# 110 was sys_iopl +111 common vhangup sys_vhangup +# 112 was sys_idle +# syscall to call a syscall! +113 oabi syscall sys_syscall +114 common wait4 sys_wait4 +115 common swapoff sys_swapoff +116 common sysinfo sys_sysinfo +117 oabi ipc sys_ipc sys_oabi_ipc +118 common fsync sys_fsync +119 common sigreturn sys_sigreturn_wrapper +120 common clone sys_clone +121 common setdomainname sys_setdomainname +122 common uname sys_newuname +# 123 was sys_modify_ldt +124 common adjtimex sys_adjtimex_time32 +125 common mprotect sys_mprotect +126 common sigprocmask sys_sigprocmask +# 127 was sys_create_module +128 common init_module sys_init_module +129 common delete_module sys_delete_module +# 130 was sys_get_kernel_syms +131 common quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_ni_syscall +135 common sysfs sys_sysfs +136 common personality sys_personality +# 137 was sys_afs_syscall +138 common setfsuid sys_setfsuid16 +139 common setfsgid sys_setfsgid16 +140 common _llseek sys_llseek +141 common getdents sys_getdents +142 common _newselect sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv +146 common writev sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 common _sysctl sys_ni_syscall +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep_time32 +163 common mremap sys_mremap +164 common setresuid sys_setresuid16 +165 common getresuid sys_getresuid16 +# 166 was sys_vm86 +# 167 was sys_query_module +168 common poll sys_poll +169 common nfsservctl +170 common setresgid sys_setresgid16 +171 common getresgid sys_getresgid16 +172 common prctl sys_prctl +173 common rt_sigreturn sys_rt_sigreturn_wrapper +174 common rt_sigaction sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending +177 common rt_sigtimedwait sys_rt_sigtimedwait_time32 +178 common rt_sigqueueinfo sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend +180 common pread64 sys_pread64 sys_oabi_pread64 +181 common pwrite64 sys_pwrite64 sys_oabi_pwrite64 +182 common chown sys_chown16 +183 common getcwd sys_getcwd +184 common capget sys_capget +185 common capset sys_capset +186 common sigaltstack sys_sigaltstack +187 common sendfile sys_sendfile +# 188 reserved +# 189 reserved +190 common vfork sys_vfork +# SuS compliant getrlimit +191 common ugetrlimit sys_getrlimit +192 common mmap2 sys_mmap2 +193 common truncate64 sys_truncate64 sys_oabi_truncate64 +194 common ftruncate64 sys_ftruncate64 sys_oabi_ftruncate64 +195 common stat64 sys_stat64 sys_oabi_stat64 +196 common lstat64 sys_lstat64 sys_oabi_lstat64 +197 common fstat64 sys_fstat64 sys_oabi_fstat64 +198 common lchown32 sys_lchown +199 common getuid32 sys_getuid +200 common getgid32 sys_getgid +201 common geteuid32 sys_geteuid +202 common getegid32 sys_getegid +203 common setreuid32 sys_setreuid +204 common setregid32 sys_setregid +205 common getgroups32 sys_getgroups +206 common setgroups32 sys_setgroups +207 common fchown32 sys_fchown +208 common setresuid32 sys_setresuid +209 common getresuid32 sys_getresuid +210 common setresgid32 sys_setresgid +211 common getresgid32 sys_getresgid +212 common chown32 sys_chown +213 common setuid32 sys_setuid +214 common setgid32 sys_setgid +215 common setfsuid32 sys_setfsuid +216 common setfsgid32 sys_setfsgid +217 common getdents64 sys_getdents64 +218 common pivot_root sys_pivot_root +219 common mincore sys_mincore +220 common madvise sys_madvise +221 common fcntl64 sys_fcntl64 sys_oabi_fcntl64 +# 222 for tux +# 223 is unused +224 common gettid sys_gettid +225 common readahead sys_readahead sys_oabi_readahead +226 common setxattr sys_setxattr +227 common lsetxattr sys_lsetxattr +228 common fsetxattr sys_fsetxattr +229 common getxattr sys_getxattr +230 common lgetxattr sys_lgetxattr +231 common fgetxattr sys_fgetxattr +232 common listxattr sys_listxattr +233 common llistxattr sys_llistxattr +234 common flistxattr sys_flistxattr +235 common removexattr sys_removexattr +236 common lremovexattr sys_lremovexattr +237 common fremovexattr sys_fremovexattr +238 common tkill sys_tkill +239 common sendfile64 sys_sendfile64 +240 common futex sys_futex_time32 +241 common sched_setaffinity sys_sched_setaffinity +242 common sched_getaffinity sys_sched_getaffinity +243 common io_setup sys_io_setup +244 common io_destroy sys_io_destroy +245 common io_getevents sys_io_getevents_time32 +246 common io_submit sys_io_submit +247 common io_cancel sys_io_cancel +248 common exit_group sys_exit_group +249 common lookup_dcookie sys_ni_syscall +250 common epoll_create sys_epoll_create +251 common epoll_ctl sys_epoll_ctl sys_oabi_epoll_ctl +252 common epoll_wait sys_epoll_wait +253 common remap_file_pages sys_remap_file_pages +# 254 for set_thread_area +# 255 for get_thread_area +256 common set_tid_address sys_set_tid_address +257 common timer_create sys_timer_create +258 common timer_settime sys_timer_settime32 +259 common timer_gettime sys_timer_gettime32 +260 common timer_getoverrun sys_timer_getoverrun +261 common timer_delete sys_timer_delete +262 common clock_settime sys_clock_settime32 +263 common clock_gettime sys_clock_gettime32 +264 common clock_getres sys_clock_getres_time32 +265 common clock_nanosleep sys_clock_nanosleep_time32 +266 common statfs64 sys_statfs64_wrapper +267 common fstatfs64 sys_fstatfs64_wrapper +268 common tgkill sys_tgkill +269 common utimes sys_utimes_time32 +270 common arm_fadvise64_64 sys_arm_fadvise64_64 +271 common pciconfig_iobase sys_pciconfig_iobase +272 common pciconfig_read sys_pciconfig_read +273 common pciconfig_write sys_pciconfig_write +274 common mq_open sys_mq_open +275 common mq_unlink sys_mq_unlink +276 common mq_timedsend sys_mq_timedsend_time32 +277 common mq_timedreceive sys_mq_timedreceive_time32 +278 common mq_notify sys_mq_notify +279 common mq_getsetattr sys_mq_getsetattr +280 common waitid sys_waitid +281 common socket sys_socket +282 common bind sys_bind sys_oabi_bind +283 common connect sys_connect sys_oabi_connect +284 common listen sys_listen +285 common accept sys_accept +286 common getsockname sys_getsockname +287 common getpeername sys_getpeername +288 common socketpair sys_socketpair +289 common send sys_send +290 common sendto sys_sendto sys_oabi_sendto +291 common recv sys_recv +292 common recvfrom sys_recvfrom +293 common shutdown sys_shutdown +294 common setsockopt sys_setsockopt +295 common getsockopt sys_getsockopt +296 common sendmsg sys_sendmsg sys_oabi_sendmsg +297 common recvmsg sys_recvmsg +298 common semop sys_semop sys_oabi_semop +299 common semget sys_semget +300 common semctl sys_old_semctl +301 common msgsnd sys_msgsnd +302 common msgrcv sys_msgrcv +303 common msgget sys_msgget +304 common msgctl sys_old_msgctl +305 common shmat sys_shmat +306 common shmdt sys_shmdt +307 common shmget sys_shmget +308 common shmctl sys_old_shmctl +309 common add_key sys_add_key +310 common request_key sys_request_key +311 common keyctl sys_keyctl +312 common semtimedop sys_semtimedop_time32 sys_oabi_semtimedop +313 common vserver +314 common ioprio_set sys_ioprio_set +315 common ioprio_get sys_ioprio_get +316 common inotify_init sys_inotify_init +317 common inotify_add_watch sys_inotify_add_watch +318 common inotify_rm_watch sys_inotify_rm_watch +319 common mbind sys_mbind +320 common get_mempolicy sys_get_mempolicy +321 common set_mempolicy sys_set_mempolicy +322 common openat sys_openat +323 common mkdirat sys_mkdirat +324 common mknodat sys_mknodat +325 common fchownat sys_fchownat +326 common futimesat sys_futimesat_time32 +327 common fstatat64 sys_fstatat64 sys_oabi_fstatat64 +328 common unlinkat sys_unlinkat +329 common renameat sys_renameat +330 common linkat sys_linkat +331 common symlinkat sys_symlinkat +332 common readlinkat sys_readlinkat +333 common fchmodat sys_fchmodat +334 common faccessat sys_faccessat +335 common pselect6 sys_pselect6_time32 +336 common ppoll sys_ppoll_time32 +337 common unshare sys_unshare +338 common set_robust_list sys_set_robust_list +339 common get_robust_list sys_get_robust_list +340 common splice sys_splice +341 common arm_sync_file_range sys_sync_file_range2 +342 common tee sys_tee +343 common vmsplice sys_vmsplice +344 common move_pages sys_move_pages +345 common getcpu sys_getcpu +346 common epoll_pwait sys_epoll_pwait +347 common kexec_load sys_kexec_load +348 common utimensat sys_utimensat_time32 +349 common signalfd sys_signalfd +350 common timerfd_create sys_timerfd_create +351 common eventfd sys_eventfd +352 common fallocate sys_fallocate +353 common timerfd_settime sys_timerfd_settime32 +354 common timerfd_gettime sys_timerfd_gettime32 +355 common signalfd4 sys_signalfd4 +356 common eventfd2 sys_eventfd2 +357 common epoll_create1 sys_epoll_create1 +358 common dup3 sys_dup3 +359 common pipe2 sys_pipe2 +360 common inotify_init1 sys_inotify_init1 +361 common preadv sys_preadv +362 common pwritev sys_pwritev +363 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +364 common perf_event_open sys_perf_event_open +365 common recvmmsg sys_recvmmsg_time32 +366 common accept4 sys_accept4 +367 common fanotify_init sys_fanotify_init +368 common fanotify_mark sys_fanotify_mark +369 common prlimit64 sys_prlimit64 +370 common name_to_handle_at sys_name_to_handle_at +371 common open_by_handle_at sys_open_by_handle_at +372 common clock_adjtime sys_clock_adjtime32 +373 common syncfs sys_syncfs +374 common sendmmsg sys_sendmmsg +375 common setns sys_setns +376 common process_vm_readv sys_process_vm_readv +377 common process_vm_writev sys_process_vm_writev +378 common kcmp sys_kcmp +379 common finit_module sys_finit_module +380 common sched_setattr sys_sched_setattr +381 common sched_getattr sys_sched_getattr +382 common renameat2 sys_renameat2 +383 common seccomp sys_seccomp +384 common getrandom sys_getrandom +385 common memfd_create sys_memfd_create +386 common bpf sys_bpf +387 common execveat sys_execveat +388 common userfaultfd sys_userfaultfd +389 common membarrier sys_membarrier +390 common mlock2 sys_mlock2 +391 common copy_file_range sys_copy_file_range +392 common preadv2 sys_preadv2 +393 common pwritev2 sys_pwritev2 +394 common pkey_mprotect sys_pkey_mprotect +395 common pkey_alloc sys_pkey_alloc +396 common pkey_free sys_pkey_free +397 common statx sys_statx +398 common rseq sys_rseq +399 common io_pgetevents sys_io_pgetevents_time32 +400 common migrate_pages sys_migrate_pages +401 common kexec_file_load sys_kexec_file_load +# 402 is unused +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 +414 common ppoll_time64 sys_ppoll +416 common io_pgetevents_time64 sys_io_pgetevents +417 common recvmmsg_time64 sys_recvmmsg +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat diff --git a/tools/perf/arch/arm/include/syscall_table.h b/tools/perf/arch/arm/include/syscall_table.h new file mode 100644 index 000000000000..4c942821662d --- /dev/null +++ b/tools/perf/arch/arm/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_32.h> diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index 91570d5d428e..087e099fb453 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -1,25 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 PERF_HAVE_JITDUMP := 1 HAVE_KVM_STAT_SUPPORT := 1 - -# -# Syscall table generation for perf -# - -out := $(OUTPUT)arch/arm64/include/generated/asm -header := $(out)/syscalls.c -incpath := $(srctree)/tools -sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h -sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/ -systbl := $(sysprf)/mksyscalltbl - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ - -clean:: - $(call QUIET_CLEAN, arm64) $(RM) $(header) - -archheaders: $(header) diff --git a/tools/perf/arch/arm64/entry/syscalls/Kbuild b/tools/perf/arch/arm64/entry/syscalls/Kbuild new file mode 100644 index 000000000000..84c6599b4ea6 --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/Kbuild @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/arm64/entry/syscalls/Makefile.syscalls b/tools/perf/arch/arm64/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..e7e78c2d1c02 --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/Makefile.syscalls @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += +syscall_abis_64 += renameat rlimit memfd_secret + +syscalltbl = $(srctree)/tools/perf/arch/arm64/entry/syscalls/syscall_%.tbl diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl deleted file mode 100755 index 27d747c92d44..000000000000 --- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,46 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate system call table for perf. Derived from -# powerpc script. -# -# Copyright IBM Corp. 2017 -# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> -# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> -# Changed by: Kim Phillips <kim.phillips@arm.com> - -gcc=$1 -hostcc=$2 -incpath=$3 -input=$4 - -if ! test -r $input; then - echo "Could not read input file" >&2 - exit 1 -fi - -create_sc_table() -{ - local sc nr max_nr - - while read sc nr; do - printf "%s\n" " [$nr] = \"$sc\"," - max_nr=$nr - done - - echo "#define SYSCALLTBL_ARM64_MAX_ID $max_nr" -} - -create_table() -{ - echo "#include \"$input\"" - echo "static const char *const syscalltbl_arm64[] = {" - create_sc_table - echo "};" -} - -$gcc -E -dM -x c -I $incpath/include/uapi $input \ - |awk '$2 ~ "__NR" && $3 !~ "__NR3264_" { - sub("^#define __NR(3264)?_", ""); - print | "sort -k2 -n"}' \ - |create_table diff --git a/tools/perf/arch/arm64/entry/syscalls/syscall_32.tbl b/tools/perf/arch/arm64/entry/syscalls/syscall_32.tbl new file mode 100644 index 000000000000..9a37930d4e26 --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/syscall_32.tbl @@ -0,0 +1,476 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# AArch32 (compat) system call definitions. +# +# Copyright (C) 2001-2005 Russell King +# Copyright (C) 2012 ARM Ltd. +# +# This file corresponds to arch/arm/tools/syscall.tbl +# for the native EABI syscalls and should be kept in sync +# Instead of the OABI syscalls, it contains pointers to +# the compat entry points where they differ from the native +# syscalls. +# +0 common restart_syscall sys_restart_syscall +1 common exit sys_exit +2 common fork sys_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open compat_sys_open +6 common close sys_close +# 7 was sys_waitpid +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 common execve sys_execve compat_sys_execve +12 common chdir sys_chdir +# 13 was sys_time +14 common mknod sys_mknod +15 common chmod sys_chmod +16 common lchown sys_lchown16 +# 17 was sys_break +# 18 was sys_stat +19 common lseek sys_lseek compat_sys_lseek +20 common getpid sys_getpid +21 common mount sys_mount +# 22 was sys_umount +23 common setuid sys_setuid16 +24 common getuid sys_getuid16 +# 25 was sys_stime +26 common ptrace sys_ptrace compat_sys_ptrace +# 27 was sys_alarm +# 28 was sys_fstat +29 common pause sys_pause +# 30 was sys_utime +# 31 was sys_stty +# 32 was sys_gtty +33 common access sys_access +34 common nice sys_nice +# 35 was sys_ftime +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_pipe +43 common times sys_times compat_sys_times +# 44 was sys_prof +45 common brk sys_brk +46 common setgid sys_setgid16 +47 common getgid sys_getgid16 +# 48 was sys_signal +49 common geteuid sys_geteuid16 +50 common getegid sys_getegid16 +51 common acct sys_acct +52 common umount2 sys_umount +# 53 was sys_lock +54 common ioctl sys_ioctl compat_sys_ioctl +55 common fcntl sys_fcntl compat_sys_fcntl +# 56 was sys_mpx +57 common setpgid sys_setpgid +# 58 was sys_ulimit +# 59 was sys_olduname +60 common umask sys_umask +61 common chroot sys_chroot +62 common ustat sys_ustat compat_sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 common sigaction sys_sigaction compat_sys_sigaction +# 68 was sys_sgetmask +# 69 was sys_ssetmask +70 common setreuid sys_setreuid16 +71 common setregid sys_setregid16 +72 common sigsuspend sys_sigsuspend +73 common sigpending sys_sigpending compat_sys_sigpending +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit compat_sys_setrlimit +# 76 was compat_sys_getrlimit +77 common getrusage sys_getrusage compat_sys_getrusage +78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday +79 common settimeofday sys_settimeofday compat_sys_settimeofday +80 common getgroups sys_getgroups16 +81 common setgroups sys_setgroups16 +# 82 was compat_sys_select +83 common symlink sys_symlink +# 84 was sys_lstat +85 common readlink sys_readlink +86 common uselib sys_uselib +87 common swapon sys_swapon +88 common reboot sys_reboot +# 89 was sys_readdir +# 90 was sys_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate compat_sys_truncate +93 common ftruncate sys_ftruncate compat_sys_ftruncate +94 common fchmod sys_fchmod +95 common fchown sys_fchown16 +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +# 98 was sys_profil +99 common statfs sys_statfs compat_sys_statfs +100 common fstatfs sys_fstatfs compat_sys_fstatfs +# 101 was sys_ioperm +# 102 was sys_socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer compat_sys_setitimer +105 common getitimer sys_getitimer compat_sys_getitimer +106 common stat sys_newstat compat_sys_newstat +107 common lstat sys_newlstat compat_sys_newlstat +108 common fstat sys_newfstat compat_sys_newfstat +# 109 was sys_uname +# 110 was sys_iopl +111 common vhangup sys_vhangup +# 112 was sys_idle +# 113 was sys_syscall +114 common wait4 sys_wait4 compat_sys_wait4 +115 common swapoff sys_swapoff +116 common sysinfo sys_sysinfo compat_sys_sysinfo +# 117 was sys_ipc +118 common fsync sys_fsync +119 common sigreturn sys_sigreturn_wrapper compat_sys_sigreturn +120 common clone sys_clone +121 common setdomainname sys_setdomainname +122 common uname sys_newuname +# 123 was sys_modify_ldt +124 common adjtimex sys_adjtimex_time32 +125 common mprotect sys_mprotect +126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask +# 127 was sys_create_module +128 common init_module sys_init_module +129 common delete_module sys_delete_module +# 130 was sys_get_kernel_syms +131 common quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_ni_syscall +135 common sysfs sys_sysfs +136 common personality sys_personality +# 137 was sys_afs_syscall +138 common setfsuid sys_setfsuid16 +139 common setfsgid sys_setfsgid16 +140 common _llseek sys_llseek +141 common getdents sys_getdents compat_sys_getdents +142 common _newselect sys_select compat_sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv +146 common writev sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 common _sysctl sys_ni_syscall +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep_time32 +163 common mremap sys_mremap +164 common setresuid sys_setresuid16 +165 common getresuid sys_getresuid16 +# 166 was sys_vm86 +# 167 was sys_query_module +168 common poll sys_poll +169 common nfsservctl sys_ni_syscall +170 common setresgid sys_setresgid16 +171 common getresgid sys_getresgid16 +172 common prctl sys_prctl +173 common rt_sigreturn sys_rt_sigreturn_wrapper compat_sys_rt_sigreturn +174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +177 common rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +180 common pread64 sys_pread64 compat_sys_aarch32_pread64 +181 common pwrite64 sys_pwrite64 compat_sys_aarch32_pwrite64 +182 common chown sys_chown16 +183 common getcwd sys_getcwd +184 common capget sys_capget +185 common capset sys_capset +186 common sigaltstack sys_sigaltstack compat_sys_sigaltstack +187 common sendfile sys_sendfile compat_sys_sendfile +# 188 reserved +# 189 reserved +190 common vfork sys_vfork +# SuS compliant getrlimit +191 common ugetrlimit sys_getrlimit compat_sys_getrlimit +192 common mmap2 sys_mmap2 compat_sys_aarch32_mmap2 +193 common truncate64 sys_truncate64 compat_sys_aarch32_truncate64 +194 common ftruncate64 sys_ftruncate64 compat_sys_aarch32_ftruncate64 +195 common stat64 sys_stat64 +196 common lstat64 sys_lstat64 +197 common fstat64 sys_fstat64 +198 common lchown32 sys_lchown +199 common getuid32 sys_getuid +200 common getgid32 sys_getgid +201 common geteuid32 sys_geteuid +202 common getegid32 sys_getegid +203 common setreuid32 sys_setreuid +204 common setregid32 sys_setregid +205 common getgroups32 sys_getgroups +206 common setgroups32 sys_setgroups +207 common fchown32 sys_fchown +208 common setresuid32 sys_setresuid +209 common getresuid32 sys_getresuid +210 common setresgid32 sys_setresgid +211 common getresgid32 sys_getresgid +212 common chown32 sys_chown +213 common setuid32 sys_setuid +214 common setgid32 sys_setgid +215 common setfsuid32 sys_setfsuid +216 common setfsgid32 sys_setfsgid +217 common getdents64 sys_getdents64 +218 common pivot_root sys_pivot_root +219 common mincore sys_mincore +220 common madvise sys_madvise +221 common fcntl64 sys_fcntl64 compat_sys_fcntl64 +# 222 for tux +# 223 is unused +224 common gettid sys_gettid +225 common readahead sys_readahead compat_sys_aarch32_readahead +226 common setxattr sys_setxattr +227 common lsetxattr sys_lsetxattr +228 common fsetxattr sys_fsetxattr +229 common getxattr sys_getxattr +230 common lgetxattr sys_lgetxattr +231 common fgetxattr sys_fgetxattr +232 common listxattr sys_listxattr +233 common llistxattr sys_llistxattr +234 common flistxattr sys_flistxattr +235 common removexattr sys_removexattr +236 common lremovexattr sys_lremovexattr +237 common fremovexattr sys_fremovexattr +238 common tkill sys_tkill +239 common sendfile64 sys_sendfile64 +240 common futex sys_futex_time32 +241 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +242 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +243 common io_setup sys_io_setup compat_sys_io_setup +244 common io_destroy sys_io_destroy +245 common io_getevents sys_io_getevents_time32 +246 common io_submit sys_io_submit compat_sys_io_submit +247 common io_cancel sys_io_cancel +248 common exit_group sys_exit_group +249 common lookup_dcookie sys_ni_syscall +250 common epoll_create sys_epoll_create +251 common epoll_ctl sys_epoll_ctl +252 common epoll_wait sys_epoll_wait +253 common remap_file_pages sys_remap_file_pages +# 254 for set_thread_area +# 255 for get_thread_area +256 common set_tid_address sys_set_tid_address +257 common timer_create sys_timer_create compat_sys_timer_create +258 common timer_settime sys_timer_settime32 +259 common timer_gettime sys_timer_gettime32 +260 common timer_getoverrun sys_timer_getoverrun +261 common timer_delete sys_timer_delete +262 common clock_settime sys_clock_settime32 +263 common clock_gettime sys_clock_gettime32 +264 common clock_getres sys_clock_getres_time32 +265 common clock_nanosleep sys_clock_nanosleep_time32 +266 common statfs64 sys_statfs64_wrapper compat_sys_aarch32_statfs64 +267 common fstatfs64 sys_fstatfs64_wrapper compat_sys_aarch32_fstatfs64 +268 common tgkill sys_tgkill +269 common utimes sys_utimes_time32 +270 common arm_fadvise64_64 sys_arm_fadvise64_64 compat_sys_aarch32_fadvise64_64 +271 common pciconfig_iobase sys_pciconfig_iobase +272 common pciconfig_read sys_pciconfig_read +273 common pciconfig_write sys_pciconfig_write +274 common mq_open sys_mq_open compat_sys_mq_open +275 common mq_unlink sys_mq_unlink +276 common mq_timedsend sys_mq_timedsend_time32 +277 common mq_timedreceive sys_mq_timedreceive_time32 +278 common mq_notify sys_mq_notify compat_sys_mq_notify +279 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +280 common waitid sys_waitid compat_sys_waitid +281 common socket sys_socket +282 common bind sys_bind +283 common connect sys_connect +284 common listen sys_listen +285 common accept sys_accept +286 common getsockname sys_getsockname +287 common getpeername sys_getpeername +288 common socketpair sys_socketpair +289 common send sys_send +290 common sendto sys_sendto +291 common recv sys_recv compat_sys_recv +292 common recvfrom sys_recvfrom compat_sys_recvfrom +293 common shutdown sys_shutdown +294 common setsockopt sys_setsockopt +295 common getsockopt sys_getsockopt +296 common sendmsg sys_sendmsg compat_sys_sendmsg +297 common recvmsg sys_recvmsg compat_sys_recvmsg +298 common semop sys_semop +299 common semget sys_semget +300 common semctl sys_old_semctl compat_sys_old_semctl +301 common msgsnd sys_msgsnd compat_sys_msgsnd +302 common msgrcv sys_msgrcv compat_sys_msgrcv +303 common msgget sys_msgget +304 common msgctl sys_old_msgctl compat_sys_old_msgctl +305 common shmat sys_shmat compat_sys_shmat +306 common shmdt sys_shmdt +307 common shmget sys_shmget +308 common shmctl sys_old_shmctl compat_sys_old_shmctl +309 common add_key sys_add_key +310 common request_key sys_request_key +311 common keyctl sys_keyctl compat_sys_keyctl +312 common semtimedop sys_semtimedop_time32 +313 common vserver sys_ni_syscall +314 common ioprio_set sys_ioprio_set +315 common ioprio_get sys_ioprio_get +316 common inotify_init sys_inotify_init +317 common inotify_add_watch sys_inotify_add_watch +318 common inotify_rm_watch sys_inotify_rm_watch +319 common mbind sys_mbind +320 common get_mempolicy sys_get_mempolicy +321 common set_mempolicy sys_set_mempolicy +322 common openat sys_openat compat_sys_openat +323 common mkdirat sys_mkdirat +324 common mknodat sys_mknodat +325 common fchownat sys_fchownat +326 common futimesat sys_futimesat_time32 +327 common fstatat64 sys_fstatat64 +328 common unlinkat sys_unlinkat +329 common renameat sys_renameat +330 common linkat sys_linkat +331 common symlinkat sys_symlinkat +332 common readlinkat sys_readlinkat +333 common fchmodat sys_fchmodat +334 common faccessat sys_faccessat +335 common pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +336 common ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +337 common unshare sys_unshare +338 common set_robust_list sys_set_robust_list compat_sys_set_robust_list +339 common get_robust_list sys_get_robust_list compat_sys_get_robust_list +340 common splice sys_splice +341 common arm_sync_file_range sys_sync_file_range2 compat_sys_aarch32_sync_file_range2 +342 common tee sys_tee +343 common vmsplice sys_vmsplice +344 common move_pages sys_move_pages +345 common getcpu sys_getcpu +346 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait +347 common kexec_load sys_kexec_load compat_sys_kexec_load +348 common utimensat sys_utimensat_time32 +349 common signalfd sys_signalfd compat_sys_signalfd +350 common timerfd_create sys_timerfd_create +351 common eventfd sys_eventfd +352 common fallocate sys_fallocate compat_sys_aarch32_fallocate +353 common timerfd_settime sys_timerfd_settime32 +354 common timerfd_gettime sys_timerfd_gettime32 +355 common signalfd4 sys_signalfd4 compat_sys_signalfd4 +356 common eventfd2 sys_eventfd2 +357 common epoll_create1 sys_epoll_create1 +358 common dup3 sys_dup3 +359 common pipe2 sys_pipe2 +360 common inotify_init1 sys_inotify_init1 +361 common preadv sys_preadv compat_sys_preadv +362 common pwritev sys_pwritev compat_sys_pwritev +363 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +364 common perf_event_open sys_perf_event_open +365 common recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +366 common accept4 sys_accept4 +367 common fanotify_init sys_fanotify_init +368 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark +369 common prlimit64 sys_prlimit64 +370 common name_to_handle_at sys_name_to_handle_at +371 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +372 common clock_adjtime sys_clock_adjtime32 +373 common syncfs sys_syncfs +374 common sendmmsg sys_sendmmsg compat_sys_sendmmsg +375 common setns sys_setns +376 common process_vm_readv sys_process_vm_readv +377 common process_vm_writev sys_process_vm_writev +378 common kcmp sys_kcmp +379 common finit_module sys_finit_module +380 common sched_setattr sys_sched_setattr +381 common sched_getattr sys_sched_getattr +382 common renameat2 sys_renameat2 +383 common seccomp sys_seccomp +384 common getrandom sys_getrandom +385 common memfd_create sys_memfd_create +386 common bpf sys_bpf +387 common execveat sys_execveat compat_sys_execveat +388 common userfaultfd sys_userfaultfd +389 common membarrier sys_membarrier +390 common mlock2 sys_mlock2 +391 common copy_file_range sys_copy_file_range +392 common preadv2 sys_preadv2 compat_sys_preadv2 +393 common pwritev2 sys_pwritev2 compat_sys_pwritev2 +394 common pkey_mprotect sys_pkey_mprotect +395 common pkey_alloc sys_pkey_alloc +396 common pkey_free sys_pkey_free +397 common statx sys_statx +398 common rseq sys_rseq +399 common io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +400 common migrate_pages sys_migrate_pages +401 common kexec_file_load sys_kexec_file_load +# 402 is unused +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 common ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 common io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 +417 common recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/tools/perf/arch/arm64/entry/syscalls/syscall_64.tbl b/tools/perf/arch/arm64/entry/syscalls/syscall_64.tbl new file mode 120000 index 000000000000..4fdd58f10c15 --- /dev/null +++ b/tools/perf/arch/arm64/entry/syscalls/syscall_64.tbl @@ -0,0 +1 @@ +../../../../../scripts/syscall.tbl
\ No newline at end of file diff --git a/tools/perf/arch/arm64/include/syscall_table.h b/tools/perf/arch/arm64/include/syscall_table.h new file mode 100644 index 000000000000..7ff51b783000 --- /dev/null +++ b/tools/perf/arch/arm64/include/syscall_table.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 64 +#include <asm/syscalls_64.h> +#else +#include <asm/syscalls_32.h> +#endif diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 22b19dcc6beb..4301181b8e45 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -274,33 +274,9 @@ static void arm_spe_setup_evsel(struct evsel *evsel, struct perf_cpu_map *cpus) evsel__set_sample_bit(evsel, PHYS_ADDR); } -static int arm_spe_recording_options(struct auxtrace_record *itr, - struct evlist *evlist, - struct record_opts *opts) +static int arm_spe_setup_aux_buffer(struct record_opts *opts) { - struct arm_spe_recording *sper = - container_of(itr, struct arm_spe_recording, itr); - struct evsel *evsel, *tmp; - struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; bool privileged = perf_event_paranoid_check(-1); - struct evsel *tracking_evsel; - int err; - - sper->evlist = evlist; - - evlist__for_each_entry(evlist, evsel) { - if (evsel__is_aux_event(evsel)) { - if (!strstarts(evsel->pmu->name, ARM_SPE_PMU_NAME)) { - pr_err("Found unexpected auxtrace event: %s\n", - evsel->pmu->name); - return -EINVAL; - } - opts->full_auxtrace = true; - } - } - - if (!opts->full_auxtrace) - return 0; /* * we are in snapshot mode. @@ -330,6 +306,9 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n"); return -EINVAL; } + + pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME, + opts->auxtrace_snapshot_size); } /* We are in full trace mode but '-m,xyz' wasn't specified */ @@ -355,14 +334,15 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, } } - if (opts->auxtrace_snapshot_mode) - pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME, - opts->auxtrace_snapshot_size); + return 0; +} - evlist__for_each_entry_safe(evlist, tmp, evsel) { - if (evsel__is_aux_event(evsel)) - arm_spe_setup_evsel(evsel, cpus); - } +static int arm_spe_setup_tracking_event(struct evlist *evlist, + struct record_opts *opts) +{ + int err; + struct evsel *tracking_evsel; + struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; /* Add dummy event to keep tracking */ err = parse_event(evlist, "dummy:u"); @@ -388,6 +368,52 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, return 0; } +static int arm_spe_recording_options(struct auxtrace_record *itr, + struct evlist *evlist, + struct record_opts *opts) +{ + struct arm_spe_recording *sper = + container_of(itr, struct arm_spe_recording, itr); + struct evsel *evsel, *tmp; + struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; + bool discard = false; + int err; + + sper->evlist = evlist; + + evlist__for_each_entry(evlist, evsel) { + if (evsel__is_aux_event(evsel)) { + if (!strstarts(evsel->pmu->name, ARM_SPE_PMU_NAME)) { + pr_err("Found unexpected auxtrace event: %s\n", + evsel->pmu->name); + return -EINVAL; + } + opts->full_auxtrace = true; + } + } + + if (!opts->full_auxtrace) + return 0; + + evlist__for_each_entry_safe(evlist, tmp, evsel) { + if (evsel__is_aux_event(evsel)) { + arm_spe_setup_evsel(evsel, cpus); + if (evsel->core.attr.config & + perf_pmu__format_bits(evsel->pmu, "discard")) + discard = true; + } + } + + if (discard) + return 0; + + err = arm_spe_setup_aux_buffer(opts); + if (err) + return err; + + return arm_spe_setup_tracking_event(evlist, opts); +} + static int arm_spe_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused, struct record_opts *opts, const char *str) diff --git a/tools/perf/arch/csky/entry/syscalls/Kbuild b/tools/perf/arch/csky/entry/syscalls/Kbuild new file mode 100644 index 000000000000..11707c481a24 --- /dev/null +++ b/tools/perf/arch/csky/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h diff --git a/tools/perf/arch/csky/entry/syscalls/Makefile.syscalls b/tools/perf/arch/csky/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..ea2dd10d0571 --- /dev/null +++ b/tools/perf/arch/csky/entry/syscalls/Makefile.syscalls @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += csky time32 stat64 rlimit diff --git a/tools/perf/arch/csky/include/syscall_table.h b/tools/perf/arch/csky/include/syscall_table.h new file mode 100644 index 000000000000..4c942821662d --- /dev/null +++ b/tools/perf/arch/csky/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_32.h> diff --git a/tools/perf/arch/loongarch/Makefile b/tools/perf/arch/loongarch/Makefile index 52544d59245b..087e099fb453 100644 --- a/tools/perf/arch/loongarch/Makefile +++ b/tools/perf/arch/loongarch/Makefile @@ -1,25 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 PERF_HAVE_JITDUMP := 1 HAVE_KVM_STAT_SUPPORT := 1 - -# -# Syscall table generation for perf -# - -out := $(OUTPUT)arch/loongarch/include/generated/asm -header := $(out)/syscalls.c -incpath := $(srctree)/tools -sysdef := $(srctree)/tools/arch/loongarch/include/uapi/asm/unistd.h -sysprf := $(srctree)/tools/perf/arch/loongarch/entry/syscalls/ -systbl := $(sysprf)/mksyscalltbl - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ - -clean:: - $(call QUIET_CLEAN, loongarch) $(RM) $(header) - -archheaders: $(header) diff --git a/tools/perf/arch/loongarch/entry/syscalls/Kbuild b/tools/perf/arch/loongarch/entry/syscalls/Kbuild new file mode 100644 index 000000000000..9a41e3572c3a --- /dev/null +++ b/tools/perf/arch/loongarch/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/loongarch/entry/syscalls/Makefile.syscalls b/tools/perf/arch/loongarch/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..47d32da2aed8 --- /dev/null +++ b/tools/perf/arch/loongarch/entry/syscalls/Makefile.syscalls @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_64 += diff --git a/tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl b/tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl deleted file mode 100755 index c10ad3580aef..000000000000 --- a/tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,45 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate system call table for perf. Derived from -# powerpc script. -# -# Author(s): Ming Wang <wangming01@loongson.cn> -# Author(s): Huacai Chen <chenhuacai@loongson.cn> -# Copyright (C) 2020-2023 Loongson Technology Corporation Limited - -gcc=$1 -hostcc=$2 -incpath=$3 -input=$4 - -if ! test -r $input; then - echo "Could not read input file" >&2 - exit 1 -fi - -create_sc_table() -{ - local sc nr max_nr - - while read sc nr; do - printf "%s\n" " [$nr] = \"$sc\"," - max_nr=$nr - done - - echo "#define SYSCALLTBL_LOONGARCH_MAX_ID $max_nr" -} - -create_table() -{ - echo "#include \"$input\"" - echo "static const char *const syscalltbl_loongarch[] = {" - create_sc_table - echo "};" -} - -$gcc -E -dM -x c -I $incpath/include/uapi $input \ - |awk '$2 ~ "__NR" && $3 !~ "__NR3264_" { - sub("^#define __NR(3264)?_", ""); - print | "sort -k2 -n"}' \ - |create_table diff --git a/tools/perf/arch/loongarch/include/syscall_table.h b/tools/perf/arch/loongarch/include/syscall_table.h new file mode 100644 index 000000000000..9d0646d3455c --- /dev/null +++ b/tools/perf/arch/loongarch/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscall_table_64.h> diff --git a/tools/perf/arch/mips/Makefile b/tools/perf/arch/mips/Makefile deleted file mode 100644 index 827168f1077a..000000000000 --- a/tools/perf/arch/mips/Makefile +++ /dev/null @@ -1,18 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# Syscall table generation for perf -out := $(OUTPUT)arch/mips/include/generated/asm -header := $(out)/syscalls_n64.c -sysprf := $(srctree)/tools/perf/arch/mips/entry/syscalls -sysdef := $(sysprf)/syscall_n64.tbl -systbl := $(sysprf)/mksyscalltbl - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@ - -clean:: - $(call QUIET_CLEAN, mips) $(RM) $(header) - -archheaders: $(header) diff --git a/tools/perf/arch/mips/entry/syscalls/Kbuild b/tools/perf/arch/mips/entry/syscalls/Kbuild new file mode 100644 index 000000000000..9a41e3572c3a --- /dev/null +++ b/tools/perf/arch/mips/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/mips/entry/syscalls/Makefile.syscalls b/tools/perf/arch/mips/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..9ee914bdfb05 --- /dev/null +++ b/tools/perf/arch/mips/entry/syscalls/Makefile.syscalls @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_64 += n64 + +syscalltbl = $(srctree)/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl diff --git a/tools/perf/arch/mips/entry/syscalls/mksyscalltbl b/tools/perf/arch/mips/entry/syscalls/mksyscalltbl deleted file mode 100644 index c0d93f959c4e..000000000000 --- a/tools/perf/arch/mips/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,32 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate system call table for perf. Derived from -# s390 script. -# -# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> -# Changed by: Tiezhu Yang <yangtiezhu@loongson.cn> - -SYSCALL_TBL=$1 - -if ! test -r $SYSCALL_TBL; then - echo "Could not read input file" >&2 - exit 1 -fi - -create_table() -{ - local max_nr nr abi sc discard - - echo 'static const char *const syscalltbl_mips_n64[] = {' - while read nr abi sc discard; do - printf '\t[%d] = "%s",\n' $nr $sc - max_nr=$nr - done - echo '};' - echo "#define SYSCALLTBL_MIPS_N64_MAX_ID $max_nr" -} - -grep -E "^[[:digit:]]+[[:space:]]+(n64)" $SYSCALL_TBL \ - |sort -k1 -n \ - |create_table diff --git a/tools/perf/arch/mips/include/syscall_table.h b/tools/perf/arch/mips/include/syscall_table.h new file mode 100644 index 000000000000..b53e31c15805 --- /dev/null +++ b/tools/perf/arch/mips/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_64.h> diff --git a/tools/perf/arch/parisc/entry/syscalls/Kbuild b/tools/perf/arch/parisc/entry/syscalls/Kbuild new file mode 100644 index 000000000000..84c6599b4ea6 --- /dev/null +++ b/tools/perf/arch/parisc/entry/syscalls/Kbuild @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/parisc/entry/syscalls/Makefile.syscalls b/tools/perf/arch/parisc/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..ae326fecb83b --- /dev/null +++ b/tools/perf/arch/parisc/entry/syscalls/Makefile.syscalls @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += +syscall_abis_64 += + +syscalltbl = $(srctree)/tools/perf/arch/parisc/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/parisc/entry/syscalls/syscall.tbl b/tools/perf/arch/parisc/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..66dc406b12e4 --- /dev/null +++ b/tools/perf/arch/parisc/entry/syscalls/syscall.tbl @@ -0,0 +1,463 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# system call numbers and entry vectors for parisc +# +# The format is: +# <number> <abi> <name> <entry point> <compat entry point> +# +# The <abi> can be common, 64, or 32 for this file. +# +0 common restart_syscall sys_restart_syscall +1 common exit sys_exit +2 common fork sys_fork_wrapper +3 common read sys_read +4 common write sys_write +5 common open sys_open compat_sys_open +6 common close sys_close +7 common waitpid sys_waitpid +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 common execve sys_execve compat_sys_execve +12 common chdir sys_chdir +13 32 time sys_time32 +13 64 time sys_time +14 common mknod sys_mknod +15 common chmod sys_chmod +16 common lchown sys_lchown +17 common socket sys_socket +18 common stat sys_newstat compat_sys_newstat +19 common lseek sys_lseek compat_sys_lseek +20 common getpid sys_getpid +21 common mount sys_mount +22 common bind sys_bind +23 common setuid sys_setuid +24 common getuid sys_getuid +25 32 stime sys_stime32 +25 64 stime sys_stime +26 common ptrace sys_ptrace compat_sys_ptrace +27 common alarm sys_alarm +28 common fstat sys_newfstat compat_sys_newfstat +29 common pause sys_pause +30 32 utime sys_utime32 +30 64 utime sys_utime +31 common connect sys_connect +32 common listen sys_listen +33 common access sys_access +34 common nice sys_nice +35 common accept sys_accept +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_pipe +43 common times sys_times compat_sys_times +44 common getsockname sys_getsockname +45 common brk sys_brk +46 common setgid sys_setgid +47 common getgid sys_getgid +48 common signal sys_signal +49 common geteuid sys_geteuid +50 common getegid sys_getegid +51 common acct sys_acct +52 common umount2 sys_umount +53 common getpeername sys_getpeername +54 common ioctl sys_ioctl compat_sys_ioctl +55 common fcntl sys_fcntl compat_sys_fcntl +56 common socketpair sys_socketpair +57 common setpgid sys_setpgid +58 common send sys_send +59 common uname sys_newuname +60 common umask sys_umask +61 common chroot sys_chroot +62 common ustat sys_ustat compat_sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 common pivot_root sys_pivot_root +68 common sgetmask sys_sgetmask sys32_unimplemented +69 common ssetmask sys_ssetmask sys32_unimplemented +70 common setreuid sys_setreuid +71 common setregid sys_setregid +72 common mincore sys_mincore +73 common sigpending sys_sigpending compat_sys_sigpending +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit compat_sys_setrlimit +76 common getrlimit sys_getrlimit compat_sys_getrlimit +77 common getrusage sys_getrusage compat_sys_getrusage +78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday +79 common settimeofday sys_settimeofday compat_sys_settimeofday +80 common getgroups sys_getgroups +81 common setgroups sys_setgroups +82 common sendto sys_sendto +83 common symlink sys_symlink +84 common lstat sys_newlstat compat_sys_newlstat +85 common readlink sys_readlink +86 common uselib sys_ni_syscall +87 common swapon sys_swapon +88 common reboot sys_reboot +89 common mmap2 sys_mmap2 +90 common mmap sys_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate compat_sys_truncate +93 common ftruncate sys_ftruncate compat_sys_ftruncate +94 common fchmod sys_fchmod +95 common fchown sys_fchown +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +98 common recv sys_recv compat_sys_recv +99 common statfs sys_statfs compat_sys_statfs +100 common fstatfs sys_fstatfs compat_sys_fstatfs +101 common stat64 sys_stat64 +# 102 was socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer compat_sys_setitimer +105 common getitimer sys_getitimer compat_sys_getitimer +106 common capget sys_capget +107 common capset sys_capset +108 32 pread64 parisc_pread64 +108 64 pread64 sys_pread64 +109 32 pwrite64 parisc_pwrite64 +109 64 pwrite64 sys_pwrite64 +110 common getcwd sys_getcwd +111 common vhangup sys_vhangup +112 common fstat64 sys_fstat64 +113 common vfork sys_vfork_wrapper +114 common wait4 sys_wait4 compat_sys_wait4 +115 common swapoff sys_swapoff +116 common sysinfo sys_sysinfo compat_sys_sysinfo +117 common shutdown sys_shutdown +118 common fsync sys_fsync +119 common madvise parisc_madvise +120 common clone sys_clone_wrapper +121 common setdomainname sys_setdomainname +122 common sendfile sys_sendfile compat_sys_sendfile +123 common recvfrom sys_recvfrom compat_sys_recvfrom +124 32 adjtimex sys_adjtimex_time32 +124 64 adjtimex sys_adjtimex +125 common mprotect sys_mprotect +126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask +# 127 was create_module +128 common init_module sys_init_module +129 common delete_module sys_delete_module +# 130 was get_kernel_syms +131 common quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_ni_syscall +135 common sysfs sys_sysfs +136 32 personality parisc_personality +136 64 personality sys_personality +# 137 was afs_syscall +138 common setfsuid sys_setfsuid +139 common setfsgid sys_setfsgid +140 common _llseek sys_llseek +141 common getdents sys_getdents compat_sys_getdents +142 common _newselect sys_select compat_sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv +146 common writev sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 common _sysctl sys_ni_syscall +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 32 sched_rr_get_interval sys_sched_rr_get_interval_time32 +161 64 sched_rr_get_interval sys_sched_rr_get_interval +162 32 nanosleep sys_nanosleep_time32 +162 64 nanosleep sys_nanosleep +163 common mremap sys_mremap +164 common setresuid sys_setresuid +165 common getresuid sys_getresuid +166 common sigaltstack sys_sigaltstack compat_sys_sigaltstack +# 167 was query_module +168 common poll sys_poll +# 169 was nfsservctl +170 common setresgid sys_setresgid +171 common getresgid sys_getresgid +172 common prctl sys_prctl +173 common rt_sigreturn sys_rt_sigreturn_wrapper +174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +177 32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +177 64 rt_sigtimedwait sys_rt_sigtimedwait +178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +180 common chown sys_chown +181 common setsockopt sys_setsockopt sys_setsockopt +182 common getsockopt sys_getsockopt sys_getsockopt +183 common sendmsg sys_sendmsg compat_sys_sendmsg +184 common recvmsg sys_recvmsg compat_sys_recvmsg +185 common semop sys_semop +186 common semget sys_semget +187 common semctl sys_semctl compat_sys_semctl +188 common msgsnd sys_msgsnd compat_sys_msgsnd +189 common msgrcv sys_msgrcv compat_sys_msgrcv +190 common msgget sys_msgget +191 common msgctl sys_msgctl compat_sys_msgctl +192 common shmat sys_shmat compat_sys_shmat +193 common shmdt sys_shmdt +194 common shmget sys_shmget +195 common shmctl sys_shmctl compat_sys_shmctl +# 196 was getpmsg +# 197 was putpmsg +198 common lstat64 sys_lstat64 +199 32 truncate64 parisc_truncate64 +199 64 truncate64 sys_truncate64 +200 32 ftruncate64 parisc_ftruncate64 +200 64 ftruncate64 sys_ftruncate64 +201 common getdents64 sys_getdents64 +202 common fcntl64 sys_fcntl64 compat_sys_fcntl64 +# 203 was attrctl +# 204 was acl_get +# 205 was acl_set +206 common gettid sys_gettid +207 32 readahead parisc_readahead +207 64 readahead sys_readahead +208 common tkill sys_tkill +209 common sendfile64 sys_sendfile64 compat_sys_sendfile64 +210 32 futex sys_futex_time32 +210 64 futex sys_futex +211 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +212 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +# 213 was set_thread_area +# 214 was get_thread_area +215 common io_setup sys_io_setup compat_sys_io_setup +216 common io_destroy sys_io_destroy +217 32 io_getevents sys_io_getevents_time32 +217 64 io_getevents sys_io_getevents +218 common io_submit sys_io_submit compat_sys_io_submit +219 common io_cancel sys_io_cancel +# 220 was alloc_hugepages +# 221 was free_hugepages +222 common exit_group sys_exit_group +223 common lookup_dcookie sys_ni_syscall +224 common epoll_create sys_epoll_create +225 common epoll_ctl sys_epoll_ctl +226 common epoll_wait sys_epoll_wait +227 common remap_file_pages sys_remap_file_pages +228 32 semtimedop sys_semtimedop_time32 +228 64 semtimedop sys_semtimedop +229 common mq_open sys_mq_open compat_sys_mq_open +230 common mq_unlink sys_mq_unlink +231 32 mq_timedsend sys_mq_timedsend_time32 +231 64 mq_timedsend sys_mq_timedsend +232 32 mq_timedreceive sys_mq_timedreceive_time32 +232 64 mq_timedreceive sys_mq_timedreceive +233 common mq_notify sys_mq_notify compat_sys_mq_notify +234 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +235 common waitid sys_waitid compat_sys_waitid +236 32 fadvise64_64 parisc_fadvise64_64 +236 64 fadvise64_64 sys_fadvise64_64 +237 common set_tid_address sys_set_tid_address +238 common setxattr sys_setxattr +239 common lsetxattr sys_lsetxattr +240 common fsetxattr sys_fsetxattr +241 common getxattr sys_getxattr +242 common lgetxattr sys_lgetxattr +243 common fgetxattr sys_fgetxattr +244 common listxattr sys_listxattr +245 common llistxattr sys_llistxattr +246 common flistxattr sys_flistxattr +247 common removexattr sys_removexattr +248 common lremovexattr sys_lremovexattr +249 common fremovexattr sys_fremovexattr +250 common timer_create sys_timer_create compat_sys_timer_create +251 32 timer_settime sys_timer_settime32 +251 64 timer_settime sys_timer_settime +252 32 timer_gettime sys_timer_gettime32 +252 64 timer_gettime sys_timer_gettime +253 common timer_getoverrun sys_timer_getoverrun +254 common timer_delete sys_timer_delete +255 32 clock_settime sys_clock_settime32 +255 64 clock_settime sys_clock_settime +256 32 clock_gettime sys_clock_gettime32 +256 64 clock_gettime sys_clock_gettime +257 32 clock_getres sys_clock_getres_time32 +257 64 clock_getres sys_clock_getres +258 32 clock_nanosleep sys_clock_nanosleep_time32 +258 64 clock_nanosleep sys_clock_nanosleep +259 common tgkill sys_tgkill +260 common mbind sys_mbind +261 common get_mempolicy sys_get_mempolicy +262 common set_mempolicy sys_set_mempolicy +# 263 was vserver +264 common add_key sys_add_key +265 common request_key sys_request_key +266 common keyctl sys_keyctl compat_sys_keyctl +267 common ioprio_set sys_ioprio_set +268 common ioprio_get sys_ioprio_get +269 common inotify_init sys_inotify_init +270 common inotify_add_watch sys_inotify_add_watch +271 common inotify_rm_watch sys_inotify_rm_watch +272 common migrate_pages sys_migrate_pages +273 32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +273 64 pselect6 sys_pselect6 +274 32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +274 64 ppoll sys_ppoll +275 common openat sys_openat compat_sys_openat +276 common mkdirat sys_mkdirat +277 common mknodat sys_mknodat +278 common fchownat sys_fchownat +279 32 futimesat sys_futimesat_time32 +279 64 futimesat sys_futimesat +280 common fstatat64 sys_fstatat64 +281 common unlinkat sys_unlinkat +282 common renameat sys_renameat +283 common linkat sys_linkat +284 common symlinkat sys_symlinkat +285 common readlinkat sys_readlinkat +286 common fchmodat sys_fchmodat +287 common faccessat sys_faccessat +288 common unshare sys_unshare +289 common set_robust_list sys_set_robust_list compat_sys_set_robust_list +290 common get_robust_list sys_get_robust_list compat_sys_get_robust_list +291 common splice sys_splice +292 32 sync_file_range parisc_sync_file_range +292 64 sync_file_range sys_sync_file_range +293 common tee sys_tee +294 common vmsplice sys_vmsplice +295 common move_pages sys_move_pages +296 common getcpu sys_getcpu +297 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait +298 common statfs64 sys_statfs64 compat_sys_statfs64 +299 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +300 common kexec_load sys_kexec_load compat_sys_kexec_load +301 32 utimensat sys_utimensat_time32 +301 64 utimensat sys_utimensat +302 common signalfd sys_signalfd compat_sys_signalfd +# 303 was timerfd +304 common eventfd sys_eventfd +305 32 fallocate parisc_fallocate +305 64 fallocate sys_fallocate +306 common timerfd_create parisc_timerfd_create +307 32 timerfd_settime sys_timerfd_settime32 +307 64 timerfd_settime sys_timerfd_settime +308 32 timerfd_gettime sys_timerfd_gettime32 +308 64 timerfd_gettime sys_timerfd_gettime +309 common signalfd4 parisc_signalfd4 parisc_compat_signalfd4 +310 common eventfd2 parisc_eventfd2 +311 common epoll_create1 sys_epoll_create1 +312 common dup3 sys_dup3 +313 common pipe2 parisc_pipe2 +314 common inotify_init1 parisc_inotify_init1 +315 common preadv sys_preadv compat_sys_preadv +316 common pwritev sys_pwritev compat_sys_pwritev +317 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +318 common perf_event_open sys_perf_event_open +319 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +319 64 recvmmsg sys_recvmmsg +320 common accept4 sys_accept4 +321 common prlimit64 sys_prlimit64 +322 common fanotify_init sys_fanotify_init +323 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark +324 32 clock_adjtime sys_clock_adjtime32 +324 64 clock_adjtime sys_clock_adjtime +325 common name_to_handle_at sys_name_to_handle_at +326 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +327 common syncfs sys_syncfs +328 common setns sys_setns +329 common sendmmsg sys_sendmmsg compat_sys_sendmmsg +330 common process_vm_readv sys_process_vm_readv +331 common process_vm_writev sys_process_vm_writev +332 common kcmp sys_kcmp +333 common finit_module sys_finit_module +334 common sched_setattr sys_sched_setattr +335 common sched_getattr sys_sched_getattr +336 32 utimes sys_utimes_time32 +336 64 utimes sys_utimes +337 common renameat2 sys_renameat2 +338 common seccomp sys_seccomp +339 common getrandom sys_getrandom +340 common memfd_create sys_memfd_create +341 common bpf sys_bpf +342 common execveat sys_execveat compat_sys_execveat +343 common membarrier sys_membarrier +344 common userfaultfd parisc_userfaultfd +345 common mlock2 sys_mlock2 +346 common copy_file_range sys_copy_file_range +347 common preadv2 sys_preadv2 compat_sys_preadv2 +348 common pwritev2 sys_pwritev2 compat_sys_pwritev2 +349 common statx sys_statx +350 32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +350 64 io_pgetevents sys_io_pgetevents +351 common pkey_mprotect sys_pkey_mprotect +352 common pkey_alloc sys_pkey_alloc +353 common pkey_free sys_pkey_free +354 common rseq sys_rseq +355 common kexec_file_load sys_kexec_file_load sys_kexec_file_load +356 common cacheflush sys_cacheflush +# up to 402 is unassigned and reserved for arch specific syscalls +403 32 clock_gettime64 sys_clock_gettime sys_clock_gettime +404 32 clock_settime64 sys_clock_settime sys_clock_settime +405 32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime +406 32 clock_getres_time64 sys_clock_getres sys_clock_getres +407 32 clock_nanosleep_time64 sys_clock_nanosleep sys_clock_nanosleep +408 32 timer_gettime64 sys_timer_gettime sys_timer_gettime +409 32 timer_settime64 sys_timer_settime sys_timer_settime +410 32 timerfd_gettime64 sys_timerfd_gettime sys_timerfd_gettime +411 32 timerfd_settime64 sys_timerfd_settime sys_timerfd_settime +412 32 utimensat_time64 sys_utimensat sys_utimensat +413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 +417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend +419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive +420 32 semtimedop_time64 sys_semtimedop sys_semtimedop +421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 sys_futex sys_futex +423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3_wrapper +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/tools/perf/arch/parisc/include/syscall_table.h b/tools/perf/arch/parisc/include/syscall_table.h new file mode 100644 index 000000000000..7ff51b783000 --- /dev/null +++ b/tools/perf/arch/parisc/include/syscall_table.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 64 +#include <asm/syscalls_64.h> +#else +#include <asm/syscalls_32.h> +#endif diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index dc8f4fb8e324..a295a80ea078 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -1,28 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_JITDUMP := 1 - -# -# Syscall table generation for perf -# - -out := $(OUTPUT)arch/powerpc/include/generated/asm -header32 := $(out)/syscalls_32.c -header64 := $(out)/syscalls_64.c -sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls -sysdef := $(sysprf)/syscall.tbl -systbl := $(sysprf)/mksyscalltbl - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header64): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '64' $(sysdef) > $@ - -$(header32): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '32' $(sysdef) > $@ - -clean:: - $(call QUIET_CLEAN, powerpc) $(RM) $(header32) $(header64) - -archheaders: $(header32) $(header64) diff --git a/tools/perf/arch/powerpc/entry/syscalls/Kbuild b/tools/perf/arch/powerpc/entry/syscalls/Kbuild new file mode 100644 index 000000000000..84c6599b4ea6 --- /dev/null +++ b/tools/perf/arch/powerpc/entry/syscalls/Kbuild @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/powerpc/entry/syscalls/Makefile.syscalls b/tools/perf/arch/powerpc/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..e35afbc57c79 --- /dev/null +++ b/tools/perf/arch/powerpc/entry/syscalls/Makefile.syscalls @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += nospu +syscall_abis_64 += nospu + +syscalltbl = $(srctree)/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl deleted file mode 100755 index 0eb316fe6dd1..000000000000 --- a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,39 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate system call table for perf. Derived from -# s390 script. -# -# Copyright IBM Corp. 2017 -# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> -# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> - -wordsize=$1 -SYSCALL_TBL=$2 - -if ! test -r $SYSCALL_TBL; then - echo "Could not read input file" >&2 - exit 1 -fi - -create_table() -{ - local wordsize=$1 - local max_nr nr abi sc discard - max_nr=-1 - nr=0 - - echo "static const char *const syscalltbl_powerpc_${wordsize}[] = {" - while read nr abi sc discard; do - if [ "$max_nr" -lt "$nr" ]; then - printf '\t[%d] = "%s",\n' $nr $sc - max_nr=$nr - fi - done - echo '};' - echo "#define SYSCALLTBL_POWERPC_${wordsize}_MAX_ID $max_nr" -} - -grep -E "^[[:digit:]]+[[:space:]]+(common|spu|nospu|${wordsize})" $SYSCALL_TBL \ - |sort -k1 -n \ - |create_table ${wordsize} diff --git a/tools/perf/arch/powerpc/include/syscall_table.h b/tools/perf/arch/powerpc/include/syscall_table.h new file mode 100644 index 000000000000..7ff51b783000 --- /dev/null +++ b/tools/perf/arch/powerpc/include/syscall_table.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 64 +#include <asm/syscalls_64.h> +#else +#include <asm/syscalls_32.h> +#endif diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index c7df534dbf8f..0be74f048f96 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -14,8 +14,8 @@ static bool is_compat_mode(void) { - u64 base_platform = getauxval(AT_BASE_PLATFORM); - u64 platform = getauxval(AT_PLATFORM); + unsigned long base_platform = getauxval(AT_BASE_PLATFORM); + unsigned long platform = getauxval(AT_PLATFORM); if (!strcmp((char *)platform, (char *)base_platform)) return false; diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index e8e6e6fc6f17..bd36cfd420a2 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -16,6 +16,7 @@ #define PVR_POWER9 0x004E #define PVR_POWER10 0x0080 +#define PVR_POWER11 0x0082 static const struct sample_reg sample_reg_masks[] = { SMPL_REG(r0, PERF_REG_POWERPC_R0), @@ -207,7 +208,7 @@ uint64_t arch__intr_reg_mask(void) version = (((mfspr(SPRN_PVR)) >> 16) & 0xFFFF); if (version == PVR_POWER9) extended_mask = PERF_REG_PMU_MASK_300; - else if (version == PVR_POWER10) + else if ((version == PVR_POWER10) || (version == PVR_POWER11)) extended_mask = PERF_REG_PMU_MASK_31; else return mask; diff --git a/tools/perf/arch/riscv/Makefile b/tools/perf/arch/riscv/Makefile index 18ad078000e2..087e099fb453 100644 --- a/tools/perf/arch/riscv/Makefile +++ b/tools/perf/arch/riscv/Makefile @@ -1,25 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 PERF_HAVE_JITDUMP := 1 HAVE_KVM_STAT_SUPPORT := 1 - -# -# Syscall table generation for perf -# - -out := $(OUTPUT)arch/riscv/include/generated/asm -header := $(out)/syscalls.c -incpath := $(srctree)/tools -sysdef := $(srctree)/tools/arch/riscv/include/uapi/asm/unistd.h -sysprf := $(srctree)/tools/perf/arch/riscv/entry/syscalls/ -systbl := $(sysprf)/mksyscalltbl - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ - -clean:: - $(call QUIET_CLEAN, riscv) $(RM) $(header) - -archheaders: $(header) diff --git a/tools/perf/arch/riscv/entry/syscalls/Kbuild b/tools/perf/arch/riscv/entry/syscalls/Kbuild new file mode 100644 index 000000000000..9a41e3572c3a --- /dev/null +++ b/tools/perf/arch/riscv/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/riscv/entry/syscalls/Makefile.syscalls b/tools/perf/arch/riscv/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..9668fd1faf60 --- /dev/null +++ b/tools/perf/arch/riscv/entry/syscalls/Makefile.syscalls @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += riscv memfd_secret +syscall_abis_64 += riscv rlimit memfd_secret diff --git a/tools/perf/arch/riscv/entry/syscalls/mksyscalltbl b/tools/perf/arch/riscv/entry/syscalls/mksyscalltbl deleted file mode 100755 index c59f5e852b97..000000000000 --- a/tools/perf/arch/riscv/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,47 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate system call table for perf. Derived from -# powerpc script. -# -# Copyright IBM Corp. 2017 -# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> -# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> -# Changed by: Kim Phillips <kim.phillips@arm.com> -# Changed by: Björn Töpel <bjorn@rivosinc.com> - -gcc=$1 -hostcc=$2 -incpath=$3 -input=$4 - -if ! test -r $input; then - echo "Could not read input file" >&2 - exit 1 -fi - -create_sc_table() -{ - local sc nr max_nr - - while read sc nr; do - printf "%s\n" " [$nr] = \"$sc\"," - max_nr=$nr - done - - echo "#define SYSCALLTBL_RISCV_MAX_ID $max_nr" -} - -create_table() -{ - echo "#include \"$input\"" - echo "static const char *const syscalltbl_riscv[] = {" - create_sc_table - echo "};" -} - -$gcc -E -dM -x c -I $incpath/include/uapi $input \ - |awk '$2 ~ "__NR" && $3 !~ "__NR3264_" { - sub("^#define __NR(3264)?_", ""); - print | "sort -k2 -n"}' \ - |create_table diff --git a/tools/perf/arch/riscv/include/syscall_table.h b/tools/perf/arch/riscv/include/syscall_table.h new file mode 100644 index 000000000000..7ff51b783000 --- /dev/null +++ b/tools/perf/arch/riscv/include/syscall_table.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 64 +#include <asm/syscalls_64.h> +#else +#include <asm/syscalls_32.h> +#endif diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index c431c21b11ef..0033698a65ce 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -1,24 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_JITDUMP := 1 - -# -# Syscall table generation for perf -# - -out := $(OUTPUT)arch/s390/include/generated/asm -header := $(out)/syscalls_64.c -sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls -sysdef := $(sysprf)/syscall.tbl -systbl := $(sysprf)/mksyscalltbl - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@ - -clean:: - $(call QUIET_CLEAN, s390) $(RM) $(header) - -archheaders: $(header) diff --git a/tools/perf/arch/s390/entry/syscalls/Kbuild b/tools/perf/arch/s390/entry/syscalls/Kbuild new file mode 100644 index 000000000000..9a41e3572c3a --- /dev/null +++ b/tools/perf/arch/s390/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/s390/entry/syscalls/Makefile.syscalls b/tools/perf/arch/s390/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..9762d7abf17c --- /dev/null +++ b/tools/perf/arch/s390/entry/syscalls/Makefile.syscalls @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_64 += renameat rlimit memfd_secret + +syscalltbl = $(srctree)/tools/perf/arch/s390/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl deleted file mode 100755 index 52eb88a77c94..000000000000 --- a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,32 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# -# Generate system call table for perf -# -# Copyright IBM Corp. 2017, 2018 -# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> -# - -SYSCALL_TBL=$1 - -if ! test -r $SYSCALL_TBL; then - echo "Could not read input file" >&2 - exit 1 -fi - -create_table() -{ - local max_nr nr abi sc discard - - echo 'static const char *const syscalltbl_s390_64[] = {' - while read nr abi sc discard; do - printf '\t[%d] = "%s",\n' $nr $sc - max_nr=$nr - done - echo '};' - echo "#define SYSCALLTBL_S390_64_MAX_ID $max_nr" -} - -grep -E "^[[:digit:]]+[[:space:]]+(common|64)" $SYSCALL_TBL \ - |sort -k1 -n \ - |create_table diff --git a/tools/perf/arch/s390/include/syscall_table.h b/tools/perf/arch/s390/include/syscall_table.h new file mode 100644 index 000000000000..b53e31c15805 --- /dev/null +++ b/tools/perf/arch/s390/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_64.h> diff --git a/tools/perf/arch/sh/entry/syscalls/Kbuild b/tools/perf/arch/sh/entry/syscalls/Kbuild new file mode 100644 index 000000000000..11707c481a24 --- /dev/null +++ b/tools/perf/arch/sh/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h diff --git a/tools/perf/arch/sh/entry/syscalls/Makefile.syscalls b/tools/perf/arch/sh/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..25080390e4ed --- /dev/null +++ b/tools/perf/arch/sh/entry/syscalls/Makefile.syscalls @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += +syscalltbl = $(srctree)/tools/perf/arch/sh/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..c8cad33bf250 --- /dev/null +++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl @@ -0,0 +1,472 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# system call numbers and entry vectors for sh +# +# The format is: +# <number> <abi> <name> <entry point> +# +# The <abi> is always "common" for this file +# +0 common restart_syscall sys_restart_syscall +1 common exit sys_exit +2 common fork sys_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open +6 common close sys_close +7 common waitpid sys_waitpid +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 common execve sys_execve +12 common chdir sys_chdir +13 common time sys_time32 +14 common mknod sys_mknod +15 common chmod sys_chmod +16 common lchown sys_lchown16 +# 17 was break +18 common oldstat sys_stat +19 common lseek sys_lseek +20 common getpid sys_getpid +21 common mount sys_mount +22 common umount sys_oldumount +23 common setuid sys_setuid16 +24 common getuid sys_getuid16 +25 common stime sys_stime32 +26 common ptrace sys_ptrace +27 common alarm sys_alarm +28 common oldfstat sys_fstat +29 common pause sys_pause +30 common utime sys_utime32 +# 31 was stty +# 32 was gtty +33 common access sys_access +34 common nice sys_nice +# 35 was ftime +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_sh_pipe +43 common times sys_times +# 44 was prof +45 common brk sys_brk +46 common setgid sys_setgid16 +47 common getgid sys_getgid16 +48 common signal sys_signal +49 common geteuid sys_geteuid16 +50 common getegid sys_getegid16 +51 common acct sys_acct +52 common umount2 sys_umount +# 53 was lock +54 common ioctl sys_ioctl +55 common fcntl sys_fcntl +# 56 was mpx +57 common setpgid sys_setpgid +# 58 was ulimit +# 59 was olduname +60 common umask sys_umask +61 common chroot sys_chroot +62 common ustat sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 common sigaction sys_sigaction +68 common sgetmask sys_sgetmask +69 common ssetmask sys_ssetmask +70 common setreuid sys_setreuid16 +71 common setregid sys_setregid16 +72 common sigsuspend sys_sigsuspend +73 common sigpending sys_sigpending +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit +76 common getrlimit sys_old_getrlimit +77 common getrusage sys_getrusage +78 common gettimeofday sys_gettimeofday +79 common settimeofday sys_settimeofday +80 common getgroups sys_getgroups16 +81 common setgroups sys_setgroups16 +# 82 was select +83 common symlink sys_symlink +84 common oldlstat sys_lstat +85 common readlink sys_readlink +86 common uselib sys_uselib +87 common swapon sys_swapon +88 common reboot sys_reboot +89 common readdir sys_old_readdir +90 common mmap old_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate +93 common ftruncate sys_ftruncate +94 common fchmod sys_fchmod +95 common fchown sys_fchown16 +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +# 98 was profil +99 common statfs sys_statfs +100 common fstatfs sys_fstatfs +# 101 was ioperm +102 common socketcall sys_socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer +105 common getitimer sys_getitimer +106 common stat sys_newstat +107 common lstat sys_newlstat +108 common fstat sys_newfstat +109 common olduname sys_uname +# 110 was iopl +111 common vhangup sys_vhangup +# 112 was idle +# 113 was vm86old +114 common wait4 sys_wait4 +115 common swapoff sys_swapoff +116 common sysinfo sys_sysinfo +117 common ipc sys_ipc +118 common fsync sys_fsync +119 common sigreturn sys_sigreturn +120 common clone sys_clone +121 common setdomainname sys_setdomainname +122 common uname sys_newuname +123 common cacheflush sys_cacheflush +124 common adjtimex sys_adjtimex_time32 +125 common mprotect sys_mprotect +126 common sigprocmask sys_sigprocmask +# 127 was create_module +128 common init_module sys_init_module +129 common delete_module sys_delete_module +# 130 was get_kernel_syms +131 common quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_ni_syscall +135 common sysfs sys_sysfs +136 common personality sys_personality +# 137 was afs_syscall +138 common setfsuid sys_setfsuid16 +139 common setfsgid sys_setfsgid16 +140 common _llseek sys_llseek +141 common getdents sys_getdents +142 common _newselect sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv +146 common writev sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 common _sysctl sys_ni_syscall +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 common sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep_time32 +163 common mremap sys_mremap +164 common setresuid sys_setresuid16 +165 common getresuid sys_getresuid16 +# 166 was vm86 +# 167 was query_module +168 common poll sys_poll +169 common nfsservctl sys_ni_syscall +170 common setresgid sys_setresgid16 +171 common getresgid sys_getresgid16 +172 common prctl sys_prctl +173 common rt_sigreturn sys_rt_sigreturn +174 common rt_sigaction sys_rt_sigaction +175 common rt_sigprocmask sys_rt_sigprocmask +176 common rt_sigpending sys_rt_sigpending +177 common rt_sigtimedwait sys_rt_sigtimedwait_time32 +178 common rt_sigqueueinfo sys_rt_sigqueueinfo +179 common rt_sigsuspend sys_rt_sigsuspend +180 common pread64 sys_pread_wrapper +181 common pwrite64 sys_pwrite_wrapper +182 common chown sys_chown16 +183 common getcwd sys_getcwd +184 common capget sys_capget +185 common capset sys_capset +186 common sigaltstack sys_sigaltstack +187 common sendfile sys_sendfile +# 188 is reserved for getpmsg +# 189 is reserved for putpmsg +190 common vfork sys_vfork +191 common ugetrlimit sys_getrlimit +192 common mmap2 sys_mmap2 +193 common truncate64 sys_truncate64 +194 common ftruncate64 sys_ftruncate64 +195 common stat64 sys_stat64 +196 common lstat64 sys_lstat64 +197 common fstat64 sys_fstat64 +198 common lchown32 sys_lchown +199 common getuid32 sys_getuid +200 common getgid32 sys_getgid +201 common geteuid32 sys_geteuid +202 common getegid32 sys_getegid +203 common setreuid32 sys_setreuid +204 common setregid32 sys_setregid +205 common getgroups32 sys_getgroups +206 common setgroups32 sys_setgroups +207 common fchown32 sys_fchown +208 common setresuid32 sys_setresuid +209 common getresuid32 sys_getresuid +210 common setresgid32 sys_setresgid +211 common getresgid32 sys_getresgid +212 common chown32 sys_chown +213 common setuid32 sys_setuid +214 common setgid32 sys_setgid +215 common setfsuid32 sys_setfsuid +216 common setfsgid32 sys_setfsgid +217 common pivot_root sys_pivot_root +218 common mincore sys_mincore +219 common madvise sys_madvise +220 common getdents64 sys_getdents64 +221 common fcntl64 sys_fcntl64 +# 222 is reserved for tux +# 223 is unused +224 common gettid sys_gettid +225 common readahead sys_readahead +226 common setxattr sys_setxattr +227 common lsetxattr sys_lsetxattr +228 common fsetxattr sys_fsetxattr +229 common getxattr sys_getxattr +230 common lgetxattr sys_lgetxattr +231 common fgetxattr sys_fgetxattr +232 common listxattr sys_listxattr +233 common llistxattr sys_llistxattr +234 common flistxattr sys_flistxattr +235 common removexattr sys_removexattr +236 common lremovexattr sys_lremovexattr +237 common fremovexattr sys_fremovexattr +238 common tkill sys_tkill +239 common sendfile64 sys_sendfile64 +240 common futex sys_futex_time32 +241 common sched_setaffinity sys_sched_setaffinity +242 common sched_getaffinity sys_sched_getaffinity +# 243 is reserved for set_thread_area +# 244 is reserved for get_thread_area +245 common io_setup sys_io_setup +246 common io_destroy sys_io_destroy +247 common io_getevents sys_io_getevents_time32 +248 common io_submit sys_io_submit +249 common io_cancel sys_io_cancel +250 common fadvise64 sys_fadvise64 +# 251 is unused +252 common exit_group sys_exit_group +253 common lookup_dcookie sys_ni_syscall +254 common epoll_create sys_epoll_create +255 common epoll_ctl sys_epoll_ctl +256 common epoll_wait sys_epoll_wait +257 common remap_file_pages sys_remap_file_pages +258 common set_tid_address sys_set_tid_address +259 common timer_create sys_timer_create +260 common timer_settime sys_timer_settime32 +261 common timer_gettime sys_timer_gettime32 +262 common timer_getoverrun sys_timer_getoverrun +263 common timer_delete sys_timer_delete +264 common clock_settime sys_clock_settime32 +265 common clock_gettime sys_clock_gettime32 +266 common clock_getres sys_clock_getres_time32 +267 common clock_nanosleep sys_clock_nanosleep_time32 +268 common statfs64 sys_statfs64 +269 common fstatfs64 sys_fstatfs64 +270 common tgkill sys_tgkill +271 common utimes sys_utimes_time32 +272 common fadvise64_64 sys_fadvise64_64_wrapper +# 273 is reserved for vserver +274 common mbind sys_mbind +275 common get_mempolicy sys_get_mempolicy +276 common set_mempolicy sys_set_mempolicy +277 common mq_open sys_mq_open +278 common mq_unlink sys_mq_unlink +279 common mq_timedsend sys_mq_timedsend_time32 +280 common mq_timedreceive sys_mq_timedreceive_time32 +281 common mq_notify sys_mq_notify +282 common mq_getsetattr sys_mq_getsetattr +283 common kexec_load sys_kexec_load +284 common waitid sys_waitid +285 common add_key sys_add_key +286 common request_key sys_request_key +287 common keyctl sys_keyctl +288 common ioprio_set sys_ioprio_set +289 common ioprio_get sys_ioprio_get +290 common inotify_init sys_inotify_init +291 common inotify_add_watch sys_inotify_add_watch +292 common inotify_rm_watch sys_inotify_rm_watch +# 293 is unused +294 common migrate_pages sys_migrate_pages +295 common openat sys_openat +296 common mkdirat sys_mkdirat +297 common mknodat sys_mknodat +298 common fchownat sys_fchownat +299 common futimesat sys_futimesat_time32 +300 common fstatat64 sys_fstatat64 +301 common unlinkat sys_unlinkat +302 common renameat sys_renameat +303 common linkat sys_linkat +304 common symlinkat sys_symlinkat +305 common readlinkat sys_readlinkat +306 common fchmodat sys_fchmodat +307 common faccessat sys_faccessat +308 common pselect6 sys_pselect6_time32 +309 common ppoll sys_ppoll_time32 +310 common unshare sys_unshare +311 common set_robust_list sys_set_robust_list +312 common get_robust_list sys_get_robust_list +313 common splice sys_splice +314 common sync_file_range sys_sh_sync_file_range6 +315 common tee sys_tee +316 common vmsplice sys_vmsplice +317 common move_pages sys_move_pages +318 common getcpu sys_getcpu +319 common epoll_pwait sys_epoll_pwait +320 common utimensat sys_utimensat_time32 +321 common signalfd sys_signalfd +322 common timerfd_create sys_timerfd_create +323 common eventfd sys_eventfd +324 common fallocate sys_fallocate +325 common timerfd_settime sys_timerfd_settime32 +326 common timerfd_gettime sys_timerfd_gettime32 +327 common signalfd4 sys_signalfd4 +328 common eventfd2 sys_eventfd2 +329 common epoll_create1 sys_epoll_create1 +330 common dup3 sys_dup3 +331 common pipe2 sys_pipe2 +332 common inotify_init1 sys_inotify_init1 +333 common preadv sys_preadv +334 common pwritev sys_pwritev +335 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +336 common perf_event_open sys_perf_event_open +337 common fanotify_init sys_fanotify_init +338 common fanotify_mark sys_fanotify_mark +339 common prlimit64 sys_prlimit64 +340 common socket sys_socket +341 common bind sys_bind +342 common connect sys_connect +343 common listen sys_listen +344 common accept sys_accept +345 common getsockname sys_getsockname +346 common getpeername sys_getpeername +347 common socketpair sys_socketpair +348 common send sys_send +349 common sendto sys_sendto +350 common recv sys_recv +351 common recvfrom sys_recvfrom +352 common shutdown sys_shutdown +353 common setsockopt sys_setsockopt +354 common getsockopt sys_getsockopt +355 common sendmsg sys_sendmsg +356 common recvmsg sys_recvmsg +357 common recvmmsg sys_recvmmsg_time32 +358 common accept4 sys_accept4 +359 common name_to_handle_at sys_name_to_handle_at +360 common open_by_handle_at sys_open_by_handle_at +361 common clock_adjtime sys_clock_adjtime32 +362 common syncfs sys_syncfs +363 common sendmmsg sys_sendmmsg +364 common setns sys_setns +365 common process_vm_readv sys_process_vm_readv +366 common process_vm_writev sys_process_vm_writev +367 common kcmp sys_kcmp +368 common finit_module sys_finit_module +369 common sched_getattr sys_sched_getattr +370 common sched_setattr sys_sched_setattr +371 common renameat2 sys_renameat2 +372 common seccomp sys_seccomp +373 common getrandom sys_getrandom +374 common memfd_create sys_memfd_create +375 common bpf sys_bpf +376 common execveat sys_execveat +377 common userfaultfd sys_userfaultfd +378 common membarrier sys_membarrier +379 common mlock2 sys_mlock2 +380 common copy_file_range sys_copy_file_range +381 common preadv2 sys_preadv2 +382 common pwritev2 sys_pwritev2 +383 common statx sys_statx +384 common pkey_mprotect sys_pkey_mprotect +385 common pkey_alloc sys_pkey_alloc +386 common pkey_free sys_pkey_free +387 common rseq sys_rseq +388 common sync_file_range2 sys_sync_file_range2 +# room for arch specific syscalls +393 common semget sys_semget +394 common semctl sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl +397 common shmat sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd +401 common msgrcv sys_msgrcv +402 common msgctl sys_msgctl +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 +414 common ppoll_time64 sys_ppoll +416 common io_pgetevents_time64 sys_io_pgetevents +417 common recvmmsg_time64 sys_recvmmsg +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +# 435 reserved for clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat diff --git a/tools/perf/arch/sh/include/syscall_table.h b/tools/perf/arch/sh/include/syscall_table.h new file mode 100644 index 000000000000..4c942821662d --- /dev/null +++ b/tools/perf/arch/sh/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_32.h> diff --git a/tools/perf/arch/sparc/entry/syscalls/Kbuild b/tools/perf/arch/sparc/entry/syscalls/Kbuild new file mode 100644 index 000000000000..84c6599b4ea6 --- /dev/null +++ b/tools/perf/arch/sparc/entry/syscalls/Kbuild @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/sparc/entry/syscalls/Makefile.syscalls b/tools/perf/arch/sparc/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..212c1800b644 --- /dev/null +++ b/tools/perf/arch/sparc/entry/syscalls/Makefile.syscalls @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += +syscall_abis_64 += +syscalltbl = $(srctree)/tools/perf/arch/sparc/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..727f99d333b3 --- /dev/null +++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl @@ -0,0 +1,514 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# system call numbers and entry vectors for sparc +# +# The format is: +# <number> <abi> <name> <entry point> <compat entry point> +# +# The <abi> can be common, 64, or 32 for this file. +# +0 common restart_syscall sys_restart_syscall +1 32 exit sys_exit sparc_exit +1 64 exit sparc_exit +2 common fork sys_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open compat_sys_open +6 common close sys_close +7 common wait4 sys_wait4 compat_sys_wait4 +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 32 execv sunos_execv +11 64 execv sys_nis_syscall +12 common chdir sys_chdir +13 32 chown sys_chown16 +13 64 chown sys_chown +14 common mknod sys_mknod +15 common chmod sys_chmod +16 32 lchown sys_lchown16 +16 64 lchown sys_lchown +17 common brk sys_brk +18 common perfctr sys_nis_syscall +19 common lseek sys_lseek compat_sys_lseek +20 common getpid sys_getpid +21 common capget sys_capget +22 common capset sys_capset +23 32 setuid sys_setuid16 +23 64 setuid sys_setuid +24 32 getuid sys_getuid16 +24 64 getuid sys_getuid +25 common vmsplice sys_vmsplice +26 common ptrace sys_ptrace compat_sys_ptrace +27 common alarm sys_alarm +28 common sigaltstack sys_sigaltstack compat_sys_sigaltstack +29 32 pause sys_pause +29 64 pause sys_nis_syscall +30 32 utime sys_utime32 +30 64 utime sys_utime +31 32 lchown32 sys_lchown +32 32 fchown32 sys_fchown +33 common access sys_access +34 common nice sys_nice +35 32 chown32 sys_chown +36 common sync sys_sync +37 common kill sys_kill +38 common stat sys_newstat compat_sys_newstat +39 32 sendfile sys_sendfile compat_sys_sendfile +39 64 sendfile sys_sendfile64 +40 common lstat sys_newlstat compat_sys_newlstat +41 common dup sys_dup +42 common pipe sys_sparc_pipe +43 common times sys_times compat_sys_times +44 32 getuid32 sys_getuid +45 common umount2 sys_umount +46 32 setgid sys_setgid16 +46 64 setgid sys_setgid +47 32 getgid sys_getgid16 +47 64 getgid sys_getgid +48 common signal sys_signal +49 32 geteuid sys_geteuid16 +49 64 geteuid sys_geteuid +50 32 getegid sys_getegid16 +50 64 getegid sys_getegid +51 common acct sys_acct +52 64 memory_ordering sys_memory_ordering +53 32 getgid32 sys_getgid +54 common ioctl sys_ioctl compat_sys_ioctl +55 common reboot sys_reboot +56 32 mmap2 sys_mmap2 sys32_mmap2 +57 common symlink sys_symlink +58 common readlink sys_readlink +59 32 execve sys_execve sys32_execve +59 64 execve sys64_execve +60 common umask sys_umask +61 common chroot sys_chroot +62 common fstat sys_newfstat compat_sys_newfstat +63 common fstat64 sys_fstat64 compat_sys_fstat64 +64 common getpagesize sys_getpagesize +65 common msync sys_msync +66 common vfork sys_vfork +67 common pread64 sys_pread64 compat_sys_pread64 +68 common pwrite64 sys_pwrite64 compat_sys_pwrite64 +69 32 geteuid32 sys_geteuid +70 32 getegid32 sys_getegid +71 common mmap sys_mmap +72 32 setreuid32 sys_setreuid +73 32 munmap sys_munmap +73 64 munmap sys_64_munmap +74 common mprotect sys_mprotect +75 common madvise sys_madvise +76 common vhangup sys_vhangup +77 32 truncate64 sys_truncate64 compat_sys_truncate64 +78 common mincore sys_mincore +79 32 getgroups sys_getgroups16 +79 64 getgroups sys_getgroups +80 32 setgroups sys_setgroups16 +80 64 setgroups sys_setgroups +81 common getpgrp sys_getpgrp +82 32 setgroups32 sys_setgroups +83 common setitimer sys_setitimer compat_sys_setitimer +84 32 ftruncate64 sys_ftruncate64 compat_sys_ftruncate64 +85 common swapon sys_swapon +86 common getitimer sys_getitimer compat_sys_getitimer +87 32 setuid32 sys_setuid +88 common sethostname sys_sethostname +89 32 setgid32 sys_setgid +90 common dup2 sys_dup2 +91 32 setfsuid32 sys_setfsuid +92 common fcntl sys_fcntl compat_sys_fcntl +93 common select sys_select compat_sys_select +94 32 setfsgid32 sys_setfsgid +95 common fsync sys_fsync +96 common setpriority sys_setpriority +97 common socket sys_socket +98 common connect sys_connect +99 common accept sys_accept +100 common getpriority sys_getpriority +101 common rt_sigreturn sys_rt_sigreturn sys32_rt_sigreturn +102 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +103 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +104 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +105 32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +105 64 rt_sigtimedwait sys_rt_sigtimedwait +106 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +107 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +108 32 setresuid32 sys_setresuid +108 64 setresuid sys_setresuid +109 32 getresuid32 sys_getresuid +109 64 getresuid sys_getresuid +110 32 setresgid32 sys_setresgid +110 64 setresgid sys_setresgid +111 32 getresgid32 sys_getresgid +111 64 getresgid sys_getresgid +112 32 setregid32 sys_setregid +113 common recvmsg sys_recvmsg compat_sys_recvmsg +114 common sendmsg sys_sendmsg compat_sys_sendmsg +115 32 getgroups32 sys_getgroups +116 common gettimeofday sys_gettimeofday compat_sys_gettimeofday +117 common getrusage sys_getrusage compat_sys_getrusage +118 common getsockopt sys_getsockopt sys_getsockopt +119 common getcwd sys_getcwd +120 common readv sys_readv +121 common writev sys_writev +122 common settimeofday sys_settimeofday compat_sys_settimeofday +123 32 fchown sys_fchown16 +123 64 fchown sys_fchown +124 common fchmod sys_fchmod +125 common recvfrom sys_recvfrom compat_sys_recvfrom +126 32 setreuid sys_setreuid16 +126 64 setreuid sys_setreuid +127 32 setregid sys_setregid16 +127 64 setregid sys_setregid +128 common rename sys_rename +129 common truncate sys_truncate compat_sys_truncate +130 common ftruncate sys_ftruncate compat_sys_ftruncate +131 common flock sys_flock +132 common lstat64 sys_lstat64 compat_sys_lstat64 +133 common sendto sys_sendto +134 common shutdown sys_shutdown +135 common socketpair sys_socketpair +136 common mkdir sys_mkdir +137 common rmdir sys_rmdir +138 32 utimes sys_utimes_time32 +138 64 utimes sys_utimes +139 common stat64 sys_stat64 compat_sys_stat64 +140 common sendfile64 sys_sendfile64 +141 common getpeername sys_getpeername +142 32 futex sys_futex_time32 +142 64 futex sys_futex +143 common gettid sys_gettid +144 common getrlimit sys_getrlimit compat_sys_getrlimit +145 common setrlimit sys_setrlimit compat_sys_setrlimit +146 common pivot_root sys_pivot_root +147 common prctl sys_prctl +148 common pciconfig_read sys_pciconfig_read +149 common pciconfig_write sys_pciconfig_write +150 common getsockname sys_getsockname +151 common inotify_init sys_inotify_init +152 common inotify_add_watch sys_inotify_add_watch +153 common poll sys_poll +154 common getdents64 sys_getdents64 +155 32 fcntl64 sys_fcntl64 compat_sys_fcntl64 +156 common inotify_rm_watch sys_inotify_rm_watch +157 common statfs sys_statfs compat_sys_statfs +158 common fstatfs sys_fstatfs compat_sys_fstatfs +159 common umount sys_oldumount +160 common sched_set_affinity sys_sched_setaffinity compat_sys_sched_setaffinity +161 common sched_get_affinity sys_sched_getaffinity compat_sys_sched_getaffinity +162 common getdomainname sys_getdomainname +163 common setdomainname sys_setdomainname +164 64 utrap_install sys_utrap_install +165 common quotactl sys_quotactl +166 common set_tid_address sys_set_tid_address +167 common mount sys_mount +168 common ustat sys_ustat compat_sys_ustat +169 common setxattr sys_setxattr +170 common lsetxattr sys_lsetxattr +171 common fsetxattr sys_fsetxattr +172 common getxattr sys_getxattr +173 common lgetxattr sys_lgetxattr +174 common getdents sys_getdents compat_sys_getdents +175 common setsid sys_setsid +176 common fchdir sys_fchdir +177 common fgetxattr sys_fgetxattr +178 common listxattr sys_listxattr +179 common llistxattr sys_llistxattr +180 common flistxattr sys_flistxattr +181 common removexattr sys_removexattr +182 common lremovexattr sys_lremovexattr +183 32 sigpending sys_sigpending compat_sys_sigpending +183 64 sigpending sys_nis_syscall +184 common query_module sys_ni_syscall +185 common setpgid sys_setpgid +186 common fremovexattr sys_fremovexattr +187 common tkill sys_tkill +188 32 exit_group sys_exit_group sparc_exit_group +188 64 exit_group sparc_exit_group +189 common uname sys_newuname +190 common init_module sys_init_module +191 32 personality sys_personality sys_sparc64_personality +191 64 personality sys_sparc64_personality +192 32 remap_file_pages sys_sparc_remap_file_pages sys_remap_file_pages +192 64 remap_file_pages sys_remap_file_pages +193 common epoll_create sys_epoll_create +194 common epoll_ctl sys_epoll_ctl +195 common epoll_wait sys_epoll_wait +196 common ioprio_set sys_ioprio_set +197 common getppid sys_getppid +198 32 sigaction sys_sparc_sigaction compat_sys_sparc_sigaction +198 64 sigaction sys_nis_syscall +199 common sgetmask sys_sgetmask +200 common ssetmask sys_ssetmask +201 32 sigsuspend sys_sigsuspend +201 64 sigsuspend sys_nis_syscall +202 common oldlstat sys_newlstat compat_sys_newlstat +203 common uselib sys_uselib +204 32 readdir sys_old_readdir compat_sys_old_readdir +204 64 readdir sys_nis_syscall +205 common readahead sys_readahead compat_sys_readahead +206 common socketcall sys_socketcall compat_sys_socketcall +207 common syslog sys_syslog +208 common lookup_dcookie sys_ni_syscall +209 common fadvise64 sys_fadvise64 compat_sys_fadvise64 +210 common fadvise64_64 sys_fadvise64_64 compat_sys_fadvise64_64 +211 common tgkill sys_tgkill +212 common waitpid sys_waitpid +213 common swapoff sys_swapoff +214 common sysinfo sys_sysinfo compat_sys_sysinfo +215 32 ipc sys_ipc compat_sys_ipc +215 64 ipc sys_sparc_ipc +216 32 sigreturn sys_sigreturn sys32_sigreturn +216 64 sigreturn sys_nis_syscall +217 common clone sys_clone +218 common ioprio_get sys_ioprio_get +219 32 adjtimex sys_adjtimex_time32 +219 64 adjtimex sys_sparc_adjtimex +220 32 sigprocmask sys_sigprocmask compat_sys_sigprocmask +220 64 sigprocmask sys_nis_syscall +221 common create_module sys_ni_syscall +222 common delete_module sys_delete_module +223 common get_kernel_syms sys_ni_syscall +224 common getpgid sys_getpgid +225 common bdflush sys_ni_syscall +226 common sysfs sys_sysfs +227 common afs_syscall sys_nis_syscall +228 common setfsuid sys_setfsuid16 +229 common setfsgid sys_setfsgid16 +230 common _newselect sys_select compat_sys_select +231 32 time sys_time32 +232 common splice sys_splice +233 32 stime sys_stime32 +233 64 stime sys_stime +234 common statfs64 sys_statfs64 compat_sys_statfs64 +235 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +236 common _llseek sys_llseek +237 common mlock sys_mlock +238 common munlock sys_munlock +239 common mlockall sys_mlockall +240 common munlockall sys_munlockall +241 common sched_setparam sys_sched_setparam +242 common sched_getparam sys_sched_getparam +243 common sched_setscheduler sys_sched_setscheduler +244 common sched_getscheduler sys_sched_getscheduler +245 common sched_yield sys_sched_yield +246 common sched_get_priority_max sys_sched_get_priority_max +247 common sched_get_priority_min sys_sched_get_priority_min +248 32 sched_rr_get_interval sys_sched_rr_get_interval_time32 +248 64 sched_rr_get_interval sys_sched_rr_get_interval +249 32 nanosleep sys_nanosleep_time32 +249 64 nanosleep sys_nanosleep +250 32 mremap sys_mremap +250 64 mremap sys_64_mremap +251 common _sysctl sys_ni_syscall +252 common getsid sys_getsid +253 common fdatasync sys_fdatasync +254 32 nfsservctl sys_ni_syscall sys_nis_syscall +254 64 nfsservctl sys_nis_syscall +255 common sync_file_range sys_sync_file_range compat_sys_sync_file_range +256 32 clock_settime sys_clock_settime32 +256 64 clock_settime sys_clock_settime +257 32 clock_gettime sys_clock_gettime32 +257 64 clock_gettime sys_clock_gettime +258 32 clock_getres sys_clock_getres_time32 +258 64 clock_getres sys_clock_getres +259 32 clock_nanosleep sys_clock_nanosleep_time32 +259 64 clock_nanosleep sys_clock_nanosleep +260 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +261 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +262 32 timer_settime sys_timer_settime32 +262 64 timer_settime sys_timer_settime +263 32 timer_gettime sys_timer_gettime32 +263 64 timer_gettime sys_timer_gettime +264 common timer_getoverrun sys_timer_getoverrun +265 common timer_delete sys_timer_delete +266 common timer_create sys_timer_create compat_sys_timer_create +# 267 was vserver +267 common vserver sys_nis_syscall +268 common io_setup sys_io_setup compat_sys_io_setup +269 common io_destroy sys_io_destroy +270 common io_submit sys_io_submit compat_sys_io_submit +271 common io_cancel sys_io_cancel +272 32 io_getevents sys_io_getevents_time32 +272 64 io_getevents sys_io_getevents +273 common mq_open sys_mq_open compat_sys_mq_open +274 common mq_unlink sys_mq_unlink +275 32 mq_timedsend sys_mq_timedsend_time32 +275 64 mq_timedsend sys_mq_timedsend +276 32 mq_timedreceive sys_mq_timedreceive_time32 +276 64 mq_timedreceive sys_mq_timedreceive +277 common mq_notify sys_mq_notify compat_sys_mq_notify +278 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +279 common waitid sys_waitid compat_sys_waitid +280 common tee sys_tee +281 common add_key sys_add_key +282 common request_key sys_request_key +283 common keyctl sys_keyctl compat_sys_keyctl +284 common openat sys_openat compat_sys_openat +285 common mkdirat sys_mkdirat +286 common mknodat sys_mknodat +287 common fchownat sys_fchownat +288 32 futimesat sys_futimesat_time32 +288 64 futimesat sys_futimesat +289 common fstatat64 sys_fstatat64 compat_sys_fstatat64 +290 common unlinkat sys_unlinkat +291 common renameat sys_renameat +292 common linkat sys_linkat +293 common symlinkat sys_symlinkat +294 common readlinkat sys_readlinkat +295 common fchmodat sys_fchmodat +296 common faccessat sys_faccessat +297 32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +297 64 pselect6 sys_pselect6 +298 32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +298 64 ppoll sys_ppoll +299 common unshare sys_unshare +300 common set_robust_list sys_set_robust_list compat_sys_set_robust_list +301 common get_robust_list sys_get_robust_list compat_sys_get_robust_list +302 common migrate_pages sys_migrate_pages +303 common mbind sys_mbind +304 common get_mempolicy sys_get_mempolicy +305 common set_mempolicy sys_set_mempolicy +306 common kexec_load sys_kexec_load compat_sys_kexec_load +307 common move_pages sys_move_pages +308 common getcpu sys_getcpu +309 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait +310 32 utimensat sys_utimensat_time32 +310 64 utimensat sys_utimensat +311 common signalfd sys_signalfd compat_sys_signalfd +312 common timerfd_create sys_timerfd_create +313 common eventfd sys_eventfd +314 common fallocate sys_fallocate compat_sys_fallocate +315 32 timerfd_settime sys_timerfd_settime32 +315 64 timerfd_settime sys_timerfd_settime +316 32 timerfd_gettime sys_timerfd_gettime32 +316 64 timerfd_gettime sys_timerfd_gettime +317 common signalfd4 sys_signalfd4 compat_sys_signalfd4 +318 common eventfd2 sys_eventfd2 +319 common epoll_create1 sys_epoll_create1 +320 common dup3 sys_dup3 +321 common pipe2 sys_pipe2 +322 common inotify_init1 sys_inotify_init1 +323 common accept4 sys_accept4 +324 common preadv sys_preadv compat_sys_preadv +325 common pwritev sys_pwritev compat_sys_pwritev +326 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +327 common perf_event_open sys_perf_event_open +328 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +328 64 recvmmsg sys_recvmmsg +329 common fanotify_init sys_fanotify_init +330 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark +331 common prlimit64 sys_prlimit64 +332 common name_to_handle_at sys_name_to_handle_at +333 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +334 32 clock_adjtime sys_clock_adjtime32 +334 64 clock_adjtime sys_sparc_clock_adjtime +335 common syncfs sys_syncfs +336 common sendmmsg sys_sendmmsg compat_sys_sendmmsg +337 common setns sys_setns +338 common process_vm_readv sys_process_vm_readv +339 common process_vm_writev sys_process_vm_writev +340 32 kern_features sys_ni_syscall sys_kern_features +340 64 kern_features sys_kern_features +341 common kcmp sys_kcmp +342 common finit_module sys_finit_module +343 common sched_setattr sys_sched_setattr +344 common sched_getattr sys_sched_getattr +345 common renameat2 sys_renameat2 +346 common seccomp sys_seccomp +347 common getrandom sys_getrandom +348 common memfd_create sys_memfd_create +349 common bpf sys_bpf +350 32 execveat sys_execveat sys32_execveat +350 64 execveat sys64_execveat +351 common membarrier sys_membarrier +352 common userfaultfd sys_userfaultfd +353 common bind sys_bind +354 common listen sys_listen +355 common setsockopt sys_setsockopt sys_setsockopt +356 common mlock2 sys_mlock2 +357 common copy_file_range sys_copy_file_range +358 common preadv2 sys_preadv2 compat_sys_preadv2 +359 common pwritev2 sys_pwritev2 compat_sys_pwritev2 +360 common statx sys_statx +361 32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +361 64 io_pgetevents sys_io_pgetevents +362 common pkey_mprotect sys_pkey_mprotect +363 common pkey_alloc sys_pkey_alloc +364 common pkey_free sys_pkey_free +365 common rseq sys_rseq +# room for arch specific syscalls +392 64 semtimedop sys_semtimedop +393 common semget sys_semget +394 common semctl sys_semctl compat_sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl compat_sys_shmctl +397 common shmat sys_shmat compat_sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd compat_sys_msgsnd +401 common msgrcv sys_msgrcv compat_sys_msgrcv +402 common msgctl sys_msgctl compat_sys_msgctl +403 32 clock_gettime64 sys_clock_gettime sys_clock_gettime +404 32 clock_settime64 sys_clock_settime sys_clock_settime +405 32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime +406 32 clock_getres_time64 sys_clock_getres sys_clock_getres +407 32 clock_nanosleep_time64 sys_clock_nanosleep sys_clock_nanosleep +408 32 timer_gettime64 sys_timer_gettime sys_timer_gettime +409 32 timer_settime64 sys_timer_settime sys_timer_settime +410 32 timerfd_gettime64 sys_timerfd_gettime sys_timerfd_gettime +411 32 timerfd_settime64 sys_timerfd_settime sys_timerfd_settime +412 32 utimensat_time64 sys_utimensat sys_utimensat +413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 +417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend +419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive +420 32 semtimedop_time64 sys_semtimedop sys_semtimedop +421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 sys_futex sys_futex +423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +# 435 reserved for clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat diff --git a/tools/perf/arch/sparc/include/syscall_table.h b/tools/perf/arch/sparc/include/syscall_table.h new file mode 100644 index 000000000000..7ff51b783000 --- /dev/null +++ b/tools/perf/arch/sparc/include/syscall_table.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 64 +#include <asm/syscalls_64.h> +#else +#include <asm/syscalls_32.h> +#endif diff --git a/tools/perf/arch/x86/Build b/tools/perf/arch/x86/Build index 87d057491343..02a1ca780a20 100644 --- a/tools/perf/arch/x86/Build +++ b/tools/perf/arch/x86/Build @@ -2,7 +2,6 @@ perf-util-y += util/ perf-test-y += tests/ ifdef SHELLCHECK - SHELL_TESTS := entry/syscalls/syscalltbl.sh TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log) else SHELL_TESTS := diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index a6b6e0a9308a..a295a80ea078 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -1,28 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_JITDUMP := 1 - -### -# Syscall table generation -# - -generated := $(OUTPUT)arch/x86/include/generated -out := $(generated)/asm -header := $(out)/syscalls_64.c -header_32 := $(out)/syscalls_32.c -sys := $(srctree)/tools/perf/arch/x86/entry/syscalls -systbl := $(sys)/syscalltbl.sh - -# Create output directory if not already present -$(shell [ -d '$(out)' ] || mkdir -p '$(out)') - -$(header): $(sys)/syscall_64.tbl $(systbl) - $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@ - -$(header_32): $(sys)/syscall_32.tbl $(systbl) - $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_32.tbl 'x86' > $@ - -clean:: - $(call QUIET_CLEAN, x86) $(RM) -r $(header) $(generated) - -archheaders: $(header) $(header_32) diff --git a/tools/perf/arch/x86/entry/syscalls/Kbuild b/tools/perf/arch/x86/entry/syscalls/Kbuild new file mode 100644 index 000000000000..84c6599b4ea6 --- /dev/null +++ b/tools/perf/arch/x86/entry/syscalls/Kbuild @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h +syscall-y += syscalls_64.h diff --git a/tools/perf/arch/x86/entry/syscalls/Makefile.syscalls b/tools/perf/arch/x86/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..db3d5d6d4e56 --- /dev/null +++ b/tools/perf/arch/x86/entry/syscalls/Makefile.syscalls @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += i386 +syscall_abis_64 += + +syscalltbl = $(srctree)/tools/perf/arch/x86/entry/syscalls/syscall_%.tbl diff --git a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh deleted file mode 100755 index 2b71f99933a5..000000000000 --- a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh +++ /dev/null @@ -1,42 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -in="$1" -arch="$2" - -syscall_macro() { - nr="$1" - name="$2" - - echo " [$nr] = \"$name\"," -} - -emit() { - nr="$1" - entry="$2" - - syscall_macro "$nr" "$entry" -} - -echo "static const char *const syscalltbl_${arch}[] = {" - -sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX) -grep '^[0-9]' "$in" | sort -n > $sorted_table - -max_nr=0 -# the params are: nr abi name entry compat -# use _ for intentionally unused variables according to SC2034 -while read nr _ name _ _; do - if [ $nr -ge 512 ] ; then # discard compat sycalls - break - fi - - emit "$nr" "$name" - max_nr=$nr -done < $sorted_table - -rm -f $sorted_table - -echo "};" - -echo "#define SYSCALLTBL_${arch}_MAX_ID ${max_nr}" diff --git a/tools/perf/arch/x86/include/syscall_table.h b/tools/perf/arch/x86/include/syscall_table.h new file mode 100644 index 000000000000..7ff51b783000 --- /dev/null +++ b/tools/perf/arch/x86/include/syscall_table.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 64 +#include <asm/syscalls_64.h> +#else +#include <asm/syscalls_32.h> +#endif diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index 848327378694..06d7c0205b3d 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -15,6 +15,6 @@ perf-util-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-util-$(CONFIG_AUXTRACE) += auxtrace.o -perf-util-$(CONFIG_AUXTRACE) += archinsn.o +perf-util-y += archinsn.o perf-util-$(CONFIG_AUXTRACE) += intel-pt.o perf-util-$(CONFIG_AUXTRACE) += intel-bts.o diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c index 366b44d0bb7e..7442a2cd87ed 100644 --- a/tools/perf/arch/x86/util/iostat.c +++ b/tools/perf/arch/x86/util/iostat.c @@ -32,7 +32,7 @@ #define MAX_PATH 1024 #endif -#define UNCORE_IIO_PMU_PATH "devices/uncore_iio_%d" +#define UNCORE_IIO_PMU_PATH "bus/event_source/devices/uncore_iio_%d" #define SYSFS_UNCORE_PMU_PATH "%s/"UNCORE_IIO_PMU_PATH #define PLATFORM_MAPPING_PATH UNCORE_IIO_PMU_PATH"/die%d" @@ -403,6 +403,10 @@ void iostat_prefix(struct evlist *evlist, struct iio_root_port *rp = evlist->selected->priv; if (rp) { + /* + * TODO: This is the incorrect format in JSON mode. + * See prepare_timestamp() + */ if (ts) sprintf(prefix, "%6lu.%09lu%s%04x:%02x%s", ts->tv_sec, ts->tv_nsec, diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c index f63747d0abdf..d1c654839049 100644 --- a/tools/perf/arch/x86/util/topdown.c +++ b/tools/perf/arch/x86/util/topdown.c @@ -81,7 +81,7 @@ bool arch_topdown_sample_read(struct evsel *leader) */ evlist__for_each_entry(leader->evlist, evsel) { if (evsel->core.leader != leader->core.leader) - return false; + continue; if (evsel != leader && arch_is_topdown_metrics(evsel)) return true; } diff --git a/tools/perf/arch/xtensa/entry/syscalls/Kbuild b/tools/perf/arch/xtensa/entry/syscalls/Kbuild new file mode 100644 index 000000000000..11707c481a24 --- /dev/null +++ b/tools/perf/arch/xtensa/entry/syscalls/Kbuild @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscalls_32.h diff --git a/tools/perf/arch/xtensa/entry/syscalls/Makefile.syscalls b/tools/perf/arch/xtensa/entry/syscalls/Makefile.syscalls new file mode 100644 index 000000000000..d4aa2358460c --- /dev/null +++ b/tools/perf/arch/xtensa/entry/syscalls/Makefile.syscalls @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += +syscalltbl = $(srctree)/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl new file mode 100644 index 000000000000..37effc1b134e --- /dev/null +++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl @@ -0,0 +1,439 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# system call numbers and entry vectors for xtensa +# +# The format is: +# <number> <abi> <name> <entry point> +# +# The <abi> is always "common" for this file +# +0 common spill sys_ni_syscall +1 common xtensa sys_ni_syscall +2 common available4 sys_ni_syscall +3 common available5 sys_ni_syscall +4 common available6 sys_ni_syscall +5 common available7 sys_ni_syscall +6 common available8 sys_ni_syscall +7 common available9 sys_ni_syscall +# File Operations +8 common open sys_open +9 common close sys_close +10 common dup sys_dup +11 common dup2 sys_dup2 +12 common read sys_read +13 common write sys_write +14 common select sys_select +15 common lseek sys_lseek +16 common poll sys_poll +17 common _llseek sys_llseek +18 common epoll_wait sys_epoll_wait +19 common epoll_ctl sys_epoll_ctl +20 common epoll_create sys_epoll_create +21 common creat sys_creat +22 common truncate sys_truncate +23 common ftruncate sys_ftruncate +24 common readv sys_readv +25 common writev sys_writev +26 common fsync sys_fsync +27 common fdatasync sys_fdatasync +28 common truncate64 sys_truncate64 +29 common ftruncate64 sys_ftruncate64 +30 common pread64 sys_pread64 +31 common pwrite64 sys_pwrite64 +32 common link sys_link +33 common rename sys_rename +34 common symlink sys_symlink +35 common readlink sys_readlink +36 common mknod sys_mknod +37 common pipe sys_pipe +38 common unlink sys_unlink +39 common rmdir sys_rmdir +40 common mkdir sys_mkdir +41 common chdir sys_chdir +42 common fchdir sys_fchdir +43 common getcwd sys_getcwd +44 common chmod sys_chmod +45 common chown sys_chown +46 common stat sys_newstat +47 common stat64 sys_stat64 +48 common lchown sys_lchown +49 common lstat sys_newlstat +50 common lstat64 sys_lstat64 +51 common available51 sys_ni_syscall +52 common fchmod sys_fchmod +53 common fchown sys_fchown +54 common fstat sys_newfstat +55 common fstat64 sys_fstat64 +56 common flock sys_flock +57 common access sys_access +58 common umask sys_umask +59 common getdents sys_getdents +60 common getdents64 sys_getdents64 +61 common fcntl64 sys_fcntl64 +62 common fallocate sys_fallocate +63 common fadvise64_64 xtensa_fadvise64_64 +64 common utime sys_utime32 +65 common utimes sys_utimes_time32 +66 common ioctl sys_ioctl +67 common fcntl sys_fcntl +68 common setxattr sys_setxattr +69 common getxattr sys_getxattr +70 common listxattr sys_listxattr +71 common removexattr sys_removexattr +72 common lsetxattr sys_lsetxattr +73 common lgetxattr sys_lgetxattr +74 common llistxattr sys_llistxattr +75 common lremovexattr sys_lremovexattr +76 common fsetxattr sys_fsetxattr +77 common fgetxattr sys_fgetxattr +78 common flistxattr sys_flistxattr +79 common fremovexattr sys_fremovexattr +# File Map / Shared Memory Operations +80 common mmap2 sys_mmap_pgoff +81 common munmap sys_munmap +82 common mprotect sys_mprotect +83 common brk sys_brk +84 common mlock sys_mlock +85 common munlock sys_munlock +86 common mlockall sys_mlockall +87 common munlockall sys_munlockall +88 common mremap sys_mremap +89 common msync sys_msync +90 common mincore sys_mincore +91 common madvise sys_madvise +92 common shmget sys_shmget +93 common shmat xtensa_shmat +94 common shmctl sys_old_shmctl +95 common shmdt sys_shmdt +# Socket Operations +96 common socket sys_socket +97 common setsockopt sys_setsockopt +98 common getsockopt sys_getsockopt +99 common shutdown sys_shutdown +100 common bind sys_bind +101 common connect sys_connect +102 common listen sys_listen +103 common accept sys_accept +104 common getsockname sys_getsockname +105 common getpeername sys_getpeername +106 common sendmsg sys_sendmsg +107 common recvmsg sys_recvmsg +108 common send sys_send +109 common recv sys_recv +110 common sendto sys_sendto +111 common recvfrom sys_recvfrom +112 common socketpair sys_socketpair +113 common sendfile sys_sendfile +114 common sendfile64 sys_sendfile64 +115 common sendmmsg sys_sendmmsg +# Process Operations +116 common clone sys_clone +117 common execve sys_execve +118 common exit sys_exit +119 common exit_group sys_exit_group +120 common getpid sys_getpid +121 common wait4 sys_wait4 +122 common waitid sys_waitid +123 common kill sys_kill +124 common tkill sys_tkill +125 common tgkill sys_tgkill +126 common set_tid_address sys_set_tid_address +127 common gettid sys_gettid +128 common setsid sys_setsid +129 common getsid sys_getsid +130 common prctl sys_prctl +131 common personality sys_personality +132 common getpriority sys_getpriority +133 common setpriority sys_setpriority +134 common setitimer sys_setitimer +135 common getitimer sys_getitimer +136 common setuid sys_setuid +137 common getuid sys_getuid +138 common setgid sys_setgid +139 common getgid sys_getgid +140 common geteuid sys_geteuid +141 common getegid sys_getegid +142 common setreuid sys_setreuid +143 common setregid sys_setregid +144 common setresuid sys_setresuid +145 common getresuid sys_getresuid +146 common setresgid sys_setresgid +147 common getresgid sys_getresgid +148 common setpgid sys_setpgid +149 common getpgid sys_getpgid +150 common getppid sys_getppid +151 common getpgrp sys_getpgrp +# 152 was set_thread_area +152 common reserved152 sys_ni_syscall +# 153 was get_thread_area +153 common reserved153 sys_ni_syscall +154 common times sys_times +155 common acct sys_acct +156 common sched_setaffinity sys_sched_setaffinity +157 common sched_getaffinity sys_sched_getaffinity +158 common capget sys_capget +159 common capset sys_capset +160 common ptrace sys_ptrace +161 common semtimedop sys_semtimedop_time32 +162 common semget sys_semget +163 common semop sys_semop +164 common semctl sys_old_semctl +165 common available165 sys_ni_syscall +166 common msgget sys_msgget +167 common msgsnd sys_msgsnd +168 common msgrcv sys_msgrcv +169 common msgctl sys_old_msgctl +170 common available170 sys_ni_syscall +# File System +171 common umount2 sys_umount +172 common mount sys_mount +173 common swapon sys_swapon +174 common chroot sys_chroot +175 common pivot_root sys_pivot_root +176 common umount sys_oldumount +177 common swapoff sys_swapoff +178 common sync sys_sync +179 common syncfs sys_syncfs +180 common setfsuid sys_setfsuid +181 common setfsgid sys_setfsgid +182 common sysfs sys_sysfs +183 common ustat sys_ustat +184 common statfs sys_statfs +185 common fstatfs sys_fstatfs +186 common statfs64 sys_statfs64 +187 common fstatfs64 sys_fstatfs64 +# System +188 common setrlimit sys_setrlimit +189 common getrlimit sys_getrlimit +190 common getrusage sys_getrusage +191 common futex sys_futex_time32 +192 common gettimeofday sys_gettimeofday +193 common settimeofday sys_settimeofday +194 common adjtimex sys_adjtimex_time32 +195 common nanosleep sys_nanosleep_time32 +196 common getgroups sys_getgroups +197 common setgroups sys_setgroups +198 common sethostname sys_sethostname +199 common setdomainname sys_setdomainname +200 common syslog sys_syslog +201 common vhangup sys_vhangup +202 common uselib sys_uselib +203 common reboot sys_reboot +204 common quotactl sys_quotactl +# 205 was old nfsservctl +205 common nfsservctl sys_ni_syscall +206 common _sysctl sys_ni_syscall +207 common bdflush sys_ni_syscall +208 common uname sys_newuname +209 common sysinfo sys_sysinfo +210 common init_module sys_init_module +211 common delete_module sys_delete_module +212 common sched_setparam sys_sched_setparam +213 common sched_getparam sys_sched_getparam +214 common sched_setscheduler sys_sched_setscheduler +215 common sched_getscheduler sys_sched_getscheduler +216 common sched_get_priority_max sys_sched_get_priority_max +217 common sched_get_priority_min sys_sched_get_priority_min +218 common sched_rr_get_interval sys_sched_rr_get_interval_time32 +219 common sched_yield sys_sched_yield +222 common available222 sys_ni_syscall +# Signal Handling +223 common restart_syscall sys_restart_syscall +224 common sigaltstack sys_sigaltstack +225 common rt_sigreturn xtensa_rt_sigreturn +226 common rt_sigaction sys_rt_sigaction +227 common rt_sigprocmask sys_rt_sigprocmask +228 common rt_sigpending sys_rt_sigpending +229 common rt_sigtimedwait sys_rt_sigtimedwait_time32 +230 common rt_sigqueueinfo sys_rt_sigqueueinfo +231 common rt_sigsuspend sys_rt_sigsuspend +# Message +232 common mq_open sys_mq_open +233 common mq_unlink sys_mq_unlink +234 common mq_timedsend sys_mq_timedsend_time32 +235 common mq_timedreceive sys_mq_timedreceive_time32 +236 common mq_notify sys_mq_notify +237 common mq_getsetattr sys_mq_getsetattr +238 common available238 sys_ni_syscall +239 common io_setup sys_io_setup +# IO +240 common io_destroy sys_io_destroy +241 common io_submit sys_io_submit +242 common io_getevents sys_io_getevents_time32 +243 common io_cancel sys_io_cancel +244 common clock_settime sys_clock_settime32 +245 common clock_gettime sys_clock_gettime32 +246 common clock_getres sys_clock_getres_time32 +247 common clock_nanosleep sys_clock_nanosleep_time32 +# Timer +248 common timer_create sys_timer_create +249 common timer_delete sys_timer_delete +250 common timer_settime sys_timer_settime32 +251 common timer_gettime sys_timer_gettime32 +252 common timer_getoverrun sys_timer_getoverrun +# System +253 common reserved253 sys_ni_syscall +254 common lookup_dcookie sys_ni_syscall +255 common available255 sys_ni_syscall +256 common add_key sys_add_key +257 common request_key sys_request_key +258 common keyctl sys_keyctl +259 common available259 sys_ni_syscall +260 common readahead sys_readahead +261 common remap_file_pages sys_remap_file_pages +262 common migrate_pages sys_migrate_pages +263 common mbind sys_mbind +264 common get_mempolicy sys_get_mempolicy +265 common set_mempolicy sys_set_mempolicy +266 common unshare sys_unshare +267 common move_pages sys_move_pages +268 common splice sys_splice +269 common tee sys_tee +270 common vmsplice sys_vmsplice +271 common available271 sys_ni_syscall +272 common pselect6 sys_pselect6_time32 +273 common ppoll sys_ppoll_time32 +274 common epoll_pwait sys_epoll_pwait +275 common epoll_create1 sys_epoll_create1 +276 common inotify_init sys_inotify_init +277 common inotify_add_watch sys_inotify_add_watch +278 common inotify_rm_watch sys_inotify_rm_watch +279 common inotify_init1 sys_inotify_init1 +280 common getcpu sys_getcpu +281 common kexec_load sys_ni_syscall +282 common ioprio_set sys_ioprio_set +283 common ioprio_get sys_ioprio_get +284 common set_robust_list sys_set_robust_list +285 common get_robust_list sys_get_robust_list +286 common available286 sys_ni_syscall +287 common available287 sys_ni_syscall +# Relative File Operations +288 common openat sys_openat +289 common mkdirat sys_mkdirat +290 common mknodat sys_mknodat +291 common unlinkat sys_unlinkat +292 common renameat sys_renameat +293 common linkat sys_linkat +294 common symlinkat sys_symlinkat +295 common readlinkat sys_readlinkat +296 common utimensat sys_utimensat_time32 +297 common fchownat sys_fchownat +298 common futimesat sys_futimesat_time32 +299 common fstatat64 sys_fstatat64 +300 common fchmodat sys_fchmodat +301 common faccessat sys_faccessat +302 common available302 sys_ni_syscall +303 common available303 sys_ni_syscall +304 common signalfd sys_signalfd +# 305 was timerfd +306 common eventfd sys_eventfd +307 common recvmmsg sys_recvmmsg_time32 +308 common setns sys_setns +309 common signalfd4 sys_signalfd4 +310 common dup3 sys_dup3 +311 common pipe2 sys_pipe2 +312 common timerfd_create sys_timerfd_create +313 common timerfd_settime sys_timerfd_settime32 +314 common timerfd_gettime sys_timerfd_gettime32 +315 common available315 sys_ni_syscall +316 common eventfd2 sys_eventfd2 +317 common preadv sys_preadv +318 common pwritev sys_pwritev +319 common available319 sys_ni_syscall +320 common fanotify_init sys_fanotify_init +321 common fanotify_mark sys_fanotify_mark +322 common process_vm_readv sys_process_vm_readv +323 common process_vm_writev sys_process_vm_writev +324 common name_to_handle_at sys_name_to_handle_at +325 common open_by_handle_at sys_open_by_handle_at +326 common sync_file_range2 sys_sync_file_range2 +327 common perf_event_open sys_perf_event_open +328 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +329 common clock_adjtime sys_clock_adjtime32 +330 common prlimit64 sys_prlimit64 +331 common kcmp sys_kcmp +332 common finit_module sys_finit_module +333 common accept4 sys_accept4 +334 common sched_setattr sys_sched_setattr +335 common sched_getattr sys_sched_getattr +336 common renameat2 sys_renameat2 +337 common seccomp sys_seccomp +338 common getrandom sys_getrandom +339 common memfd_create sys_memfd_create +340 common bpf sys_bpf +341 common execveat sys_execveat +342 common userfaultfd sys_userfaultfd +343 common membarrier sys_membarrier +344 common mlock2 sys_mlock2 +345 common copy_file_range sys_copy_file_range +346 common preadv2 sys_preadv2 +347 common pwritev2 sys_pwritev2 +348 common pkey_mprotect sys_pkey_mprotect +349 common pkey_alloc sys_pkey_alloc +350 common pkey_free sys_pkey_free +351 common statx sys_statx +352 common rseq sys_rseq +# 353 through 402 are unassigned to sync up with generic numbers +403 common clock_gettime64 sys_clock_gettime +404 common clock_settime64 sys_clock_settime +405 common clock_adjtime64 sys_clock_adjtime +406 common clock_getres_time64 sys_clock_getres +407 common clock_nanosleep_time64 sys_clock_nanosleep +408 common timer_gettime64 sys_timer_gettime +409 common timer_settime64 sys_timer_settime +410 common timerfd_gettime64 sys_timerfd_gettime +411 common timerfd_settime64 sys_timerfd_settime +412 common utimensat_time64 sys_utimensat +413 common pselect6_time64 sys_pselect6 +414 common ppoll_time64 sys_ppoll +416 common io_pgetevents_time64 sys_io_pgetevents +417 common recvmmsg_time64 sys_recvmmsg +418 common mq_timedsend_time64 sys_mq_timedsend +419 common mq_timedreceive_time64 sys_mq_timedreceive +420 common semtimedop_time64 sys_semtimedop +421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait +422 common futex_time64 sys_futex +423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +436 common close_range sys_close_range +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 +442 common mount_setattr sys_mount_setattr +443 common quotactl_fd sys_quotactl_fd +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self +# 447 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat diff --git a/tools/perf/arch/xtensa/include/syscall_table.h b/tools/perf/arch/xtensa/include/syscall_table.h new file mode 100644 index 000000000000..4c942821662d --- /dev/null +++ b/tools/perf/arch/xtensa/include/syscall_table.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <asm/syscalls_32.h> diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c index a759eb2328be..f55c07e4be94 100644 --- a/tools/perf/bench/inject-buildid.c +++ b/tools/perf/bench/inject-buildid.c @@ -52,7 +52,7 @@ struct bench_dso { static int nr_dsos; static struct bench_dso *dsos; -extern int cmd_inject(int argc, const char *argv[]); +extern int main(int argc, const char **argv); static const struct option options[] = { OPT_UINTEGER('i', "iterations", &iterations, @@ -294,7 +294,7 @@ static int setup_injection(struct bench_data *data, bool build_id_all) if (data->pid == 0) { const char **inject_argv; - int inject_argc = 2; + int inject_argc = 3; close(data->input_pipe[1]); close(data->output_pipe[0]); @@ -318,15 +318,16 @@ static int setup_injection(struct bench_data *data, bool build_id_all) if (inject_argv == NULL) exit(1); - inject_argv[0] = strdup("inject"); - inject_argv[1] = strdup("-b"); + inject_argv[0] = strdup("perf"); + inject_argv[1] = strdup("inject"); + inject_argv[2] = strdup("-b"); if (build_id_all) - inject_argv[2] = strdup("--buildid-all"); + inject_argv[3] = strdup("--buildid-all"); /* signal that we're ready to go */ close(ready_pipe[1]); - cmd_inject(inject_argc, inject_argv); + main(inject_argc, inject_argv); exit(0); } diff --git a/tools/perf/bench/syscall.c b/tools/perf/bench/syscall.c index ea4dfc07cbd6..e7dc216f717f 100644 --- a/tools/perf/bench/syscall.c +++ b/tools/perf/bench/syscall.c @@ -22,8 +22,7 @@ #define __NR_fork -1 #endif -#define LOOPS_DEFAULT 10000000 -static int loops = LOOPS_DEFAULT; +static int loops; static const struct option options[] = { OPT_INTEGER('l', "loop", &loops, "Specify number of loops"), @@ -80,6 +79,18 @@ static int bench_syscall_common(int argc, const char **argv, int syscall) const char *name = NULL; int i; + switch (syscall) { + case __NR_fork: + case __NR_execve: + /* Limit default loop to 10000 times to save time */ + loops = 10000; + break; + default: + loops = 10000000; + break; + } + + /* Options -l and --loops override default above */ argc = parse_options(argc, argv, options, bench_syscall_usage, 0); gettimeofday(&start, NULL); @@ -94,16 +105,9 @@ static int bench_syscall_common(int argc, const char **argv, int syscall) break; case __NR_fork: test_fork(); - /* Only loop 10000 times to save time */ - if (i == 10000) - loops = 10000; break; case __NR_execve: test_execve(); - /* Only loop 10000 times to save time */ - if (i == 10000) - loops = 10000; - break; default: break; } diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index bb87e6e7687d..836ae0122dab 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -7,6 +7,7 @@ * a histogram of results, along various sorting keys. */ #include "builtin.h" +#include "perf.h" #include "util/color.h" #include <linux/list.h> diff --git a/tools/perf/builtin-check.c b/tools/perf/builtin-check.c index 2346536a5ee1..61a11a9b4e75 100644 --- a/tools/perf/builtin-check.c +++ b/tools/perf/builtin-check.c @@ -31,7 +31,6 @@ struct feature_status supported_features[] = { FEATURE_STATUS("dwarf_getlocations", HAVE_LIBDW_SUPPORT), FEATURE_STATUS("dwarf-unwind", HAVE_DWARF_UNWIND_SUPPORT), FEATURE_STATUS("auxtrace", HAVE_AUXTRACE_SUPPORT), - FEATURE_STATUS("libaudit", HAVE_LIBAUDIT_SUPPORT), FEATURE_STATUS("libbfd", HAVE_LIBBFD_SUPPORT), FEATURE_STATUS("libcapstone", HAVE_LIBCAPSTONE_SUPPORT), FEATURE_STATUS("libcrypto", HAVE_LIBCRYPTO_SUPPORT), @@ -47,7 +46,6 @@ struct feature_status supported_features[] = { FEATURE_STATUS("libunwind", HAVE_LIBUNWIND_SUPPORT), FEATURE_STATUS("lzma", HAVE_LZMA_SUPPORT), FEATURE_STATUS("numa_num_possible_cpus", HAVE_LIBNUMA_SUPPORT), - FEATURE_STATUS("syscall_table", HAVE_SYSCALL_TABLE_SUPPORT), FEATURE_STATUS("zlib", HAVE_ZLIB_SUPPORT), FEATURE_STATUS("zstd", HAVE_ZSTD_SUPPORT), diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c index 2e8363778935..45b5312fbe83 100644 --- a/tools/perf/builtin-config.c +++ b/tools/perf/builtin-config.c @@ -154,6 +154,44 @@ static int parse_config_arg(char *arg, char **var, char **value) return 0; } +int perf_config__set_variable(const char *var, const char *value) +{ + char path[PATH_MAX]; + char *user_config = mkpath(path, sizeof(path), "%s/.perfconfig", getenv("HOME")); + const char *config_filename; + struct perf_config_set *set; + int ret = -1; + + if (use_system_config) + config_exclusive_filename = perf_etc_perfconfig(); + else if (use_user_config) + config_exclusive_filename = user_config; + + if (!config_exclusive_filename) + config_filename = user_config; + else + config_filename = config_exclusive_filename; + + set = perf_config_set__new(); + if (!set) + goto out_err; + + if (perf_config_set__collect(set, config_filename, var, value) < 0) { + pr_err("Failed to add '%s=%s'\n", var, value); + goto out_err; + } + + if (set_config(set, config_filename) < 0) { + pr_err("Failed to set the configs on %s\n", config_filename); + goto out_err; + } + + ret = 0; +out_err: + perf_config_set__delete(set); + return ret; +} + int cmd_config(int argc, const char **argv) { int i, ret = -1; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 82fb7773e03e..ae490d58af92 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -6,6 +6,7 @@ * DSOs and symbol information, sort them and produce a diff. */ #include "builtin.h" +#include "perf.h" #include "util/debug.h" #include "util/event.h" @@ -1019,12 +1020,12 @@ static int process_base_stream(struct data__file *data_base, continue; es_base = evsel_streams__entry(data_base->evlist_streams, - evsel_base->core.idx); + evsel_base); if (!es_base) return -1; es_pair = evsel_streams__entry(data_pair->evlist_streams, - evsel_pair->core.idx); + evsel_pair); if (!es_pair) return -1; diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index a56cf8b0a7d4..cfd770ec7286 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -43,6 +43,8 @@ static volatile sig_atomic_t workload_exec_errno; static volatile sig_atomic_t done; +static struct stats latency_stats; /* for tracepoints */ + static void sig_handler(int sig __maybe_unused) { done = true; @@ -726,9 +728,11 @@ out: return (done && !workload_exec_errno) ? 0 : -1; } -static void make_histogram(int buckets[], char *buf, size_t len, char *linebuf, - bool use_nsec) +static void make_histogram(struct perf_ftrace *ftrace, int buckets[], + char *buf, size_t len, char *linebuf) { + int min_latency = ftrace->min_latency; + int max_latency = ftrace->max_latency; char *p, *q; char *unit; double num; @@ -774,16 +778,34 @@ static void make_histogram(int buckets[], char *buf, size_t len, char *linebuf, if (!unit || strncmp(unit, " us", 3)) goto next; - if (use_nsec) + if (ftrace->use_nsec) num *= 1000; - i = log2(num); - if (i < 0) - i = 0; + i = 0; + if (num < min_latency) + goto do_inc; + + num -= min_latency; + + if (!ftrace->bucket_range) { + i = log2(num); + if (i < 0) + i = 0; + } else { + // Less than 1 unit (ms or ns), or, in the future, + // than the min latency desired. + if (num > 0) // 1st entry: [ 1 unit .. bucket_range units ] + i = num / ftrace->bucket_range + 1; + if (num >= max_latency - min_latency) + i = NUM_BUCKET -1; + } if (i >= NUM_BUCKET) i = NUM_BUCKET - 1; + num += min_latency; +do_inc: buckets[i]++; + update_stats(&latency_stats, num); next: /* empty the line buffer for the next output */ @@ -794,8 +816,10 @@ next: strcat(linebuf, p); } -static void display_histogram(int buckets[], bool use_nsec) +static void display_histogram(struct perf_ftrace *ftrace, int buckets[]) { + int min_latency = ftrace->min_latency; + bool use_nsec = ftrace->use_nsec; int i; int total = 0; int bar_total = 46; /* to fit in 80 column */ @@ -814,30 +838,74 @@ static void display_histogram(int buckets[], bool use_nsec) " DURATION ", "COUNT", bar_total, "GRAPH"); bar_len = buckets[0] * bar_total / total; - printf(" %4d - %-4d %s | %10d | %.*s%*s |\n", - 0, 1, use_nsec ? "ns" : "us", buckets[0], bar_len, bar, bar_total - bar_len, ""); + + printf(" %4d - %4d %s | %10d | %.*s%*s |\n", + 0, min_latency ?: 1, use_nsec ? "ns" : "us", + buckets[0], bar_len, bar, bar_total - bar_len, ""); for (i = 1; i < NUM_BUCKET - 1; i++) { - int start = (1 << (i - 1)); - int stop = 1 << i; + unsigned int start, stop; const char *unit = use_nsec ? "ns" : "us"; - if (start >= 1024) { - start >>= 10; - stop >>= 10; - unit = use_nsec ? "us" : "ms"; + if (!ftrace->bucket_range) { + start = (1 << (i - 1)); + stop = 1 << i; + + if (start >= 1024) { + start >>= 10; + stop >>= 10; + unit = use_nsec ? "us" : "ms"; + } + } else { + start = (i - 1) * ftrace->bucket_range + min_latency; + stop = i * ftrace->bucket_range + min_latency; + + if (start >= ftrace->max_latency) + break; + if (stop > ftrace->max_latency) + stop = ftrace->max_latency; + + if (start >= 1000) { + double dstart = start / 1000.0, + dstop = stop / 1000.0; + printf(" %4.2f - %-4.2f", dstart, dstop); + unit = use_nsec ? "us" : "ms"; + goto print_bucket_info; + } } + + printf(" %4d - %4d", start, stop); +print_bucket_info: bar_len = buckets[i] * bar_total / total; - printf(" %4d - %-4d %s | %10d | %.*s%*s |\n", - start, stop, unit, buckets[i], bar_len, bar, + printf(" %s | %10d | %.*s%*s |\n", unit, buckets[i], bar_len, bar, bar_total - bar_len, ""); } bar_len = buckets[NUM_BUCKET - 1] * bar_total / total; - printf(" %4d - %-4s %s | %10d | %.*s%*s |\n", - 1, "...", use_nsec ? "ms" : " s", buckets[NUM_BUCKET - 1], + if (!ftrace->bucket_range) { + printf(" %4d - %-4s %s", 1, "...", use_nsec ? "ms" : "s "); + } else { + unsigned int upper_outlier = (NUM_BUCKET - 2) * ftrace->bucket_range + min_latency; + if (upper_outlier > ftrace->max_latency) + upper_outlier = ftrace->max_latency; + + if (upper_outlier >= 1000) { + double dstart = upper_outlier / 1000.0; + + printf(" %4.2f - %-4s %s", dstart, "...", use_nsec ? "us" : "ms"); + } else { + printf(" %4d - %4s %s", upper_outlier, "...", use_nsec ? "ns" : "us"); + } + } + printf(" | %10d | %.*s%*s |\n", buckets[NUM_BUCKET - 1], bar_len, bar, bar_total - bar_len, ""); + printf("\n# statistics (in %s)\n", ftrace->use_nsec ? "nsec" : "usec"); + printf(" total time: %20.0f\n", latency_stats.mean * latency_stats.n); + printf(" avg time: %20.0f\n", latency_stats.mean); + printf(" max time: %20"PRIu64"\n", latency_stats.max); + printf(" min time: %20"PRIu64"\n", latency_stats.min); + printf(" count: %20.0f\n", latency_stats.n); } static int prepare_func_latency(struct perf_ftrace *ftrace) @@ -876,6 +944,8 @@ static int prepare_func_latency(struct perf_ftrace *ftrace) if (fd < 0) pr_err("failed to open trace_pipe\n"); + init_stats(&latency_stats); + put_tracing_file(trace_file); return fd; } @@ -905,7 +975,7 @@ static int stop_func_latency(struct perf_ftrace *ftrace) static int read_func_latency(struct perf_ftrace *ftrace, int buckets[]) { if (ftrace->target.use_bpf) - return perf_ftrace__latency_read_bpf(ftrace, buckets); + return perf_ftrace__latency_read_bpf(ftrace, buckets, &latency_stats); return 0; } @@ -951,7 +1021,7 @@ static int __cmd_latency(struct perf_ftrace *ftrace) if (n < 0) break; - make_histogram(buckets, buf, n, line, ftrace->use_nsec); + make_histogram(ftrace, buckets, buf, n, line); } } @@ -968,12 +1038,12 @@ static int __cmd_latency(struct perf_ftrace *ftrace) int n = read(trace_fd, buf, sizeof(buf) - 1); if (n <= 0) break; - make_histogram(buckets, buf, n, line, ftrace->use_nsec); + make_histogram(ftrace, buckets, buf, n, line); } read_func_latency(ftrace, buckets); - display_histogram(buckets, ftrace->use_nsec); + display_histogram(ftrace, buckets); out: close(trace_fd); @@ -996,6 +1066,7 @@ static int prepare_func_profile(struct perf_ftrace *ftrace) { ftrace->tracer = "function_graph"; ftrace->graph_tail = 1; + ftrace->graph_verbose = 0; ftrace->profile_hash = hashmap__new(profile_hash, profile_equal, NULL); if (ftrace->profile_hash == NULL) @@ -1558,6 +1629,12 @@ int cmd_ftrace(int argc, const char **argv) #endif OPT_BOOLEAN('n', "use-nsec", &ftrace.use_nsec, "Use nano-second histogram"), + OPT_UINTEGER(0, "bucket-range", &ftrace.bucket_range, + "Bucket range in ms or ns (-n/--use-nsec), default is log2() mode"), + OPT_UINTEGER(0, "min-latency", &ftrace.min_latency, + "Minimum latency (1st bucket). Works only with --bucket-range."), + OPT_UINTEGER(0, "max-latency", &ftrace.max_latency, + "Maximum latency (last bucket). Works only with --bucket-range and total buckets less than 22."), OPT_PARENT(common_options), }; const struct option profile_options[] = { @@ -1576,6 +1653,9 @@ int cmd_ftrace(int argc, const char **argv) OPT_CALLBACK('s', "sort", &profile_sort, "key", "Sort result by key: total (default), avg, max, count, name.", parse_sort_key), + OPT_CALLBACK(0, "graph-opts", &ftrace, "options", + "Graph tracer options, available options: nosleep-time,noirqs,thresh=<n>,depth=<n>", + parse_graph_tracer_opts), OPT_PARENT(common_options), }; const struct option *options = ftrace_options; @@ -1653,6 +1733,29 @@ int cmd_ftrace(int argc, const char **argv) ret = -EINVAL; goto out_delete_filters; } + if (!ftrace.bucket_range && ftrace.min_latency) { + pr_err("--min-latency works only with --bucket-range\n"); + parse_options_usage(ftrace_usage, options, + "min-latency", /*short_opt=*/false); + ret = -EINVAL; + goto out_delete_filters; + } + if (ftrace.bucket_range && !ftrace.min_latency) { + /* default min latency should be the bucket range */ + ftrace.min_latency = ftrace.bucket_range; + } + if (!ftrace.bucket_range && ftrace.max_latency) { + pr_err("--max-latency works only with --bucket-range\n"); + parse_options_usage(ftrace_usage, options, + "max-latency", /*short_opt=*/false); + ret = -EINVAL; + goto out_delete_filters; + } + if (ftrace.bucket_range && !ftrace.max_latency) { + /* default max latency should depend on bucket range and num_buckets */ + ftrace.max_latency = (NUM_BUCKET - 2) * ftrace.bucket_range + + ftrace.min_latency; + } cmd_func = __cmd_latency; break; case PERF_FTRACE_PROFILE: diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 0854d3cd9f6a..7be6fb6df595 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -447,9 +447,7 @@ int cmd_help(int argc, const char **argv) #ifdef HAVE_LIBELF_SUPPORT "probe", #endif -#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT) "trace", -#endif NULL }; const char *builtin_help_usage[] = { "perf help [--all] [--man|--web|--info] [command]", diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 4d8d94146f8d..67fb1946ef13 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -761,6 +761,7 @@ static int parse_gfp_flags(struct evsel *evsel, struct perf_sample *sample, }; struct trace_seq seq; char *str, *pos = NULL; + const struct tep_event *tp_format; if (nr_gfps) { struct gfp_flag key = { @@ -772,8 +773,9 @@ static int parse_gfp_flags(struct evsel *evsel, struct perf_sample *sample, } trace_seq_init(&seq); - tep_print_event(evsel->tp_format->tep, - &seq, &record, "%s", TEP_PRINT_INFO); + tp_format = evsel__tp_format(evsel); + if (tp_format) + tep_print_event(tp_format->tep, &seq, &record, "%s", TEP_PRINT_INFO); str = strtok_r(seq.buffer, " ", &pos); while (str) { @@ -2012,13 +2014,13 @@ int cmd_kmem(int argc, const char **argv) if (kmem_page) { struct evsel *evsel = evlist__find_tracepoint_by_name(session->evlist, "kmem:mm_page_alloc"); + const struct tep_event *tp_format = evsel ? evsel__tp_format(evsel) : NULL; - if (evsel == NULL) { + if (tp_format == NULL) { pr_err(errmsg, "page", "page"); goto out_delete; } - - kmem_page_size = tep_get_page_size(evsel->tp_format->tep); + kmem_page_size = tep_get_page_size(tp_format->tep); symbol_conf.use_callchain = true; } diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 274568d712d1..67fd2b006b0b 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -615,67 +615,6 @@ static const char *get_filename_for_perf_kvm(void) #if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) -void exit_event_get_key(struct evsel *evsel, - struct perf_sample *sample, - struct event_key *key) -{ - key->info = 0; - key->key = evsel__intval(evsel, sample, kvm_exit_reason); -} - -bool kvm_exit_event(struct evsel *evsel) -{ - return evsel__name_is(evsel, kvm_exit_trace); -} - -bool exit_event_begin(struct evsel *evsel, - struct perf_sample *sample, struct event_key *key) -{ - if (kvm_exit_event(evsel)) { - exit_event_get_key(evsel, sample, key); - return true; - } - - return false; -} - -bool kvm_entry_event(struct evsel *evsel) -{ - return evsel__name_is(evsel, kvm_entry_trace); -} - -bool exit_event_end(struct evsel *evsel, - struct perf_sample *sample __maybe_unused, - struct event_key *key __maybe_unused) -{ - return kvm_entry_event(evsel); -} - -static const char *get_exit_reason(struct perf_kvm_stat *kvm, - struct exit_reasons_table *tbl, - u64 exit_code) -{ - while (tbl->reason != NULL) { - if (tbl->exit_code == exit_code) - return tbl->reason; - tbl++; - } - - pr_err("unknown kvm exit code:%lld on %s\n", - (unsigned long long)exit_code, kvm->exit_reasons_isa); - return "UNKNOWN"; -} - -void exit_event_decode_key(struct perf_kvm_stat *kvm, - struct event_key *key, - char *decode) -{ - const char *exit_reason = get_exit_reason(kvm, key->exit_reasons, - key->key); - - scnprintf(decode, KVM_EVENT_NAME_LEN, "%s", exit_reason); -} - static bool register_kvm_events_ops(struct perf_kvm_stat *kvm) { struct kvm_reg_events_ops *events_ops = kvm_reg_events_ops; diff --git a/tools/perf/builtin-kwork.c b/tools/perf/builtin-kwork.c index 8234410cba4c..c41a68d073de 100644 --- a/tools/perf/builtin-kwork.c +++ b/tools/perf/builtin-kwork.c @@ -6,6 +6,7 @@ */ #include "builtin.h" +#include "perf.h" #include "util/data.h" #include "util/evlist.h" @@ -1103,7 +1104,8 @@ static char *evsel__softirq_name(struct evsel *evsel, u64 num) char *name = NULL; bool found = false; struct tep_print_flag_sym *sym = NULL; - struct tep_print_arg *args = evsel->tp_format->print_fmt.args; + const struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_print_arg *args = tp_format ? tp_format->print_fmt.args : NULL; if ((args == NULL) || (args->next == NULL)) return NULL; @@ -1846,7 +1848,7 @@ static void process_skipped_events(struct perf_kwork *kwork, } } -struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork, +static struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork, struct kwork_class *class, struct kwork_work *key) { @@ -2344,6 +2346,7 @@ int cmd_kwork(int argc, const char **argv) .all_runtime = 0, .all_count = 0, .nr_skipped_events = { 0 }, + .add_work = perf_kwork_add_work, }; static const char default_report_sort_order[] = "runtime, max, count"; static const char default_latency_sort_order[] = "avg, max, count"; diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 33a456980664..5d405cd8e696 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -46,15 +46,6 @@ static struct perf_session *session; static struct target target; -/* based on kernel/lockdep.c */ -#define LOCKHASH_BITS 12 -#define LOCKHASH_SIZE (1UL << LOCKHASH_BITS) - -static struct hlist_head *lockhash_table; - -#define __lockhashfn(key) hash_long((unsigned long)key, LOCKHASH_BITS) -#define lockhashentry(key) (lockhash_table + __lockhashfn((key))) - static struct rb_root thread_stats; static bool combine_locks; @@ -67,24 +58,13 @@ static unsigned long bpf_map_entries = MAX_ENTRIES; static int max_stack_depth = CONTENTION_STACK_DEPTH; static int stack_skip = CONTENTION_STACK_SKIP; static int print_nr_entries = INT_MAX / 2; -static LIST_HEAD(callstack_filters); static const char *output_name = NULL; static FILE *lock_output; -struct callstack_filter { - struct list_head list; - char name[]; -}; - static struct lock_filter filters; static enum lock_aggr_mode aggr_mode = LOCK_AGGR_ADDR; -static bool needs_callstack(void) -{ - return !list_empty(&callstack_filters); -} - static struct thread_stat *thread_stat_find(u32 tid) { struct rb_node *node; @@ -477,93 +457,6 @@ static struct lock_stat *pop_from_result(void) return container_of(node, struct lock_stat, rb); } -struct lock_stat *lock_stat_find(u64 addr) -{ - struct hlist_head *entry = lockhashentry(addr); - struct lock_stat *ret; - - hlist_for_each_entry(ret, entry, hash_entry) { - if (ret->addr == addr) - return ret; - } - return NULL; -} - -struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags) -{ - struct hlist_head *entry = lockhashentry(addr); - struct lock_stat *ret, *new; - - hlist_for_each_entry(ret, entry, hash_entry) { - if (ret->addr == addr) - return ret; - } - - new = zalloc(sizeof(struct lock_stat)); - if (!new) - goto alloc_failed; - - new->addr = addr; - new->name = strdup(name); - if (!new->name) { - free(new); - goto alloc_failed; - } - - new->flags = flags; - new->wait_time_min = ULLONG_MAX; - - hlist_add_head(&new->hash_entry, entry); - return new; - -alloc_failed: - pr_err("memory allocation failed\n"); - return NULL; -} - -bool match_callstack_filter(struct machine *machine, u64 *callstack) -{ - struct map *kmap; - struct symbol *sym; - u64 ip; - const char *arch = perf_env__arch(machine->env); - - if (list_empty(&callstack_filters)) - return true; - - for (int i = 0; i < max_stack_depth; i++) { - struct callstack_filter *filter; - - /* - * In powerpc, the callchain saved by kernel always includes - * first three entries as the NIP (next instruction pointer), - * LR (link register), and the contents of LR save area in the - * second stack frame. In certain scenarios its possible to have - * invalid kernel instruction addresses in either LR or the second - * stack frame's LR. In that case, kernel will store that address as - * zero. - * - * The below check will continue to look into callstack, - * incase first or second callstack index entry has 0 - * address for powerpc. - */ - if (!callstack || (!callstack[i] && (strcmp(arch, "powerpc") || - (i != 1 && i != 2)))) - break; - - ip = callstack[i]; - sym = machine__find_kernel_symbol(machine, ip, &kmap); - if (sym == NULL) - continue; - - list_for_each_entry(filter, &callstack_filters, list) { - if (strstr(sym->name, filter->name)) - return true; - } - } - return false; -} - struct trace_lock_handler { /* it's used on CONFIG_LOCKDEP */ int (*acquire_event)(struct evsel *evsel, @@ -1165,7 +1058,7 @@ static int report_lock_contention_begin_event(struct evsel *evsel, if (callstack == NULL) return -ENOMEM; - if (!match_callstack_filter(machine, callstack)) { + if (!match_callstack_filter(machine, callstack, max_stack_depth)) { free(callstack); return 0; } @@ -1575,8 +1468,13 @@ static void sort_result(void) static const struct { unsigned int flags; - const char *str; - const char *name; + /* + * Name of the lock flags (access), with delimeter ':'. + * For example, rwsem:R of rwsem:W. + */ + const char *flags_name; + /* Name of the lock (type), for example, rwlock or rwsem. */ + const char *lock_name; } lock_type_table[] = { { 0, "semaphore", "semaphore" }, { LCB_F_SPIN, "spinlock", "spinlock" }, @@ -1595,24 +1493,24 @@ static const struct { { LCB_F_MUTEX | LCB_F_SPIN, "mutex:spin", "mutex-spin" }, }; -static const char *get_type_str(unsigned int flags) +static const char *get_type_flags_name(unsigned int flags) { - flags &= LCB_F_MAX_FLAGS - 1; + flags &= LCB_F_TYPE_MASK; for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { if (lock_type_table[i].flags == flags) - return lock_type_table[i].str; + return lock_type_table[i].flags_name; } return "unknown"; } -static const char *get_type_name(unsigned int flags) +static const char *get_type_lock_name(unsigned int flags) { - flags &= LCB_F_MAX_FLAGS - 1; + flags &= LCB_F_TYPE_MASK; for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { if (lock_type_table[i].flags == flags) - return lock_type_table[i].name; + return lock_type_table[i].lock_name; } return "unknown"; } @@ -1633,6 +1531,12 @@ static void lock_filter_finish(void) zfree(&filters.cgrps); filters.nr_cgrps = 0; + + for (int i = 0; i < filters.nr_slabs; i++) + free(filters.slabs[i]); + + zfree(&filters.slabs); + filters.nr_slabs = 0; } static void sort_contention_result(void) @@ -1719,7 +1623,7 @@ static void print_lock_stat_stdio(struct lock_contention *con, struct lock_stat switch (aggr_mode) { case LOCK_AGGR_CALLER: - fprintf(lock_output, " %10s %s\n", get_type_str(st->flags), st->name); + fprintf(lock_output, " %10s %s\n", get_type_flags_name(st->flags), st->name); break; case LOCK_AGGR_TASK: pid = st->addr; @@ -1729,7 +1633,7 @@ static void print_lock_stat_stdio(struct lock_contention *con, struct lock_stat break; case LOCK_AGGR_ADDR: fprintf(lock_output, " %016llx %s (%s)\n", (unsigned long long)st->addr, - st->name, get_type_name(st->flags)); + st->name, get_type_lock_name(st->flags)); break; case LOCK_AGGR_CGROUP: fprintf(lock_output, " %s\n", st->name); @@ -1770,7 +1674,7 @@ static void print_lock_stat_csv(struct lock_contention *con, struct lock_stat *s switch (aggr_mode) { case LOCK_AGGR_CALLER: - fprintf(lock_output, "%s%s %s", get_type_str(st->flags), sep, st->name); + fprintf(lock_output, "%s%s %s", get_type_flags_name(st->flags), sep, st->name); if (verbose <= 0) fprintf(lock_output, "\n"); break; @@ -1782,7 +1686,7 @@ static void print_lock_stat_csv(struct lock_contention *con, struct lock_stat *s break; case LOCK_AGGR_ADDR: fprintf(lock_output, "%llx%s %s%s %s\n", (unsigned long long)st->addr, sep, - st->name, sep, get_type_name(st->flags)); + st->name, sep, get_type_lock_name(st->flags)); break; case LOCK_AGGR_CGROUP: fprintf(lock_output, "%s\n",st->name); @@ -2137,7 +2041,8 @@ static int __cmd_contention(int argc, const char **argv) goto out_delete; } - if (lock_contention_prepare(&con) < 0) { + err = lock_contention_prepare(&con); + if (err < 0) { pr_err("lock contention BPF setup failed\n"); goto out_delete; } @@ -2158,10 +2063,14 @@ static int __cmd_contention(int argc, const char **argv) } } - if (setup_output_field(true, output_fields)) + err = setup_output_field(true, output_fields); + if (err) { + pr_err("Failed to setup output field\n"); goto out_delete; + } - if (select_key(true)) + err = select_key(true); + if (err) goto out_delete; if (symbol_conf.field_sep) { @@ -2345,10 +2254,10 @@ static int parse_lock_type(const struct option *opt __maybe_unused, const char * for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { bool found = false; - /* `tok` is `str` in `lock_type_table` if it contains ':'. */ + /* `tok` is a flags name if it contains ':'. */ if (strchr(tok, ':')) { for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { - if (!strcmp(lock_type_table[i].str, tok) && + if (!strcmp(lock_type_table[i].flags_name, tok) && add_lock_type(lock_type_table[i].flags)) { found = true; break; @@ -2365,11 +2274,14 @@ static int parse_lock_type(const struct option *opt __maybe_unused, const char * } /* - * Otherwise `tok` is `name` in `lock_type_table`. + * Otherwise `tok` is a lock name. * Single lock name could contain multiple flags. + * Replace alias `pcpu-sem` with actual name `percpu-rwsem. */ + if (!strcmp(tok, "pcpu-sem")) + tok = (char *)"percpu-rwsem"; for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { - if (!strcmp(lock_type_table[i].name, tok)) { + if (!strcmp(lock_type_table[i].lock_name, tok)) { if (add_lock_type(lock_type_table[i].flags)) { found = true; } else { @@ -2428,6 +2340,27 @@ static bool add_lock_sym(char *name) return true; } +static bool add_lock_slab(char *name) +{ + char **tmp; + char *sym = strdup(name); + + if (sym == NULL) { + pr_err("Memory allocation failure\n"); + return false; + } + + tmp = realloc(filters.slabs, (filters.nr_slabs + 1) * sizeof(*filters.slabs)); + if (tmp == NULL) { + pr_err("Memory allocation failure\n"); + return false; + } + + tmp[filters.nr_slabs++] = sym; + filters.slabs = tmp; + return true; +} + static int parse_lock_addr(const struct option *opt __maybe_unused, const char *str, int unset __maybe_unused) { @@ -2451,6 +2384,14 @@ static int parse_lock_addr(const struct option *opt __maybe_unused, const char * continue; } + if (*tok == '&') { + if (!add_lock_slab(tok + 1)) { + ret = -1; + break; + } + continue; + } + /* * At this moment, we don't have kernel symbols. Save the symbols * in a separate list and resolve them to addresses later. @@ -2465,34 +2406,6 @@ static int parse_lock_addr(const struct option *opt __maybe_unused, const char * return ret; } -static int parse_call_stack(const struct option *opt __maybe_unused, const char *str, - int unset __maybe_unused) -{ - char *s, *tmp, *tok; - int ret = 0; - - s = strdup(str); - if (s == NULL) - return -1; - - for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { - struct callstack_filter *entry; - - entry = malloc(sizeof(*entry) + strlen(tok) + 1); - if (entry == NULL) { - pr_err("Memory allocation failure\n"); - free(s); - return -1; - } - - strcpy(entry->name, tok); - list_add_tail(&entry->list, &callstack_filters); - } - - free(s); - return ret; -} - static int parse_output(const struct option *opt __maybe_unused, const char *str, int unset __maybe_unused) { diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 651188c1d825..99d5e1491a28 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -4,6 +4,7 @@ #include <sys/stat.h> #include <unistd.h> #include "builtin.h" +#include "perf.h" #include <subcmd/parse-options.h> #include "util/auxtrace.h" diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f83252472921..5db1aedf48df 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -860,7 +860,9 @@ static int record__auxtrace_init(struct record *rec) if (err) return err; - auxtrace_regroup_aux_output(rec->evlist); + err = auxtrace_parse_aux_action(rec->evlist); + if (err) + return err; return auxtrace_parse_filters(rec->evlist); } @@ -1748,10 +1750,8 @@ static void record__init_features(struct record *rec) if (rec->no_buildid) perf_header__clear_feat(&session->header, HEADER_BUILD_ID); -#ifdef HAVE_LIBTRACEEVENT if (!have_tracepoints(&rec->evlist->core.entries)) perf_header__clear_feat(&session->header, HEADER_TRACING_DATA); -#endif if (!rec->opts.branch_stack) perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index a5672749f781..19175fe9a8b1 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -348,11 +348,9 @@ static int process_read_event(const struct perf_tool *tool, struct report *rep = container_of(tool, struct report, tool); if (rep->show_threads) { - const char *name = evsel__name(evsel); int err = perf_read_values_add_value(&rep->show_threads_values, event->read.pid, event->read.tid, - evsel->core.idx, - name, + evsel, event->read.value); if (err) @@ -1555,12 +1553,12 @@ int cmd_report(int argc, const char **argv) input_name = "perf.data"; } +repeat: data.path = input_name; data.force = symbol_conf.force; symbol_conf.skip_empty = report.skip_empty; -repeat: perf_tool__init(&report.tool, ordered_events); report.tool.sample = process_sample_event; report.tool.mmap = perf_event__process_mmap; @@ -1721,22 +1719,24 @@ repeat: symbol_conf.annotate_data_sample = true; } - if (sort_order && strstr(sort_order, "ipc")) { - parse_options_usage(report_usage, options, "s", 1); - goto error; - } - - if (sort_order && strstr(sort_order, "symbol")) { - if (sort__mode == SORT_MODE__BRANCH) { - snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s", - sort_order, "ipc_lbr"); - report.symbol_ipc = true; - } else { - snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s", - sort_order, "ipc_null"); + if (last_key != K_SWITCH_INPUT_DATA) { + if (sort_order && strstr(sort_order, "ipc")) { + parse_options_usage(report_usage, options, "s", 1); + goto error; } - sort_order = sort_tmp; + if (sort_order && strstr(sort_order, "symbol")) { + if (sort__mode == SORT_MODE__BRANCH) { + snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s", + sort_order, "ipc_lbr"); + report.symbol_ipc = true; + } else { + snprintf(sort_tmp, sizeof(sort_tmp), "%s,%s", + sort_order, "ipc_null"); + } + + sort_order = sort_tmp; + } } if ((last_key != K_SWITCH_INPUT_DATA && last_key != K_RELOAD) && diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 7049c60ebf77..26ece6e9bfd1 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "builtin.h" +#include "perf.h" #include "perf-sys.h" #include "util/cpumap.h" diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 9e47905f75a6..33667b534634 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -85,15 +85,12 @@ static bool system_wide; static bool print_flags; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); -static struct perf_stat_config stat_config; static int max_blocks; static bool native_arch; static struct dlfilter *dlfilter; static int dlargc; static char **dlargv; -unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; - enum perf_output_field { PERF_OUTPUT_COMM = 1ULL << 0, PERF_OUTPUT_TID = 1ULL << 1, @@ -224,6 +221,10 @@ enum { OUTPUT_TYPE_MAX }; +// We need to refactor the evsel->priv use in in 'perf script' to allow for +// using that area, that is being used only in some cases. +#define OUTPUT_TYPE_UNSET -1 + /* default set to maintain compatibility with current format */ static struct { bool user_set; @@ -397,6 +398,14 @@ static inline int output_type(unsigned int type) return OUTPUT_TYPE_OTHER; } +static inline int evsel__output_type(struct evsel *evsel) +{ + if (evsel->script_output_type == OUTPUT_TYPE_UNSET) + evsel->script_output_type = output_type(evsel->core.attr.type); + + return evsel->script_output_type; +} + static bool output_set_by_user(void) { int j; @@ -421,13 +430,13 @@ static const char *output_field2str(enum perf_output_field field) return str; } -#define PRINT_FIELD(x) (output[output_type(attr->type)].fields & PERF_OUTPUT_##x) +#define PRINT_FIELD(x) (output[evsel__output_type(evsel)].fields & PERF_OUTPUT_##x) static int evsel__do_check_stype(struct evsel *evsel, u64 sample_type, const char *sample_msg, enum perf_output_field field, bool allow_user_set) { struct perf_event_attr *attr = &evsel->core.attr; - int type = output_type(attr->type); + int type = evsel__output_type(evsel); const char *evname; if (attr->sample_type & sample_type) @@ -461,7 +470,6 @@ static int evsel__check_stype(struct evsel *evsel, u64 sample_type, const char * static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) { - struct perf_event_attr *attr = &evsel->core.attr; bool allow_user_set; if (evsel__is_dummy_event(evsel)) @@ -578,9 +586,9 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return 0; } -static void set_print_ip_opts(struct perf_event_attr *attr) +static void evsel__set_print_ip_opts(struct evsel *evsel) { - unsigned int type = output_type(attr->type); + unsigned int type = evsel__output_type(evsel); output[type].print_ip_opts = 0; if (PRINT_FIELD(IP)) @@ -610,7 +618,7 @@ static struct evsel *find_first_output_type(struct evlist *evlist, evlist__for_each_entry(evlist, evsel) { if (evsel__is_dummy_event(evsel)) continue; - if (output_type(evsel->core.attr.type) == (int)type) + if (evsel__output_type(evsel) == (int)type) return evsel; } return NULL; @@ -652,7 +660,7 @@ static int perf_session__check_output_opt(struct perf_session *session) if (output[j].fields & PERF_OUTPUT_DSOFF) output[j].fields |= PERF_OUTPUT_DSO; - set_print_ip_opts(&evsel->core.attr); + evsel__set_print_ip_opts(evsel); tod |= output[j].fields & PERF_OUTPUT_TOD; } @@ -688,7 +696,7 @@ static int perf_session__check_output_opt(struct perf_session *session) output[j].fields |= PERF_OUTPUT_SYM; output[j].fields |= PERF_OUTPUT_SYMOFFSET; output[j].fields |= PERF_OUTPUT_DSO; - set_print_ip_opts(&evsel->core.attr); + evsel__set_print_ip_opts(evsel); goto out; } } @@ -792,7 +800,6 @@ static int perf_sample__fprintf_start(struct perf_script *script, struct evsel *evsel, u32 type, FILE *fp) { - struct perf_event_attr *attr = &evsel->core.attr; unsigned long secs; unsigned long long nsecs; int printed = 0; @@ -944,7 +951,7 @@ static int print_bstack_flags(FILE *fp, struct branch_entry *br) static int perf_sample__fprintf_brstack(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct branch_stack *br = sample->branch_stack; struct branch_entry *entries = perf_sample__branch_entries(sample); @@ -983,7 +990,7 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct branch_stack *br = sample->branch_stack; struct branch_entry *entries = perf_sample__branch_entries(sample); @@ -1021,7 +1028,7 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct branch_stack *br = sample->branch_stack; struct branch_entry *entries = perf_sample__branch_entries(sample); @@ -1188,7 +1195,7 @@ out: return ret; } -static int any_dump_insn(struct perf_event_attr *attr __maybe_unused, +static int any_dump_insn(struct evsel *evsel __maybe_unused, struct perf_insn *x, uint64_t ip, u8 *inbuf, int inlen, int *lenp, FILE *fp) @@ -1216,15 +1223,14 @@ static int add_padding(FILE *fp, int printed, int padding) static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en, struct perf_insn *x, u8 *inbuf, int len, int insn, FILE *fp, int *total_cycles, - struct perf_event_attr *attr, - struct thread *thread, struct evsel *evsel, + struct thread *thread, u64 br_cntr) { int ilen = 0; int printed = fprintf(fp, "\t%016" PRIx64 "\t", ip); - printed += add_padding(fp, any_dump_insn(attr, x, ip, inbuf, len, &ilen, fp), 30); + printed += add_padding(fp, any_dump_insn(evsel, x, ip, inbuf, len, &ilen, fp), 30); printed += fprintf(fp, "\t"); if (PRINT_FIELD(BRSTACKINSNLEN)) @@ -1280,7 +1286,7 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en, static int ip__fprintf_sym(uint64_t addr, struct thread *thread, u8 cpumode, int cpu, struct symbol **lastsym, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct addr_location al; int off, printed = 0, ret = 0; @@ -1356,10 +1362,10 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, machine, thread, &x.is64bit, &x.cpumode, false); if (len > 0) { printed += ip__fprintf_sym(entries[nr - 1].from, thread, - x.cpumode, x.cpu, &lastsym, attr, fp); + x.cpumode, x.cpu, &lastsym, evsel, fp); printed += ip__fprintf_jump(entries[nr - 1].from, &entries[nr - 1], &x, buffer, len, 0, fp, &total_cycles, - attr, thread, evsel, br_cntr); + evsel, thread, br_cntr); if (PRINT_FIELD(SRCCODE)) printed += print_srccode(thread, x.cpumode, entries[nr - 1].from); } @@ -1387,19 +1393,19 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, for (off = 0; off < (unsigned)len; off += ilen) { uint64_t ip = start + off; - printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp); + printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, evsel, fp); if (ip == end) { if (PRINT_FIELD(BRCNTR) && sample->branch_stack_cntr) br_cntr = sample->branch_stack_cntr[i]; printed += ip__fprintf_jump(ip, &entries[i], &x, buffer + off, len - off, ++insn, fp, - &total_cycles, attr, thread, evsel, br_cntr); + &total_cycles, evsel, thread, br_cntr); if (PRINT_FIELD(SRCCODE)) printed += print_srccode(thread, x.cpumode, ip); break; } else { ilen = 0; printed += fprintf(fp, "\t%016" PRIx64 "\t", ip); - printed += any_dump_insn(attr, &x, ip, buffer + off, len - off, &ilen, fp); + printed += any_dump_insn(evsel, &x, ip, buffer + off, len - off, &ilen, fp); if (PRINT_FIELD(BRSTACKINSNLEN)) printed += fprintf(fp, "\tilen: %d", ilen); printed += fprintf(fp, "\n"); @@ -1438,7 +1444,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, end = start + 128; } len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true); - printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, attr, fp); + printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, evsel, fp); if (len <= 0) { /* Print at least last IP if basic block did not work */ len = grab_bb(buffer, sample->ip, sample->ip, @@ -1447,7 +1453,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, goto out; ilen = 0; printed += fprintf(fp, "\t%016" PRIx64 "\t", sample->ip); - printed += any_dump_insn(attr, &x, sample->ip, buffer, len, &ilen, fp); + printed += any_dump_insn(evsel, &x, sample->ip, buffer, len, &ilen, fp); if (PRINT_FIELD(BRSTACKINSNLEN)) printed += fprintf(fp, "\tilen: %d", ilen); printed += fprintf(fp, "\n"); @@ -1458,7 +1464,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, for (off = 0; off <= end - start; off += ilen) { ilen = 0; printed += fprintf(fp, "\t%016" PRIx64 "\t", start + off); - printed += any_dump_insn(attr, &x, start + off, buffer + off, len - off, &ilen, fp); + printed += any_dump_insn(evsel, &x, start + off, buffer + off, len - off, &ilen, fp); if (PRINT_FIELD(BRSTACKINSNLEN)) printed += fprintf(fp, "\tilen: %d", ilen); printed += fprintf(fp, "\n"); @@ -1482,13 +1488,13 @@ out: static int perf_sample__fprintf_addr(struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { struct addr_location al; int printed = fprintf(fp, "%16" PRIx64, sample->addr); addr_location__init(&al); - if (!sample_addr_correlates_sym(attr)) + if (!sample_addr_correlates_sym(&evsel->core.attr)) goto out; thread__resolve(thread, &al, sample); @@ -1515,11 +1521,10 @@ static const char *resolve_branch_sym(struct perf_sample *sample, struct addr_location *addr_al, u64 *ip) { - struct perf_event_attr *attr = &evsel->core.attr; const char *name = NULL; if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) { - if (sample_addr_correlates_sym(attr)) { + if (sample_addr_correlates_sym(&evsel->core.attr)) { if (!addr_al->thread) thread__resolve(thread, addr_al, sample); if (addr_al->sym) @@ -1545,7 +1550,6 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, struct addr_location *addr_al, FILE *fp) { - struct perf_event_attr *attr = &evsel->core.attr; size_t depth = thread_stack__depth(thread, sample->cpu); const char *name = NULL; static int spacing; @@ -1589,19 +1593,6 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, return len + dlen; } -__weak void arch_fetch_insn(struct perf_sample *sample __maybe_unused, - struct thread *thread __maybe_unused, - struct machine *machine __maybe_unused) -{ -} - -void script_fetch_insn(struct perf_sample *sample, struct thread *thread, - struct machine *machine) -{ - if (sample->insn_len == 0 && native_arch) - arch_fetch_insn(sample, thread, machine); -} - static int perf_sample__fprintf_insn(struct perf_sample *sample, struct evsel *evsel, struct perf_event_attr *attr, @@ -1611,7 +1602,7 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample, { int printed = 0; - script_fetch_insn(sample, thread, machine); + script_fetch_insn(sample, thread, machine, native_arch); if (PRINT_FIELD(INSNLEN)) printed += fprintf(fp, " ilen: %d", sample->insn_len); @@ -1630,7 +1621,7 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample, } static int perf_sample__fprintf_ipc(struct perf_sample *sample, - struct perf_event_attr *attr, FILE *fp) + struct evsel *evsel, FILE *fp) { unsigned int ipc; @@ -1651,7 +1642,7 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, struct machine *machine, FILE *fp) { struct perf_event_attr *attr = &evsel->core.attr; - unsigned int type = output_type(attr->type); + unsigned int type = evsel__output_type(evsel); bool print_srcline_last = false; int printed = 0; @@ -1688,10 +1679,10 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, ((evsel->core.attr.sample_type & PERF_SAMPLE_ADDR) && !output[type].user_set)) { printed += fprintf(fp, " => "); - printed += perf_sample__fprintf_addr(sample, thread, attr, fp); + printed += perf_sample__fprintf_addr(sample, thread, evsel, fp); } - printed += perf_sample__fprintf_ipc(sample, attr, fp); + printed += perf_sample__fprintf_ipc(sample, evsel, fp); if (print_srcline_last) printed += map__fprintf_srcline(al->map, al->addr, "\n ", fp); @@ -1709,87 +1700,6 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample, return printed; } -static struct { - u32 flags; - const char *name; -} sample_flags[] = { - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "jcc"}, - {PERF_IP_FLAG_BRANCH, "jmp"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT, "int"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT, "iret"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET, "syscall"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET, "sysret"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "async"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_INTERRUPT, "hw int"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "tx abrt"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "tr strt"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMENTRY, "vmentry"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMEXIT, "vmexit"}, - {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_BRANCH_MISS, "br miss"}, - {0, NULL} -}; - -static const char *sample_flags_to_name(u32 flags) -{ - int i; - - for (i = 0; sample_flags[i].name ; i++) { - if (sample_flags[i].flags == flags) - return sample_flags[i].name; - } - - return NULL; -} - -int perf_sample__sprintf_flags(u32 flags, char *str, size_t sz) -{ - u32 xf = PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_INTR_DISABLE | - PERF_IP_FLAG_INTR_TOGGLE; - const char *chars = PERF_IP_FLAG_CHARS; - const size_t n = strlen(PERF_IP_FLAG_CHARS); - const char *name = NULL; - size_t i, pos = 0; - char xs[16] = {0}; - - if (flags & xf) - snprintf(xs, sizeof(xs), "(%s%s%s)", - flags & PERF_IP_FLAG_IN_TX ? "x" : "", - flags & PERF_IP_FLAG_INTR_DISABLE ? "D" : "", - flags & PERF_IP_FLAG_INTR_TOGGLE ? "t" : ""); - - name = sample_flags_to_name(flags & ~xf); - if (name) - return snprintf(str, sz, "%-15s%6s", name, xs); - - if (flags & PERF_IP_FLAG_TRACE_BEGIN) { - name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_BEGIN)); - if (name) - return snprintf(str, sz, "tr strt %-7s%6s", name, xs); - } - - if (flags & PERF_IP_FLAG_TRACE_END) { - name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_END)); - if (name) - return snprintf(str, sz, "tr end %-7s%6s", name, xs); - } - - for (i = 0; i < n; i++, flags >>= 1) { - if ((flags & 1) && pos < sz) - str[pos++] = chars[i]; - } - for (; i < 32; i++, flags >>= 1) { - if ((flags & 1) && pos < sz) - str[pos++] = '?'; - } - if (pos < sz) - str[pos] = 0; - - return pos; -} - static int perf_sample__fprintf_flags(u32 flags, FILE *fp) { char str[SAMPLE_FLAGS_BUF_SIZE]; @@ -2254,7 +2164,7 @@ static void process_event(struct perf_script *script, { struct thread *thread = al->thread; struct perf_event_attr *attr = &evsel->core.attr; - unsigned int type = output_type(attr->type); + unsigned int type = evsel__output_type(evsel); struct evsel_script *es = evsel->priv; FILE *fp = es->fp; char str[PAGE_SIZE_NAME_LEN]; @@ -2289,15 +2199,20 @@ static void process_event(struct perf_script *script, } #ifdef HAVE_LIBTRACEEVENT if (PRINT_FIELD(TRACE) && sample->raw_data) { - event_format__fprintf(evsel->tp_format, sample->cpu, - sample->raw_data, sample->raw_size, fp); + const struct tep_event *tp_format = evsel__tp_format(evsel); + + if (tp_format) { + event_format__fprintf(tp_format, sample->cpu, + sample->raw_data, sample->raw_size, + fp); + } } #endif if (attr->type == PERF_TYPE_SYNTH && PRINT_FIELD(SYNTH)) perf_sample__fprintf_synth(sample, evsel, fp); if (PRINT_FIELD(ADDR)) - perf_sample__fprintf_addr(sample, thread, attr, fp); + perf_sample__fprintf_addr(sample, thread, evsel, fp); if (PRINT_FIELD(DATA_SRC)) data_src__fprintf(sample->data_src, fp); @@ -2347,11 +2262,11 @@ static void process_event(struct perf_script *script, perf_sample__fprintf_uregs(sample, attr, arch, fp); if (PRINT_FIELD(BRSTACK)) - perf_sample__fprintf_brstack(sample, thread, attr, fp); + perf_sample__fprintf_brstack(sample, thread, evsel, fp); else if (PRINT_FIELD(BRSTACKSYM)) - perf_sample__fprintf_brstacksym(sample, thread, attr, fp); + perf_sample__fprintf_brstacksym(sample, thread, evsel, fp); else if (PRINT_FIELD(BRSTACKOFF)) - perf_sample__fprintf_brstackoff(sample, thread, attr, fp); + perf_sample__fprintf_brstackoff(sample, thread, evsel, fp); if (evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT)) perf_sample__fprintf_bpf_output(sample, fp); @@ -2366,7 +2281,7 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(CODE_PAGE_SIZE)) fprintf(fp, " %s", get_page_size_name(sample->code_page_size, str)); - perf_sample__fprintf_ipc(sample, attr, fp); + perf_sample__fprintf_ipc(sample, evsel, fp); fprintf(fp, "\n"); @@ -2599,14 +2514,14 @@ static int process_attr(const struct perf_tool *tool, union perf_event *event, sample_type & PERF_SAMPLE_BRANCH_STACK || (sample_type & PERF_SAMPLE_REGS_USER && sample_type & PERF_SAMPLE_STACK_USER))) { - int type = output_type(evsel->core.attr.type); + int type = evsel__output_type(evsel); if (!(output[type].user_unset_fields & PERF_OUTPUT_IP)) output[type].fields |= PERF_OUTPUT_IP; if (!(output[type].user_unset_fields & PERF_OUTPUT_SYM)) output[type].fields |= PERF_OUTPUT_SYM; } - set_print_ip_opts(&evsel->core.attr); + evsel__set_print_ip_opts(evsel); return 0; } @@ -2959,79 +2874,18 @@ static int __cmd_script(struct perf_script *script) return ret; } -struct script_spec { - struct list_head node; - struct scripting_ops *ops; - char spec[]; -}; - -static LIST_HEAD(script_specs); - -static struct script_spec *script_spec__new(const char *spec, - struct scripting_ops *ops) -{ - struct script_spec *s = malloc(sizeof(*s) + strlen(spec) + 1); - - if (s != NULL) { - strcpy(s->spec, spec); - s->ops = ops; - } - - return s; -} - -static void script_spec__add(struct script_spec *s) -{ - list_add_tail(&s->node, &script_specs); -} - -static struct script_spec *script_spec__find(const char *spec) +static int list_available_languages_cb(struct scripting_ops *ops, const char *spec) { - struct script_spec *s; - - list_for_each_entry(s, &script_specs, node) - if (strcasecmp(s->spec, spec) == 0) - return s; - return NULL; -} - -int script_spec_register(const char *spec, struct scripting_ops *ops) -{ - struct script_spec *s; - - s = script_spec__find(spec); - if (s) - return -1; - - s = script_spec__new(spec, ops); - if (!s) - return -1; - else - script_spec__add(s); - + fprintf(stderr, " %-42s [%s]\n", spec, ops->name); return 0; } -static struct scripting_ops *script_spec__lookup(const char *spec) -{ - struct script_spec *s = script_spec__find(spec); - if (!s) - return NULL; - - return s->ops; -} - static void list_available_languages(void) { - struct script_spec *s; - fprintf(stderr, "\n"); fprintf(stderr, "Scripting language extensions (used in " "perf script -s [spec:]script.[spec]):\n\n"); - - list_for_each_entry(s, &script_specs, node) - fprintf(stderr, " %-42s [%s]\n", s->spec, s->ops->name); - + script_spec__for_each(&list_available_languages_cb); fprintf(stderr, "\n"); } @@ -3523,144 +3377,6 @@ static void free_dlarg(void) free(dlargv); } -/* - * Some scripts specify the required events in their "xxx-record" file, - * this function will check if the events in perf.data match those - * mentioned in the "xxx-record". - * - * Fixme: All existing "xxx-record" are all in good formats "-e event ", - * which is covered well now. And new parsing code should be added to - * cover the future complex formats like event groups etc. - */ -static int check_ev_match(char *dir_name, char *scriptname, - struct perf_session *session) -{ - char filename[MAXPATHLEN], evname[128]; - char line[BUFSIZ], *p; - struct evsel *pos; - int match, len; - FILE *fp; - - scnprintf(filename, MAXPATHLEN, "%s/bin/%s-record", dir_name, scriptname); - - fp = fopen(filename, "r"); - if (!fp) - return -1; - - while (fgets(line, sizeof(line), fp)) { - p = skip_spaces(line); - if (*p == '#') - continue; - - while (strlen(p)) { - p = strstr(p, "-e"); - if (!p) - break; - - p += 2; - p = skip_spaces(p); - len = strcspn(p, " \t"); - if (!len) - break; - - snprintf(evname, len + 1, "%s", p); - - match = 0; - evlist__for_each_entry(session->evlist, pos) { - if (evsel__name_is(pos, evname)) { - match = 1; - break; - } - } - - if (!match) { - fclose(fp); - return -1; - } - } - } - - fclose(fp); - return 0; -} - -/* - * Return -1 if none is found, otherwise the actual scripts number. - * - * Currently the only user of this function is the script browser, which - * will list all statically runnable scripts, select one, execute it and - * show the output in a perf browser. - */ -int find_scripts(char **scripts_array, char **scripts_path_array, int num, - int pathlen) -{ - struct dirent *script_dirent, *lang_dirent; - char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; - DIR *scripts_dir, *lang_dir; - struct perf_session *session; - struct perf_data data = { - .path = input_name, - .mode = PERF_DATA_MODE_READ, - }; - char *temp; - int i = 0; - - session = perf_session__new(&data, NULL); - if (IS_ERR(session)) - return PTR_ERR(session); - - snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); - - scripts_dir = opendir(scripts_path); - if (!scripts_dir) { - perf_session__delete(session); - return -1; - } - - for_each_lang(scripts_path, scripts_dir, lang_dirent) { - scnprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, - lang_dirent->d_name); -#ifndef HAVE_LIBPERL_SUPPORT - if (strstr(lang_path, "perl")) - continue; -#endif -#ifndef HAVE_LIBPYTHON_SUPPORT - if (strstr(lang_path, "python")) - continue; -#endif - - lang_dir = opendir(lang_path); - if (!lang_dir) - continue; - - for_each_script(lang_path, lang_dir, script_dirent) { - /* Skip those real time scripts: xxxtop.p[yl] */ - if (strstr(script_dirent->d_name, "top.")) - continue; - if (i >= num) - break; - snprintf(scripts_path_array[i], pathlen, "%s/%s", - lang_path, - script_dirent->d_name); - temp = strchr(script_dirent->d_name, '.'); - snprintf(scripts_array[i], - (temp - script_dirent->d_name) + 1, - "%s", script_dirent->d_name); - - if (check_ev_match(lang_path, - scripts_array[i], session)) - continue; - - i++; - } - closedir(lang_dir); - } - - closedir(scripts_dir); - perf_session__delete(session); - return i; -} - static char *get_script_path(const char *script_root, const char *suffix) { struct dirent *script_dirent, *lang_dirent; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index fdf5172646a5..68ea7589c143 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -97,7 +97,7 @@ #include <internal/threadmap.h> #define DEFAULT_SEPARATOR " " -#define FREEZE_ON_SMI_PATH "devices/cpu/freeze_on_smi" +#define FREEZE_ON_SMI_PATH "bus/event_source/devices/cpu/freeze_on_smi" static void print_counters(struct timespec *ts, int argc, const char **argv); @@ -112,8 +112,6 @@ static struct target target = { .uid = UINT_MAX, }; -#define METRIC_ONLY_LEN 20 - static volatile sig_atomic_t child_pid = -1; static int detailed_run = 0; static bool transaction_run; @@ -151,21 +149,6 @@ static struct perf_stat perf_stat; static volatile sig_atomic_t done = 0; -static struct perf_stat_config stat_config = { - .aggr_mode = AGGR_GLOBAL, - .aggr_level = MAX_CACHE_LVL + 1, - .scale = true, - .unit_width = 4, /* strlen("unit") */ - .run_count = 1, - .metric_only_len = METRIC_ONLY_LEN, - .walltime_nsecs_stats = &walltime_nsecs_stats, - .ru_stats = &ru_stats, - .big_num = true, - .ctl_fd = -1, - .ctl_fd_ack = -1, - .iostat_run = false, -}; - /* Options set from the command line. */ struct opt_aggr_mode { bool node, socket, die, cluster, cache, core, thread, no_aggr; @@ -1071,16 +1054,6 @@ static void sig_atexit(void) kill(getpid(), signr); } -void perf_stat__set_big_num(int set) -{ - stat_config.big_num = (set != 0); -} - -void perf_stat__set_no_csv_summary(int set) -{ - stat_config.no_csv_summary = (set != 0); -} - static int stat__set_big_num(const struct option *opt __maybe_unused, const char *s __maybe_unused, int unset) { diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index ca3e8eca6610..4fd31d29b2ab 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -267,9 +267,9 @@ static void perf_top__show_details(struct perf_top *top) if (top->evlist->enabled) { if (top->zero) - symbol__annotate_zero_histogram(symbol, top->sym_evsel->core.idx); + symbol__annotate_zero_histogram(symbol, top->sym_evsel); else - symbol__annotate_decay_histogram(symbol, top->sym_evsel->core.idx); + symbol__annotate_decay_histogram(symbol, top->sym_evsel); } if (more != 0) printf("%d lines not displayed, maybe increase display entries [e]\n", more); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 2756c4f5b5da..d466447ae928 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -389,7 +389,12 @@ static struct syscall_arg_fmt *evsel__syscall_arg_fmt(struct evsel *evsel) } if (et->fmt == NULL) { - et->fmt = calloc(evsel->tp_format->format.nr_fields, sizeof(struct syscall_arg_fmt)); + const struct tep_event *tp_format = evsel__tp_format(evsel); + + if (tp_format == NULL) + goto out_delete; + + et->fmt = calloc(tp_format->format.nr_fields, sizeof(struct syscall_arg_fmt)); if (et->fmt == NULL) goto out_delete; } @@ -1108,7 +1113,6 @@ static bool syscall_arg__strtoul_btf_type(char *bf __maybe_unused, size_t size _ .strtoul = STUL_STRARRAY_FLAGS, \ .parm = &strarray__##array, } -#include "trace/beauty/arch_errno_names.c" #include "trace/beauty/eventfd.c" #include "trace/beauty/futex_op.c" #include "trace/beauty/futex_val3.c" @@ -2069,30 +2073,11 @@ static int trace__read_syscall_info(struct trace *trace, int id) const char *name = syscalltbl__name(trace->sctbl, id); int err; -#ifdef HAVE_SYSCALL_TABLE_SUPPORT if (trace->syscalls.table == NULL) { trace->syscalls.table = calloc(trace->sctbl->syscalls.max_id + 1, sizeof(*sc)); if (trace->syscalls.table == NULL) return -ENOMEM; } -#else - if (id > trace->sctbl->syscalls.max_id || (id == 0 && trace->syscalls.table == NULL)) { - // When using libaudit we don't know beforehand what is the max syscall id - struct syscall *table = realloc(trace->syscalls.table, (id + 1) * sizeof(*sc)); - - if (table == NULL) - return -ENOMEM; - - // Need to memset from offset 0 and +1 members if brand new - if (trace->syscalls.table == NULL) - memset(table, 0, (id + 1) * sizeof(*sc)); - else - memset(table + trace->sctbl->syscalls.max_id + 1, 0, (id - trace->sctbl->syscalls.max_id) * sizeof(*sc)); - - trace->syscalls.table = table; - trace->sctbl->syscalls.max_id = id; - } -#endif sc = trace->syscalls.table + id; if (sc->nonexistent) return -EEXIST; @@ -2158,8 +2143,12 @@ static int evsel__init_tp_arg_scnprintf(struct evsel *evsel, bool *use_btf) struct syscall_arg_fmt *fmt = evsel__syscall_arg_fmt(evsel); if (fmt != NULL) { - syscall_arg_fmt__init_array(fmt, evsel->tp_format->format.fields, use_btf); - return 0; + const struct tep_event *tp_format = evsel__tp_format(evsel); + + if (tp_format) { + syscall_arg_fmt__init_array(fmt, tp_format->format.fields, use_btf); + return 0; + } } return -ENOMEM; @@ -2443,18 +2432,7 @@ static struct syscall *trace__syscall_info(struct trace *trace, err = -EINVAL; -#ifdef HAVE_SYSCALL_TABLE_SUPPORT if (id > trace->sctbl->syscalls.max_id) { -#else - if (id >= trace->sctbl->syscalls.max_id) { - /* - * With libaudit we don't know beforehand what is the max_id, - * so we let trace__read_syscall_info() figure that out as we - * go on reading syscalls. - */ - err = trace__read_syscall_info(trace, id); - if (err) -#endif goto out_cant_read; } @@ -2585,7 +2563,6 @@ static int trace__fprintf_sample(struct trace *trace, struct evsel *evsel, static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, int raw_augmented_args_size) { - void *augmented_args = NULL; /* * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter * and there we get all 6 syscall args plus the tracepoint common fields @@ -2603,10 +2580,24 @@ static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sam int args_size = raw_augmented_args_size ?: sc->args_size; *augmented_args_size = sample->raw_size - args_size; - if (*augmented_args_size > 0) - augmented_args = sample->raw_data + args_size; + if (*augmented_args_size > 0) { + static uintptr_t argbuf[1024]; /* assuming single-threaded */ + + if ((size_t)(*augmented_args_size) > sizeof(argbuf)) + return NULL; + + /* + * The perf ring-buffer is 8-byte aligned but sample->raw_data + * is not because it's preceded by u32 size. Later, beautifier + * will use the augmented args with stricter alignments like in + * some struct. To make sure it's aligned, let's copy the args + * into a static buffer as it's single-threaded for now. + */ + memcpy(argbuf, sample->raw_data + args_size, *augmented_args_size); - return augmented_args; + return argbuf; + } + return NULL; } static void syscall__exit(struct syscall *sc) @@ -3031,7 +3022,8 @@ static size_t trace__fprintf_tp_fields(struct trace *trace, struct evsel *evsel, { char bf[2048]; size_t size = sizeof(bf); - struct tep_format_field *field = evsel->tp_format->format.fields; + const struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_format_field *field = tp_format ? tp_format->format.fields : NULL; struct syscall_arg_fmt *arg = __evsel__syscall_arg_fmt(evsel); size_t printed = 0, btf_printed; unsigned long val; @@ -3149,11 +3141,13 @@ static int trace__event_handler(struct trace *trace, struct evsel *evsel, if (evsel__is_bpf_output(evsel)) { bpf_output__fprintf(trace, sample); - } else if (evsel->tp_format) { - if (strncmp(evsel->tp_format->name, "sys_enter_", 10) || - trace__fprintf_sys_enter(trace, evsel, sample)) { + } else { + const struct tep_event *tp_format = evsel__tp_format(evsel); + + if (tp_format && (strncmp(tp_format->name, "sys_enter_", 10) || + trace__fprintf_sys_enter(trace, evsel, sample))) { if (trace->libtraceevent_print) { - event_format__fprintf(evsel->tp_format, sample->cpu, + event_format__fprintf(tp_format, sample->cpu, sample->raw_data, sample->raw_size, trace->output); } else { @@ -4081,17 +4075,23 @@ static int ordered_events__deliver_event(struct ordered_events *oe, static struct syscall_arg_fmt *evsel__find_syscall_arg_fmt_by_name(struct evsel *evsel, char *arg, char **type) { - struct tep_format_field *field; struct syscall_arg_fmt *fmt = __evsel__syscall_arg_fmt(evsel); + const struct tep_event *tp_format; - if (evsel->tp_format == NULL || fmt == NULL) + if (!fmt) return NULL; - for (field = evsel->tp_format->format.fields; field; field = field->next, ++fmt) + tp_format = evsel__tp_format(evsel); + if (!tp_format) + return NULL; + + for (const struct tep_format_field *field = tp_format->format.fields; field; + field = field->next, ++fmt) { if (strcmp(field->name, arg) == 0) { *type = field->type; return fmt; } + } return NULL; } @@ -4847,13 +4847,18 @@ static void evsel__set_syscall_arg_fmt(struct evsel *evsel, const char *name) const struct syscall_fmt *scfmt = syscall_fmt__find(name); if (scfmt) { - int skip = 0; + const struct tep_event *tp_format = evsel__tp_format(evsel); - if (strcmp(evsel->tp_format->format.fields->name, "__syscall_nr") == 0 || - strcmp(evsel->tp_format->format.fields->name, "nr") == 0) - ++skip; + if (tp_format) { + int skip = 0; - memcpy(fmt + skip, scfmt->arg, (evsel->tp_format->format.nr_fields - skip) * sizeof(*fmt)); + if (strcmp(tp_format->format.fields->name, "__syscall_nr") == 0 || + strcmp(tp_format->format.fields->name, "nr") == 0) + ++skip; + + memcpy(fmt + skip, scfmt->arg, + (tp_format->format.nr_fields - skip) * sizeof(*fmt)); + } } } } @@ -4863,10 +4868,16 @@ static int evlist__set_syscall_tp_fields(struct evlist *evlist, bool *use_btf) struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->priv || !evsel->tp_format) + const struct tep_event *tp_format; + + if (evsel->priv) + continue; + + tp_format = evsel__tp_format(evsel); + if (!tp_format) continue; - if (strcmp(evsel->tp_format->system, "syscalls")) { + if (strcmp(tp_format->system, "syscalls")) { evsel__init_tp_arg_scnprintf(evsel, use_btf); continue; } @@ -4874,20 +4885,24 @@ static int evlist__set_syscall_tp_fields(struct evlist *evlist, bool *use_btf) if (evsel__init_syscall_tp(evsel)) return -1; - if (!strncmp(evsel->tp_format->name, "sys_enter_", 10)) { + if (!strncmp(tp_format->name, "sys_enter_", 10)) { struct syscall_tp *sc = __evsel__syscall_tp(evsel); if (__tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64))) return -1; - evsel__set_syscall_arg_fmt(evsel, evsel->tp_format->name + sizeof("sys_enter_") - 1); - } else if (!strncmp(evsel->tp_format->name, "sys_exit_", 9)) { + evsel__set_syscall_arg_fmt(evsel, + tp_format->name + sizeof("sys_enter_") - 1); + } else if (!strncmp(tp_format->name, "sys_exit_", 9)) { struct syscall_tp *sc = __evsel__syscall_tp(evsel); - if (__tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap)) + if (__tp_field__init_uint(&sc->ret, sizeof(u64), + sc->id.offset + sizeof(u64), + evsel->needs_swap)) return -1; - evsel__set_syscall_arg_fmt(evsel, evsel->tp_format->name + sizeof("sys_exit_") - 1); + evsel__set_syscall_arg_fmt(evsel, + tp_format->name + sizeof("sys_exit_") - 1); } } diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 94f4b3769bf7..a07e93c53848 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -2,10 +2,6 @@ #ifndef BUILTIN_H #define BUILTIN_H -#include <stddef.h> -#include <linux/compiler.h> -#include <tools/config.h> - struct feature_status { const char *name; const char *macro; @@ -56,6 +52,4 @@ int cmd_ftrace(int argc, const char **argv); int cmd_daemon(int argc, const char **argv); int cmd_kwork(int argc, const char **argv); -int find_scripts(char **scripts_array, char **scripts_path_array, int num, - int pathlen); #endif diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index a05c1c105c51..d3c6e10dce73 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -71,6 +71,7 @@ FILES=( "include/uapi/asm-generic/ioctls.h" "include/uapi/asm-generic/mman-common.h" "include/uapi/asm-generic/unistd.h" + "scripts/syscall.tbl" ) declare -a SYNC_CHECK_FILES @@ -201,6 +202,14 @@ check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscall check_2 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl check_2 tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl check_2 tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl +check_2 tools/perf/arch/arm/entry/syscalls/syscall.tbl arch/arm/tools/syscall.tbl +check_2 tools/perf/arch/sh/entry/syscalls/syscall.tbl arch/sh/kernel/syscalls/syscall.tbl +check_2 tools/perf/arch/sparc/entry/syscalls/syscall.tbl arch/sparc/kernel/syscalls/syscall.tbl +check_2 tools/perf/arch/xtensa/entry/syscalls/syscall.tbl arch/xtensa/kernel/syscalls/syscall.tbl +check_2 tools/perf/arch/alpha/entry/syscalls/syscall.tbl arch/alpha/entry/syscalls/syscall.tbl +check_2 tools/perf/arch/parisc/entry/syscalls/syscall.tbl arch/parisc/entry/syscalls/syscall.tbl +check_2 tools/perf/arch/arm64/entry/syscalls/syscall_32.tbl arch/arm64/entry/syscalls/syscall_32.tbl +check_2 tools/perf/arch/arm64/entry/syscalls/syscall_64.tbl arch/arm64/entry/syscalls/syscall_64.tbl for i in "${BEAUTY_FILES[@]}" do diff --git a/tools/perf/perf.c b/tools/perf/perf.c index a2987f2cfe1a..f0617cc41f5f 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -84,7 +84,7 @@ static struct cmd_struct commands[] = { #endif { "kvm", cmd_kvm, 0 }, { "test", cmd_test, 0 }, -#if defined(HAVE_LIBTRACEEVENT) && (defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)) +#if defined(HAVE_LIBTRACEEVENT) { "trace", cmd_trace, 0 }, #endif { "inject", cmd_inject, 0 }, @@ -514,10 +514,6 @@ int main(int argc, const char **argv) fprintf(stderr, "trace command not available: missing libtraceevent devel package at build time.\n"); goto out; -#elif !defined(HAVE_LIBAUDIT_SUPPORT) && !defined(HAVE_SYSCALL_TABLE_SUPPORT) - fprintf(stderr, - "trace command not available: missing audit-libs devel package at build time.\n"); - goto out; #else setup_path(); argv[0] = "trace"; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index c004dd4e65a3..3cb40965549f 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -3,7 +3,7 @@ #define _PERF_PERF_H #ifndef MAX_NR_CPUS -#define MAX_NR_CPUS 2048 +#define MAX_NR_CPUS 4096 #endif enum perf_affinity { diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json index c5d1d22bd034..5228f94a793f 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json @@ -229,19 +229,19 @@ }, { "MetricName": "slots_lost_misspeculation_fraction", - "MetricExpr": "(OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots)", + "MetricExpr": "100 * (OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots)", "BriefDescription": "Fraction of slots lost due to misspeculation", "DefaultMetricgroupName": "TopdownL1", "MetricGroup": "Default;TopdownL1", - "ScaleUnit": "100percent of slots" + "ScaleUnit": "1percent of slots" }, { "MetricName": "retired_fraction", - "MetricExpr": "OP_RETIRED / (CPU_CYCLES * #slots)", + "MetricExpr": "100 * OP_RETIRED / (CPU_CYCLES * #slots)", "BriefDescription": "Fraction of slots retiring, useful work", "DefaultMetricgroupName": "TopdownL1", "MetricGroup": "Default;TopdownL1", - "ScaleUnit": "100percent of slots" + "ScaleUnit": "1percent of slots" }, { "MetricName": "backend_core", @@ -266,7 +266,7 @@ }, { "MetricName": "frontend_bandwidth", - "MetricExpr": "frontend_bound - frontend_latency", + "MetricExpr": "frontend_bound - 100 * frontend_latency", "BriefDescription": "Fraction of slots the CPU did not dispatch at full bandwidth - able to dispatch partial slots only (1, 2, or 3 uops)", "MetricGroup": "TopdownL2", "ScaleUnit": "1percent of slots" diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json index 4404b8e91690..7126fbf292e0 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/exception.json @@ -5,7 +5,7 @@ }, { "ArchStdEvent": "EXC_RETURN", - "PublicDescription": "Counts any architecturally executed exception return instructions. Eg: AArch64: ERET" + "PublicDescription": "Counts any architecturally executed exception return instructions. For example: AArch64: ERET" }, { "ArchStdEvent": "EXC_UNDEF", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json index 428810f855b8..c5dcdcf43c58 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/general.json @@ -5,6 +5,6 @@ }, { "ArchStdEvent": "CNT_CYCLES", - "PublicDescription": "Counts constant frequency cycles" + "PublicDescription": "Increments at a constant frequency equal to the rate of increment of the System Counter, CNTPCT_EL0." } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json index da7c129f2569..799d106d5173 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l1d_cache.json @@ -1,11 +1,11 @@ [ { "ArchStdEvent": "L1D_CACHE_REFILL", - "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load or store operations that missed in the level 1 data cache. This event only counts one event per cache line. This event does not count cache line allocations from preload instructions or from hardware cache prefetching." + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load or store operations that missed in the level 1 data cache. This event only counts one event per cache line." }, { "ArchStdEvent": "L1D_CACHE", - "PublicDescription": "Counts level 1 data cache accesses from any load/store operations. Atomic operations that resolve in the CPUs caches (near atomic operations) count as both a write access and read access. Each access to a cache line is counted including the multiple accesses caused by single instructions such as LDM or STM. Each access to other level 1 data or unified memory structures, for example refill buffers, write buffers, and write-back buffers, are also counted." + "PublicDescription": "Counts level 1 data cache accesses from any load/store operations. Atomic operations that resolve in the CPUs caches (near atomic operations) counts as both a write access and read access. Each access to a cache line is counted including the multiple accesses caused by single instructions such as LDM or STM. Each access to other level 1 data or unified memory structures, for example refill buffers, write buffers, and write-back buffers, are also counted." }, { "ArchStdEvent": "L1D_CACHE_WB", @@ -17,7 +17,7 @@ }, { "ArchStdEvent": "L1D_CACHE_RD", - "PublicDescription": "Counts level 1 data cache accesses from any load operation. Atomic load operations that resolve in the CPUs caches count as both a write access and read access." + "PublicDescription": "Counts level 1 data cache accesses from any load operation. Atomic load operations that resolve in the CPUs caches counts as both a write access and read access." }, { "ArchStdEvent": "L1D_CACHE_WR", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json index 0e31d0daf88b..ed8291ab9737 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l2_cache.json @@ -1,11 +1,11 @@ [ { "ArchStdEvent": "L2D_CACHE", - "PublicDescription": "Counts level 2 cache accesses. level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the first level caches or translation resolutions due to accesses. This event also counts write back of dirty data from level 1 data cache to the L2 cache." + "PublicDescription": "Counts accesses to the level 2 cache due to data accesses. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the first level data cache or translation resolutions due to accesses. This event also counts write back of dirty data from level 1 data cache to the L2 cache." }, { "ArchStdEvent": "L2D_CACHE_REFILL", - "PublicDescription": "Counts cache line refills into the level 2 cache. level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 caches or translation resolutions due to accesses." + "PublicDescription": "Counts cache line refills into the level 2 cache. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 data cache or translation resolutions due to accesses." }, { "ArchStdEvent": "L2D_CACHE_WB", @@ -13,23 +13,23 @@ }, { "ArchStdEvent": "L2D_CACHE_ALLOCATE", - "PublicDescription": "TBD" + "PublicDescription": "Counts level 2 cache line allocates that do not fetch data from outside the level 2 data or unified cache." }, { "ArchStdEvent": "L2D_CACHE_RD", - "PublicDescription": "Counts level 2 cache accesses due to memory read operations. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + "PublicDescription": "Counts level 2 data cache accesses due to memory read operations. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." }, { "ArchStdEvent": "L2D_CACHE_WR", - "PublicDescription": "Counts level 2 cache accesses due to memory write operations. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + "PublicDescription": "Counts level 2 cache accesses due to memory write operations. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." }, { "ArchStdEvent": "L2D_CACHE_REFILL_RD", - "PublicDescription": "Counts refills for memory accesses due to memory read operation counted by L2D_CACHE_RD. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + "PublicDescription": "Counts refills for memory accesses due to memory read operation counted by L2D_CACHE_RD. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." }, { "ArchStdEvent": "L2D_CACHE_REFILL_WR", - "PublicDescription": "Counts refills for memory accesses due to memory write operation counted by L2D_CACHE_WR. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + "PublicDescription": "Counts refills for memory accesses due to memory write operation counted by L2D_CACHE_WR. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses." }, { "ArchStdEvent": "L2D_CACHE_WB_VICTIM", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json index 45bfba532df7..4a2e72fc5ada 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/l3_cache.json @@ -9,11 +9,11 @@ }, { "ArchStdEvent": "L3D_CACHE", - "PublicDescription": "Counts level 3 cache accesses. level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses." + "PublicDescription": "Counts level 3 cache accesses. Level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses." }, { "ArchStdEvent": "L3D_CACHE_RD", - "PublicDescription": "TBD" + "PublicDescription": "Counts level 3 cache accesses caused by any memory read operation. Level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses." }, { "ArchStdEvent": "L3D_CACHE_LMISS_RD", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json index bb712d57d58a..fd5a2e0099b8 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/ll_cache.json @@ -1,10 +1,10 @@ [ { "ArchStdEvent": "LL_CACHE_RD", - "PublicDescription": "Counts read transactions that were returned from outside the core cluster. This event counts when the system register CPUECTLR.EXTLLC bit is set. This event counts read transactions returned from outside the core if those transactions are either hit in the system level cache or missed in the SLC and are returned from any other external sources." + "PublicDescription": "Counts read transactions that were returned from outside the core cluster. This event counts for external last level cache when the system register CPUECTLR.EXTLLC bit is set, otherwise it counts for the L3 cache. This event counts read transactions returned from outside the core if those transactions are either hit in the system level cache or missed in the SLC and are returned from any other external sources." }, { "ArchStdEvent": "LL_CACHE_MISS_RD", - "PublicDescription": "Counts read transactions that were returned from outside the core cluster but missed in the system level cache. This event counts when the system register CPUECTLR.EXTLLC bit is set. This event counts read transactions returned from outside the core if those transactions are missed in the System level Cache. The data source of the transaction is indicated by a field in the CHI transaction returning to the CPU. This event does not count reads caused by cache maintenance operations." + "PublicDescription": "Counts read transactions that were returned from outside the core cluster but missed in the system level cache. This event counts for external last level cache when the system register CPUECTLR.EXTLLC bit is set, otherwise it counts for L3 cache. This event counts read transactions returned from outside the core if those transactions are missed in the System level Cache. The data source of the transaction is indicated by a field in the CHI transaction returning to the CPU. This event does not count reads caused by cache maintenance operations." } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json index 106a97f8b2e7..bb3491012a8f 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/memory.json @@ -33,7 +33,7 @@ }, { "ArchStdEvent": "MEM_ACCESS_CHECKED", - "PublicDescription": "Counts the number of memory read and write accesses in a cycle that are tag checked by the Memory Tagging Extension (MTE)." + "PublicDescription": "Counts the number of memory read and write accesses counted by MEM_ACCESS that are tag checked by the Memory Tagging Extension (MTE). This event is implemented as the sum of MEM_ACCESS_CHECKED_RD and MEM_ACCESS_CHECKED_WR" }, { "ArchStdEvent": "MEM_ACCESS_CHECKED_RD", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json index 5f449270b448..97d352f94323 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/metrics.json @@ -5,7 +5,7 @@ }, { "MetricName": "backend_stalled_cycles", - "MetricExpr": "((STALL_BACKEND / CPU_CYCLES) * 100)", + "MetricExpr": "STALL_BACKEND / CPU_CYCLES * 100", "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the backend unit of the processor.", "MetricGroup": "Cycle_Accounting", "ScaleUnit": "1percent of cycles" @@ -16,45 +16,45 @@ }, { "MetricName": "branch_misprediction_ratio", - "MetricExpr": "(BR_MIS_PRED_RETIRED / BR_RETIRED)", + "MetricExpr": "BR_MIS_PRED_RETIRED / BR_RETIRED", "BriefDescription": "This metric measures the ratio of branches mispredicted to the total number of branches architecturally executed. This gives an indication of the effectiveness of the branch prediction unit.", "MetricGroup": "Miss_Ratio;Branch_Effectiveness", - "ScaleUnit": "1per branch" + "ScaleUnit": "100percent of branches" }, { "MetricName": "branch_mpki", - "MetricExpr": "((BR_MIS_PRED_RETIRED / INST_RETIRED) * 1000)", + "MetricExpr": "BR_MIS_PRED_RETIRED / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of branch mispredictions per thousand instructions executed.", "MetricGroup": "MPKI;Branch_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "branch_percentage", - "MetricExpr": "(((BR_IMMED_SPEC + BR_INDIRECT_SPEC) / INST_SPEC) * 100)", + "MetricExpr": "(BR_IMMED_SPEC + BR_INDIRECT_SPEC) / INST_SPEC * 100", "BriefDescription": "This metric measures branch operations as a percentage of operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" }, { "MetricName": "crypto_percentage", - "MetricExpr": "((CRYPTO_SPEC / INST_SPEC) * 100)", + "MetricExpr": "CRYPTO_SPEC / INST_SPEC * 100", "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" }, { "MetricName": "dtlb_mpki", - "MetricExpr": "((DTLB_WALK / INST_RETIRED) * 1000)", + "MetricExpr": "DTLB_WALK / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of data TLB Walks per thousand instructions executed.", "MetricGroup": "MPKI;DTLB_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "dtlb_walk_ratio", - "MetricExpr": "(DTLB_WALK / L1D_TLB)", + "MetricExpr": "DTLB_WALK / L1D_TLB", "BriefDescription": "This metric measures the ratio of data TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.", "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", - "ScaleUnit": "1per TLB access" + "ScaleUnit": "100percent of TLB accesses" }, { "ArchStdEvent": "frontend_bound", @@ -62,147 +62,147 @@ }, { "MetricName": "frontend_stalled_cycles", - "MetricExpr": "((STALL_FRONTEND / CPU_CYCLES) * 100)", + "MetricExpr": "STALL_FRONTEND / CPU_CYCLES * 100", "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the frontend unit of the processor.", "MetricGroup": "Cycle_Accounting", "ScaleUnit": "1percent of cycles" }, { "MetricName": "integer_dp_percentage", - "MetricExpr": "((DP_SPEC / INST_SPEC) * 100)", + "MetricExpr": "DP_SPEC / INST_SPEC * 100", "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" }, { "MetricName": "ipc", - "MetricExpr": "(INST_RETIRED / CPU_CYCLES)", + "MetricExpr": "INST_RETIRED / CPU_CYCLES", "BriefDescription": "This metric measures the number of instructions retired per cycle.", "MetricGroup": "General", "ScaleUnit": "1per cycle" }, { "MetricName": "itlb_mpki", - "MetricExpr": "((ITLB_WALK / INST_RETIRED) * 1000)", + "MetricExpr": "ITLB_WALK / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of instruction TLB Walks per thousand instructions executed.", "MetricGroup": "MPKI;ITLB_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "itlb_walk_ratio", - "MetricExpr": "(ITLB_WALK / L1I_TLB)", + "MetricExpr": "ITLB_WALK / L1I_TLB", "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.", "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", - "ScaleUnit": "1per TLB access" + "ScaleUnit": "100percent of TLB accesses" }, { "MetricName": "l1d_cache_miss_ratio", - "MetricExpr": "(L1D_CACHE_REFILL / L1D_CACHE)", + "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE", "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.", "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness", - "ScaleUnit": "1per cache access" + "ScaleUnit": "100percent of cache accesses" }, { "MetricName": "l1d_cache_mpki", - "MetricExpr": "((L1D_CACHE_REFILL / INST_RETIRED) * 1000)", + "MetricExpr": "L1D_CACHE_REFILL / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of level 1 data cache accesses missed per thousand instructions executed.", "MetricGroup": "MPKI;L1D_Cache_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "l1d_tlb_miss_ratio", - "MetricExpr": "(L1D_TLB_REFILL / L1D_TLB)", + "MetricExpr": "L1D_TLB_REFILL / L1D_TLB", "BriefDescription": "This metric measures the ratio of level 1 data TLB accesses missed to the total number of level 1 data TLB accesses. This gives an indication of the effectiveness of the level 1 data TLB.", "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", - "ScaleUnit": "1per TLB access" + "ScaleUnit": "100percent of TLB accesses" }, { "MetricName": "l1d_tlb_mpki", - "MetricExpr": "((L1D_TLB_REFILL / INST_RETIRED) * 1000)", - "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.", + "MetricExpr": "L1D_TLB_REFILL / INST_RETIRED * 1000", + "BriefDescription": "This metric measures the number of level 1 data TLB accesses missed per thousand instructions executed.", "MetricGroup": "MPKI;DTLB_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "l1i_cache_miss_ratio", - "MetricExpr": "(L1I_CACHE_REFILL / L1I_CACHE)", + "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE", "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.", "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness", - "ScaleUnit": "1per cache access" + "ScaleUnit": "100percent of cache accesses" }, { "MetricName": "l1i_cache_mpki", - "MetricExpr": "((L1I_CACHE_REFILL / INST_RETIRED) * 1000)", + "MetricExpr": "L1I_CACHE_REFILL / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of level 1 instruction cache accesses missed per thousand instructions executed.", "MetricGroup": "MPKI;L1I_Cache_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "l1i_tlb_miss_ratio", - "MetricExpr": "(L1I_TLB_REFILL / L1I_TLB)", + "MetricExpr": "L1I_TLB_REFILL / L1I_TLB", "BriefDescription": "This metric measures the ratio of level 1 instruction TLB accesses missed to the total number of level 1 instruction TLB accesses. This gives an indication of the effectiveness of the level 1 instruction TLB.", "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", - "ScaleUnit": "1per TLB access" + "ScaleUnit": "100percent of TLB accesses" }, { "MetricName": "l1i_tlb_mpki", - "MetricExpr": "((L1I_TLB_REFILL / INST_RETIRED) * 1000)", + "MetricExpr": "L1I_TLB_REFILL / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.", "MetricGroup": "MPKI;ITLB_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "l2_cache_miss_ratio", - "MetricExpr": "(L2D_CACHE_REFILL / L2D_CACHE)", + "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE", "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness", - "ScaleUnit": "1per cache access" + "ScaleUnit": "100percent of cache accesses" }, { "MetricName": "l2_cache_mpki", - "MetricExpr": "((L2D_CACHE_REFILL / INST_RETIRED) * 1000)", + "MetricExpr": "L2D_CACHE_REFILL / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of level 2 unified cache accesses missed per thousand instructions executed. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", "MetricGroup": "MPKI;L2_Cache_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "l2_tlb_miss_ratio", - "MetricExpr": "(L2D_TLB_REFILL / L2D_TLB)", + "MetricExpr": "L2D_TLB_REFILL / L2D_TLB", "BriefDescription": "This metric measures the ratio of level 2 unified TLB accesses missed to the total number of level 2 unified TLB accesses. This gives an indication of the effectiveness of the level 2 TLB.", "MetricGroup": "Miss_Ratio;ITLB_Effectiveness;DTLB_Effectiveness", - "ScaleUnit": "1per TLB access" + "ScaleUnit": "100percent of TLB accesses" }, { "MetricName": "l2_tlb_mpki", - "MetricExpr": "((L2D_TLB_REFILL / INST_RETIRED) * 1000)", + "MetricExpr": "L2D_TLB_REFILL / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of level 2 unified TLB accesses missed per thousand instructions executed.", "MetricGroup": "MPKI;ITLB_Effectiveness;DTLB_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "ll_cache_read_hit_ratio", - "MetricExpr": "((LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD)", + "MetricExpr": "(LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD", "BriefDescription": "This metric measures the ratio of last level cache read accesses hit in the cache to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", "MetricGroup": "LL_Cache_Effectiveness", - "ScaleUnit": "1per cache access" + "ScaleUnit": "100percent of cache accesses" }, { "MetricName": "ll_cache_read_miss_ratio", - "MetricExpr": "(LL_CACHE_MISS_RD / LL_CACHE_RD)", + "MetricExpr": "LL_CACHE_MISS_RD / LL_CACHE_RD", "BriefDescription": "This metric measures the ratio of last level cache read accesses missed to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", "MetricGroup": "Miss_Ratio;LL_Cache_Effectiveness", - "ScaleUnit": "1per cache access" + "ScaleUnit": "100percent of cache accesses" }, { "MetricName": "ll_cache_read_mpki", - "MetricExpr": "((LL_CACHE_MISS_RD / INST_RETIRED) * 1000)", + "MetricExpr": "LL_CACHE_MISS_RD / INST_RETIRED * 1000", "BriefDescription": "This metric measures the number of last level cache read accesses missed per thousand instructions executed.", "MetricGroup": "MPKI;LL_Cache_Effectiveness", "ScaleUnit": "1MPKI" }, { "MetricName": "load_percentage", - "MetricExpr": "((LD_SPEC / INST_SPEC) * 100)", + "MetricExpr": "LD_SPEC / INST_SPEC * 100", "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" @@ -213,21 +213,21 @@ }, { "MetricName": "scalar_fp_percentage", - "MetricExpr": "((VFP_SPEC / INST_SPEC) * 100)", + "MetricExpr": "VFP_SPEC / INST_SPEC * 100", "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" }, { "MetricName": "simd_percentage", - "MetricExpr": "((ASE_SPEC / INST_SPEC) * 100)", + "MetricExpr": "ASE_SPEC / INST_SPEC * 100", "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" }, { "MetricName": "store_percentage", - "MetricExpr": "((ST_SPEC / INST_SPEC) * 100)", + "MetricExpr": "ST_SPEC / INST_SPEC * 100", "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.", "MetricGroup": "Operation_Mix", "ScaleUnit": "1percent of operations" @@ -300,5 +300,12 @@ "MetricGroup": "Operation_Mix", "MetricName": "branch_indirect_spec_rate", "ScaleUnit": "100%" + }, + { + "MetricName": "sve_all_percentage", + "MetricExpr": "SVE_INST_SPEC / INST_SPEC * 100", + "BriefDescription": "This metric measures scalable vector operations, including loads and stores, as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json index f297b049b62f..337e6a916f2b 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/retired.json @@ -9,7 +9,7 @@ }, { "ArchStdEvent": "CID_WRITE_RETIRED", - "PublicDescription": "Counts architecturally executed writes to the CONTEXTIDR register, which usually contain the kernel PID and can be output with hardware trace." + "PublicDescription": "Counts architecturally executed writes to the CONTEXTIDR_EL1 register, which usually contain the kernel PID and can be output with hardware trace." }, { "ArchStdEvent": "TTBR_WRITE_RETIRED", @@ -17,7 +17,7 @@ }, { "ArchStdEvent": "BR_RETIRED", - "PublicDescription": "Counts architecturally executed branches, whether the branch is taken or not. Instructions that explicitly write to the PC are also counted." + "PublicDescription": "Counts architecturally executed branches, whether the branch is taken or not. Instructions that explicitly write to the PC are also counted. Note that exception generating instructions, exception return instructions and context synchronization instructions are not counted." }, { "ArchStdEvent": "BR_MIS_PRED_RETIRED", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json index 1af961f8a6c8..a7ea0d4c4ea4 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/spec_operation.json @@ -5,7 +5,7 @@ }, { "ArchStdEvent": "BR_PRED", - "PublicDescription": "Counts branches speculatively executed and were predicted right." + "PublicDescription": "Counts all speculatively executed branches." }, { "ArchStdEvent": "INST_SPEC", @@ -29,7 +29,7 @@ }, { "ArchStdEvent": "LDREX_SPEC", - "PublicDescription": "Counts Load-Exclusive operations that have been speculatively executed. Eg: LDREX, LDX" + "PublicDescription": "Counts Load-Exclusive operations that have been speculatively executed. For example: LDREX, LDX" }, { "ArchStdEvent": "STREX_PASS_SPEC", @@ -73,15 +73,15 @@ }, { "ArchStdEvent": "BR_IMMED_SPEC", - "PublicDescription": "Counts immediate branch operations which are speculatively executed." + "PublicDescription": "Counts direct branch operations which are speculatively executed." }, { "ArchStdEvent": "BR_RETURN_SPEC", - "PublicDescription": "Counts procedure return operations (RET) which are speculatively executed." + "PublicDescription": "Counts procedure return operations (RET, RETAA and RETAB) which are speculatively executed." }, { "ArchStdEvent": "BR_INDIRECT_SPEC", - "PublicDescription": "Counts indirect branch operations including procedure returns, which are speculatively executed. This includes operations that force a software change of the PC, other than exception-generating operations. Eg: BR Xn, RET" + "PublicDescription": "Counts indirect branch operations including procedure returns, which are speculatively executed. This includes operations that force a software change of the PC, other than exception-generating operations and direct branch instructions. Some examples of the instructions counted by this event include BR Xn, RET, etc..." }, { "ArchStdEvent": "ISB_SPEC", @@ -97,11 +97,11 @@ }, { "ArchStdEvent": "RC_LD_SPEC", - "PublicDescription": "Counts any load acquire operations that are speculatively executed. Eg: LDAR, LDARH, LDARB" + "PublicDescription": "Counts any load acquire operations that are speculatively executed. For example: LDAR, LDARH, LDARB" }, { "ArchStdEvent": "RC_ST_SPEC", - "PublicDescription": "Counts any store release operations that are speculatively executed. Eg: STLR, STLRH, STLRB'" + "PublicDescription": "Counts any store release operations that are speculatively executed. For example: STLR, STLRH, STLRB" }, { "ArchStdEvent": "ASE_INST_SPEC", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json index bbbebc805034..1fcba19dfb7d 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/stall.json @@ -1,7 +1,7 @@ [ { "ArchStdEvent": "STALL_FRONTEND", - "PublicDescription": "Counts cycles when frontend could not send any micro-operations to the rename stage because of frontend resource stalls caused by fetch memory latency or branch prediction flow stalls. All the frontend slots were empty during the cycle when this event counts." + "PublicDescription": "Counts cycles when frontend could not send any micro-operations to the rename stage because of frontend resource stalls caused by fetch memory latency or branch prediction flow stalls. STALL_FRONTEND_SLOTS counts SLOTS during the cycle when this event counts." }, { "ArchStdEvent": "STALL_BACKEND", @@ -9,11 +9,11 @@ }, { "ArchStdEvent": "STALL", - "PublicDescription": "Counts cycles when no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall)." + "PublicDescription": "Counts cycles when no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall). This event is the sum of STALL_FRONTEND and STALL_BACKEND" }, { "ArchStdEvent": "STALL_SLOT_BACKEND", - "PublicDescription": "Counts slots per cycle in which no operations are sent from the rename unit to the backend due to backend resource constraints." + "PublicDescription": "Counts slots per cycle in which no operations are sent from the rename unit to the backend due to backend resource constraints. STALL_BACKEND counts during the cycle when STALL_SLOT_BACKEND counts at least 1." }, { "ArchStdEvent": "STALL_SLOT_FRONTEND", @@ -21,7 +21,7 @@ }, { "ArchStdEvent": "STALL_SLOT", - "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall)." + "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall). STALL_SLOT is the sum of STALL_SLOT_FRONTEND and STALL_SLOT_BACKEND." }, { "ArchStdEvent": "STALL_BACKEND_MEM", diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json index b550af1831f5..5704f1e83af9 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2-v2/tlb.json @@ -25,11 +25,11 @@ }, { "ArchStdEvent": "DTLB_WALK", - "PublicDescription": "Counts data memory translation table walks caused by a miss in the L2 TLB driven by a memory access. Note that partial translations that also cause a table walk are counted. This event does not count table walks caused by TLB maintenance operations." + "PublicDescription": "Counts number of demand data translation table walks caused by a miss in the L2 TLB and performing at least one memory access. Translation table walks are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that partial translations that cause a translation table walk are also counted. Also note that this event counts walks triggered by software preloads, but not walks triggered by hardware prefetchers, and that this event does not count walks triggered by TLB maintenance operations." }, { "ArchStdEvent": "ITLB_WALK", - "PublicDescription": "Counts instruction memory translation table walks caused by a miss in the L2 TLB driven by a memory access. Partial translations that also cause a table walk are counted. This event does not count table walks caused by TLB maintenance operations." + "PublicDescription": "Counts number of instruction translation table walks caused by a miss in the L2 TLB and performing at least one memory access. Translation table walks are counted even if the translation ended up taking a translation fault for reasons different than EPD, E0PD and NFD. Note that partial translations that cause a translation table walk are also counted. Also note that this event does not count walks triggered by TLB maintenance operations." }, { "ArchStdEvent": "L1D_TLB_REFILL_RD", diff --git a/tools/perf/pmu-events/arch/arm64/common-and-microarch.json b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json index 492083b99256..dddecc946575 100644 --- a/tools/perf/pmu-events/arch/arm64/common-and-microarch.json +++ b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json @@ -534,6 +534,11 @@ "BriefDescription": "SVE operations speculatively executed" }, { + "EventCode": "0x8007", + "EventName": "ASE_SVE_INST_SPEC", + "BriefDescription": "Operation speculatively executed, Advanced SIMD or SVE." + }, + { "PublicDescription": "Microarchitectural operation, Operations speculatively executed.", "EventCode": "0x8008", "EventName": "UOP_SPEC", @@ -552,48 +557,393 @@ "BriefDescription": "Floating-point Operations speculatively executed." }, { + "EventCode": "0x8011", + "EventName": "ASE_FP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD." + }, + { + "EventCode": "0x8012", + "EventName": "SVE_FP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE." + }, + { + "EventCode": "0x8013", + "EventName": "ASE_SVE_FP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE." + }, + { "PublicDescription": "Floating-point half-precision operations speculatively executed", "EventCode": "0x8014", "EventName": "FP_HP_SPEC", "BriefDescription": "Floating-point half-precision operations speculatively executed" }, { + "EventCode": "0x8015", + "EventName": "ASE_FP_HP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD half precision." + }, + { + "EventCode": "0x8016", + "EventName": "SVE_FP_HP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE half precision." + }, + { + "EventCode": "0x8017", + "EventName": "ASE_SVE_FP_HP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE half precision." + }, + { "PublicDescription": "Floating-point single-precision operations speculatively executed", "EventCode": "0x8018", "EventName": "FP_SP_SPEC", "BriefDescription": "Floating-point single-precision operations speculatively executed" }, { + "EventCode": "0x8019", + "EventName": "ASE_FP_SP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD single precision." + }, + { + "EventCode": "0x801A", + "EventName": "SVE_FP_SP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE single precision." + }, + { + "EventCode": "0x801B", + "EventName": "ASE_SVE_FP_SP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE single precision." + }, + { "PublicDescription": "Floating-point double-precision operations speculatively executed", "EventCode": "0x801C", "EventName": "FP_DP_SPEC", "BriefDescription": "Floating-point double-precision operations speculatively executed" }, { + "EventCode": "0x801D", + "EventName": "ASE_FP_DP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD double precision." + }, + { + "EventCode": "0x801E", + "EventName": "SVE_FP_DP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE double precision." + }, + { + "EventCode": "0x801F", + "EventName": "ASE_SVE_FP_DP_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE double precision." + }, + { + "EventCode": "0x8020", + "EventName": "FP_DIV_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, divide." + }, + { + "EventCode": "0x8021", + "EventName": "ASE_FP_DIV_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD divide." + }, + { + "EventCode": "0x8022", + "EventName": "SVE_FP_DIV_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE divide." + }, + { + "EventCode": "0x8023", + "EventName": "ASE_SVE_FP_DIV_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE divide." + }, + { + "EventCode": "0x8024", + "EventName": "FP_SQRT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, square root." + }, + { + "EventCode": "0x8025", + "EventName": "ASE_FP_SQRT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD square root." + }, + { + "EventCode": "0x8026", + "EventName": "SVE_FP_SQRT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE square root." + }, + { + "EventCode": "0x8027", + "EventName": "ASE_SVE_FP_SQRT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE square-root." + }, + { "PublicDescription": "Floating-point FMA Operations speculatively executed.", "EventCode": "0x8028", "EventName": "FP_FMA_SPEC", "BriefDescription": "Floating-point FMA Operations speculatively executed." }, { + "EventCode": "0x8029", + "EventName": "ASE_FP_FMA_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD FMA." + }, + { + "EventCode": "0x802A", + "EventName": "SVE_FP_FMA_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE FMA." + }, + { + "EventCode": "0x802B", + "EventName": "ASE_SVE_FP_FMA_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE FMA." + }, + { + "EventCode": "0x802C", + "EventName": "FP_MUL_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, multiply." + }, + { + "EventCode": "0x802D", + "EventName": "ASE_FP_MUL_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD multiply." + }, + { + "EventCode": "0x802E", + "EventName": "SVE_FP_MUL_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE multiply." + }, + { + "EventCode": "0x802F", + "EventName": "ASE_SVE_FP_MUL_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE multiply." + }, + { + "EventCode": "0x8030", + "EventName": "FP_ADDSUB_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, add or subtract." + }, + { + "EventCode": "0x8031", + "EventName": "ASE_FP_ADDSUB_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD add or subtract." + }, + { + "EventCode": "0x8032", + "EventName": "SVE_FP_ADDSUB_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE add or subtract." + }, + { + "EventCode": "0x8033", + "EventName": "ASE_SVE_FP_ADDSUB_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE add or subtract." + }, + { "PublicDescription": "Floating-point reciprocal estimate Operations speculatively executed.", "EventCode": "0x8034", "EventName": "FP_RECPE_SPEC", "BriefDescription": "Floating-point reciprocal estimate Operations speculatively executed." }, { + "EventCode": "0x8035", + "EventName": "ASE_FP_RECPE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD reciprocal estimate." + }, + { + "EventCode": "0x8036", + "EventName": "SVE_FP_RECPE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE reciprocal estimate." + }, + { + "EventCode": "0x8037", + "EventName": "ASE_SVE_FP_RECPE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE reciprocal estimate." + }, + { "PublicDescription": "floating-point convert Operations speculatively executed.", "EventCode": "0x8038", "EventName": "FP_CVT_SPEC", "BriefDescription": "floating-point convert Operations speculatively executed." }, { + "EventCode": "0x8039", + "EventName": "ASE_FP_CVT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD convert." + }, + { + "EventCode": "0x803A", + "EventName": "SVE_FP_CVT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE convert." + }, + { + "EventCode": "0x803B", + "EventName": "ASE_SVE_FP_CVT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE convert." + }, + { + "EventCode": "0x803C", + "EventName": "SVE_FP_AREDUCE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE accumulating reduction." + }, + { + "EventCode": "0x803D", + "EventName": "ASE_FP_PREDUCE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD pairwise add step." + }, + { + "EventCode": "0x803E", + "EventName": "SVE_FP_VREDUCE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, SVE vector reduction." + }, + { + "EventCode": "0x803F", + "EventName": "ASE_SVE_FP_VREDUCE_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE vector reduction." + }, + { + "EventCode": "0x8040", + "EventName": "INT_SPEC", + "BriefDescription": "Integer Operation speculatively executed." + }, + { + "EventCode": "0x8041", + "EventName": "ASE_INT_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD." + }, + { + "EventCode": "0x8042", + "EventName": "SVE_INT_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE." + }, + { "PublicDescription": "Advanced SIMD and SVE integer Operations speculatively executed.", "EventCode": "0x8043", "EventName": "ASE_SVE_INT_SPEC", "BriefDescription": "Advanced SIMD and SVE integer Operations speculatively executed." }, { + "EventCode": "0x8044", + "EventName": "INT_DIV_SPEC", + "BriefDescription": "Integer Operation speculatively executed, divide." + }, + { + "EventCode": "0x8045", + "EventName": "INT_DIV64_SPEC", + "BriefDescription": "Integer Operation speculatively executed, 64-bit divide." + }, + { + "EventCode": "0x8046", + "EventName": "SVE_INT_DIV_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE divide." + }, + { + "EventCode": "0x8047", + "EventName": "SVE_INT_DIV64_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE 64-bit divide." + }, + { + "EventCode": "0x8048", + "EventName": "INT_MUL_SPEC", + "BriefDescription": "Integer Operation speculatively executed, multiply." + }, + { + "EventCode": "0x8049", + "EventName": "ASE_INT_MUL_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD multiply." + }, + { + "EventCode": "0x804A", + "EventName": "SVE_INT_MUL_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE multiply." + }, + { + "EventCode": "0x804B", + "EventName": "ASE_SVE_INT_MUL_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD or SVE multiply." + }, + { + "EventCode": "0x804C", + "EventName": "INT_MUL64_SPEC", + "BriefDescription": "Integer Operation speculatively executed, 64\u00d764 multiply." + }, + { + "EventCode": "0x804D", + "EventName": "SVE_INT_MUL64_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE 64\u00d764 multiply." + }, + { + "EventCode": "0x804E", + "EventName": "INT_MULH64_SPEC", + "BriefDescription": "Integer Operation speculatively executed, 64\u00d764 multiply returning high part." + }, + { + "EventCode": "0x804F", + "EventName": "SVE_INT_MULH64_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE 64\u00d764 multiply high part." + }, + { + "EventCode": "0x8058", + "EventName": "NONFP_SPEC", + "BriefDescription": "Non-floating-point Operation speculatively executed." + }, + { + "EventCode": "0x8059", + "EventName": "ASE_NONFP_SPEC", + "BriefDescription": "Non-floating-point Operation speculatively executed, Advanced SIMD." + }, + { + "EventCode": "0x805A", + "EventName": "SVE_NONFP_SPEC", + "BriefDescription": "Non-floating-point Operation speculatively executed, SVE." + }, + { + "EventCode": "0x805B", + "EventName": "ASE_SVE_NONFP_SPEC", + "BriefDescription": "Non-floating-point Operation speculatively executed, Advanced SIMD or SVE." + }, + { + "EventCode": "0x805D", + "EventName": "ASE_INT_VREDUCE_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD reduction." + }, + { + "EventCode": "0x805E", + "EventName": "SVE_INT_VREDUCE_SPEC", + "BriefDescription": "Integer Operation speculatively executed, SVE reduction." + }, + { + "EventCode": "0x805F", + "EventName": "ASE_SVE_INT_VREDUCE_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD or SVE reduction." + }, + { + "EventCode": "0x8060", + "EventName": "SVE_PERM_SPEC", + "BriefDescription": "Operation speculatively executed, SVE permute." + }, + { + "EventCode": "0x8065", + "EventName": "SVE_XPIPE_Z2R_SPEC", + "BriefDescription": "Operation speculatively executed, SVE vector to scalar cross-pipe." + }, + { + "EventCode": "0x8066", + "EventName": "SVE_XPIPE_R2Z_SPEC", + "BriefDescription": "Operation speculatively executed, SVE scalar to vector cross-pipe." + }, + { + "EventCode": "0x8068", + "EventName": "SVE_PGEN_SPEC", + "BriefDescription": "Operation speculatively executed, SVE predicate generating." + }, + { + "EventCode": "0x8069", + "EventName": "SVE_PGEN_FLG_SPEC", + "BriefDescription": "Operation speculatively executed, SVE predicate flag setting." + }, + { + "EventCode": "0x806D", + "EventName": "SVE_PPERM_SPEC", + "BriefDescription": "Operation speculatively executed, SVE predicate permute." + }, + { "PublicDescription": "SVE predicated Operations speculatively executed.", "EventCode": "0x8074", "EventName": "SVE_PRED_SPEC", @@ -630,6 +980,16 @@ "BriefDescription": "SVE MOVPRFX Operations speculatively executed." }, { + "EventCode": "0x807D", + "EventName": "SVE_MOVPRFX_Z_SPEC", + "BriefDescription": "Operation speculatively executed, SVE MOVPRFX zeroing predication." + }, + { + "EventCode": "0x807E", + "EventName": "SVE_MOVPRFX_M_SPEC", + "BriefDescription": "Operation speculatively executed, SVE MOVPRFX merging predication." + }, + { "PublicDescription": "SVE MOVPRFX unfused Operations speculatively executed.", "EventCode": "0x807F", "EventName": "SVE_MOVPRFX_U_SPEC", @@ -696,6 +1056,16 @@ "BriefDescription": "SVE contiguous prefetch element Operations speculatively executed." }, { + "EventCode": "0x80A1", + "EventName": "SVE_LDNT_CONTIG_SPEC", + "BriefDescription": "Operation speculatively executed, SVE non-temporal contiguous load element." + }, + { + "EventCode": "0x80A2", + "EventName": "SVE_STNT_CONTIG_SPEC", + "BriefDescription": "Operation speculatively executed, SVE non-temporal contiguous store element." + }, + { "PublicDescription": "Advanced SIMD and SVE contiguous load multiple vector Operations speculatively executed.", "EventCode": "0x80A5", "EventName": "ASE_SVE_LD_MULTI_SPEC", @@ -786,6 +1156,16 @@ "BriefDescription": "Non-scalable double-precision floating-point element Operations speculatively executed." }, { + "EventCode": "0x80C8", + "EventName": "INT_SCALE_OPS_SPEC", + "BriefDescription": "Scalable integer element arithmetic operations Speculatively executed." + }, + { + "EventCode": "0x80C9", + "EventName": "INT_FIXED_OPS_SPEC", + "BriefDescription": "Non-scalable integer element arithmetic operations Speculatively executed." + }, + { "PublicDescription": "Advanced SIMD and SVE 8-bit integer operations speculatively executed", "EventCode": "0x80E3", "EventName": "ASE_SVE_INT8_SPEC", @@ -808,5 +1188,340 @@ "EventCode": "0x80EF", "EventName": "ASE_SVE_INT64_SPEC", "BriefDescription": "Advanced SIMD and SVE 64-bit integer operations speculatively executed" + }, + { + "EventCode": "0x80F3", + "EventName": "ASE_SVE_FP_DOT_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE dot-product." + }, + { + "EventCode": "0x80F7", + "EventName": "ASE_SVE_FP_MMLA_SPEC", + "BriefDescription": "Floating-point Operation speculatively executed, Advanced SIMD or SVE matrix multiply." + }, + { + "EventCode": "0x80FB", + "EventName": "ASE_SVE_INT_DOT_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD or SVE dot-product." + }, + { + "EventCode": "0x80FF", + "EventName": "ASE_SVE_INT_MMLA_SPEC", + "BriefDescription": "Integer Operation speculatively executed, Advanced SIMD or SVE matrix multiply." + }, + { + "EventCode": "0x8128", + "EventName": "DTLB_WALK_PERCYC", + "BriefDescription": "Data translation table walks in progress." + }, + { + "EventCode": "0x8129", + "EventName": "ITLB_WALK_PERCYC", + "BriefDescription": "Instruction translation table walks in progress." + }, + { + "EventCode": "0x8136", + "EventName": "DTLB_STEP", + "BriefDescription": "Data TLB translation table walk, step." + }, + { + "EventCode": "0x8137", + "EventName": "ITLB_STEP", + "BriefDescription": "Instruction TLB translation table walk, step." + }, + { + "EventCode": "0x8138", + "EventName": "DTLB_WALK_LARGE", + "BriefDescription": "Data TLB large page translation table walk." + }, + { + "EventCode": "0x8139", + "EventName": "ITLB_WALK_LARGE", + "BriefDescription": "Instruction TLB large page translation table walk." + }, + { + "EventCode": "0x813A", + "EventName": "DTLB_WALK_SMALL", + "BriefDescription": "Data TLB small page translation table walk." + }, + { + "EventCode": "0x813B", + "EventName": "ITLB_WALK_SMALL", + "BriefDescription": "Instruction TLB small page translation table walk." + }, + { + "EventCode": "0x8144", + "EventName": "L1D_CACHE_MISS", + "BriefDescription": "Level 1 data cache demand access miss." + }, + { + "EventCode": "0x8145", + "EventName": "L1I_CACHE_HWPRF", + "BriefDescription": "Level 1 instruction cache hardware prefetch." + }, + { + "EventCode": "0x814C", + "EventName": "L2D_CACHE_MISS", + "BriefDescription": "Level 2 data cache demand access miss." + }, + { + "EventCode": "0x8154", + "EventName": "L1D_CACHE_HWPRF", + "BriefDescription": "Level 1 data cache hardware prefetch." + }, + { + "EventCode": "0x8155", + "EventName": "L2D_CACHE_HWPRF", + "BriefDescription": "Level 2 data cache hardware prefetch." + }, + { + "EventCode": "0x8158", + "EventName": "STALL_FRONTEND_MEMBOUND", + "BriefDescription": "Frontend stall cycles, memory bound." + }, + { + "EventCode": "0x8159", + "EventName": "STALL_FRONTEND_L1I", + "BriefDescription": "Frontend stall cycles, level 1 instruction cache." + }, + { + "EventCode": "0x815A", + "EventName": "STALL_FRONTEND_L2I", + "BriefDescription": "Frontend stall cycles, level 2 instruction cache." + }, + { + "EventCode": "0x815B", + "EventName": "STALL_FRONTEND_MEM", + "BriefDescription": "Frontend stall cycles, last level PE cache or memory." + }, + { + "EventCode": "0x815C", + "EventName": "STALL_FRONTEND_TLB", + "BriefDescription": "Frontend stall cycles, TLB." + }, + { + "EventCode": "0x8160", + "EventName": "STALL_FRONTEND_CPUBOUND", + "BriefDescription": "Frontend stall cycles, processor bound." + }, + { + "EventCode": "0x8161", + "EventName": "STALL_FRONTEND_FLOW", + "BriefDescription": "Frontend stall cycles, flow control." + }, + { + "EventCode": "0x8162", + "EventName": "STALL_FRONTEND_FLUSH", + "BriefDescription": "Frontend stall cycles, flush recovery." + }, + { + "EventCode": "0x8163", + "EventName": "STALL_FRONTEND_RENAME", + "BriefDescription": "Frontend stall cycles, rename full." + }, + { + "EventCode": "0x8164", + "EventName": "STALL_BACKEND_MEMBOUND", + "BriefDescription": "Backend stall cycles, memory bound." + }, + { + "EventCode": "0x8165", + "EventName": "STALL_BACKEND_L1D", + "BriefDescription": "Backend stall cycles, level 1 data cache." + }, + { + "EventCode": "0x8166", + "EventName": "STALL_BACKEND_L2D", + "BriefDescription": "Backend stall cycles, level 2 data cache." + }, + { + "EventCode": "0x8167", + "EventName": "STALL_BACKEND_TLB", + "BriefDescription": "Backend stall cycles, TLB." + }, + { + "EventCode": "0x8168", + "EventName": "STALL_BACKEND_ST", + "BriefDescription": "Backend stall cycles, store." + }, + { + "EventCode": "0x816A", + "EventName": "STALL_BACKEND_CPUBOUND", + "BriefDescription": "Backend stall cycles, processor bound." + }, + { + "EventCode": "0x816B", + "EventName": "STALL_BACKEND_BUSY", + "BriefDescription": "Backend stall cycles, backend busy." + }, + { + "EventCode": "0x816C", + "EventName": "STALL_BACKEND_ILOCK", + "BriefDescription": "Backend stall cycles, input dependency." + }, + { + "EventCode": "0x816D", + "EventName": "STALL_BACKEND_RENAME", + "BriefDescription": "Backend stall cycles, rename full." + }, + { + "EventCode": "0x816E", + "EventName": "STALL_BACKEND_ATOMIC", + "BriefDescription": "Backend stall cycles, atomic operation." + }, + { + "EventCode": "0x816F", + "EventName": "STALL_BACKEND_MEMCPYSET", + "BriefDescription": "Backend stall cycles, Memory Copy or Set operation." + }, + { + "EventCode": "0x8186", + "EventName": "UOP_RETIRED", + "BriefDescription": "Micro-operation architecturally executed." + }, + { + "EventCode": "0x8188", + "EventName": "DTLB_WALK_BLOCK", + "BriefDescription": "Data TLB block translation table walk." + }, + { + "EventCode": "0x8189", + "EventName": "ITLB_WALK_BLOCK", + "BriefDescription": "Instruction TLB block translation table walk." + }, + { + "EventCode": "0x818A", + "EventName": "DTLB_WALK_PAGE", + "BriefDescription": "Data TLB page translation table walk." + }, + { + "EventCode": "0x818B", + "EventName": "ITLB_WALK_PAGE", + "BriefDescription": "Instruction TLB page translation table walk." + }, + { + "EventCode": "0x81B8", + "EventName": "L1I_CACHE_REFILL_HWPRF", + "BriefDescription": "Level 1 instruction cache refill, hardware prefetch." + }, + { + "EventCode": "0x81BC", + "EventName": "L1D_CACHE_REFILL_HWPRF", + "BriefDescription": "Level 1 data cache refill, hardware prefetch." + }, + { + "EventCode": "0x81BD", + "EventName": "L2D_CACHE_REFILL_HWPRF", + "BriefDescription": "Level 2 data cache refill, hardware prefetch." + }, + { + "EventCode": "0x81C0", + "EventName": "L1I_CACHE_HIT_RD", + "BriefDescription": "Level 1 instruction cache demand fetch hit." + }, + { + "EventCode": "0x81C4", + "EventName": "L1D_CACHE_HIT_RD", + "BriefDescription": "Level 1 data cache demand access hit, read." + }, + { + "EventCode": "0x81C5", + "EventName": "L2D_CACHE_HIT_RD", + "BriefDescription": "Level 2 data cache demand access hit, read." + }, + { + "EventCode": "0x81C8", + "EventName": "L1D_CACHE_HIT_WR", + "BriefDescription": "Level 1 data cache demand access hit, write." + }, + { + "EventCode": "0x81C9", + "EventName": "L2D_CACHE_HIT_WR", + "BriefDescription": "Level 2 data cache demand access hit, write." + }, + { + "EventCode": "0x8200", + "EventName": "L1I_CACHE_HIT", + "BriefDescription": "Level 1 instruction cache hit." + }, + { + "EventCode": "0x8204", + "EventName": "L1D_CACHE_HIT", + "BriefDescription": "Level 1 data cache hit." + }, + { + "EventCode": "0x8205", + "EventName": "L2D_CACHE_HIT", + "BriefDescription": "Level 2 data cache hit." + }, + { + "EventCode": "0x8240", + "EventName": "L1I_LFB_HIT_RD", + "BriefDescription": "Level 1 instruction cache demand fetch line-fill buffer hit." + }, + { + "EventCode": "0x8244", + "EventName": "L1D_LFB_HIT_RD", + "BriefDescription": "Level 1 data cache demand access line-fill buffer hit, read." + }, + { + "EventCode": "0x8245", + "EventName": "L2D_LFB_HIT_RD", + "BriefDescription": "Level 2 data cache demand access line-fill buffer hit, read." + }, + { + "EventCode": "0x8248", + "EventName": "L1D_LFB_HIT_WR", + "BriefDescription": "Level 1 data cache demand access line-fill buffer hit, write." + }, + { + "EventCode": "0x8249", + "EventName": "L2D_LFB_HIT_WR", + "BriefDescription": "Level 2 data cache demand access line-fill buffer hit, write." + }, + { + "EventCode": "0x8280", + "EventName": "L1I_CACHE_PRF", + "BriefDescription": "Level 1 instruction cache, preload or prefetch hit." + }, + { + "EventCode": "0x8284", + "EventName": "L1D_CACHE_PRF", + "BriefDescription": "Level 1 data cache, preload or prefetch hit." + }, + { + "EventCode": "0x8285", + "EventName": "L2D_CACHE_PRF", + "BriefDescription": "Level 2 data cache, preload or prefetch hit." + }, + { + "EventCode": "0x8288", + "EventName": "L1I_CACHE_REFILL_PRF", + "BriefDescription": "Level 1 instruction cache refill, preload or prefetch hit." + }, + { + "EventCode": "0x828C", + "EventName": "L1D_CACHE_REFILL_PRF", + "BriefDescription": "Level 1 data cache refill, preload or prefetch hit." + }, + { + "EventCode": "0x828D", + "EventName": "L2D_CACHE_REFILL_PRF", + "BriefDescription": "Level 2 data cache refill, preload or prefetch hit." + }, + { + "EventCode": "0x8320", + "EventName": "L1D_CACHE_REFILL_PERCYC", + "BriefDescription": "Level 1 data or unified cache refills in progress." + }, + { + "EventCode": "0x8321", + "EventName": "L2D_CACHE_REFILL_PERCYC", + "BriefDescription": "Level 2 data or unified cache refills in progress." + }, + { + "EventCode": "0x8324", + "EventName": "L1I_CACHE_REFILL_PERCYC", + "BriefDescription": "Level 1 instruction or unified cache refills in progress." } ] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/core-imp-def.json new file mode 100644 index 000000000000..52f5ca1482fe --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/core-imp-def.json @@ -0,0 +1,6 @@ +[ + { + "ArchStdEvent": "L1I_CACHE_PRF", + "BriefDescription": "This event counts fetch counted by either Level 1 instruction hardware prefetch or Level 1 instruction software prefetch." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/cycle_accounting.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/cycle_accounting.json new file mode 100644 index 000000000000..24ff5d8dbb98 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/cycle_accounting.json @@ -0,0 +1,122 @@ +[ + { + "EventCode": "0x0182", + "EventName": "LD_COMP_WAIT_L1_MISS", + "BriefDescription": "This event counts every cycle that no instruction was committed because the oldest and uncommitted load/store/prefetch operation waits for L2 cache access." + }, + { + "EventCode": "0x0183", + "EventName": "LD_COMP_WAIT_L1_MISS_EX", + "BriefDescription": "This event counts every cycle that no instruction was committed because the oldest and uncommitted integer load operation waits for L2 cache access." + }, + { + "EventCode": "0x0184", + "EventName": "LD_COMP_WAIT", + "BriefDescription": "This event counts every cycle that no instruction was committed because the oldest and uncommitted load/store/prefetch operation waits for L1D cache, L2 cache and memory access." + }, + { + "EventCode": "0x0185", + "EventName": "LD_COMP_WAIT_EX", + "BriefDescription": "This event counts every cycle that no instruction was committed because the oldest and uncommitted integer load operation waits for L1D cache, L2 cache and memory access." + }, + { + "EventCode": "0x0186", + "EventName": "LD_COMP_WAIT_PFP_BUSY", + "BriefDescription": "This event counts every cycle that no instruction was committed due to the lack of an available prefetch port." + }, + { + "EventCode": "0x0187", + "EventName": "LD_COMP_WAIT_PFP_BUSY_EX", + "BriefDescription": "This event counts the LD_COMP_WAIT_PFP_BUSY caused by an integer load operation." + }, + { + "EventCode": "0x0188", + "EventName": "LD_COMP_WAIT_PFP_BUSY_SWPF", + "BriefDescription": "This event counts the LD_COMP_WAIT_PFP_BUSY caused by a software prefetch instruction." + }, + { + "EventCode": "0x0189", + "EventName": "EU_COMP_WAIT", + "BriefDescription": "This event counts every cycle that no instruction was committed and the oldest and uncommitted instruction is an integer or floating-point/SIMD instruction." + }, + { + "EventCode": "0x018A", + "EventName": "FL_COMP_WAIT", + "BriefDescription": "This event counts every cycle that no instruction was committed and the oldest and uncommitted instruction is a floating-point/SIMD instruction." + }, + { + "EventCode": "0x018B", + "EventName": "BR_COMP_WAIT", + "BriefDescription": "This event counts every cycle that no instruction was committed and the oldest and uncommitted instruction is a branch instruction." + }, + { + "EventCode": "0x018C", + "EventName": "ROB_EMPTY", + "BriefDescription": "This event counts every cycle that no instruction was committed because the CSE is empty." + }, + { + "EventCode": "0x018D", + "EventName": "ROB_EMPTY_STQ_BUSY", + "BriefDescription": "This event counts every cycle that no instruction was committed because the CSE is empty and the store port (SP) is full." + }, + { + "EventCode": "0x018E", + "EventName": "WFE_WFI_CYCLE", + "BriefDescription": "This event counts every cycle that the instruction unit is halted by the WFE/WFI instruction." + }, + { + "EventCode": "0x018F", + "EventName": "RETENTION_CYCLE", + "BriefDescription": "This event counts every cycle that the instruction unit is halted by the RETENTION state." + }, + { + "EventCode": "0x0190", + "EventName": "_0INST_COMMIT", + "BriefDescription": "This event counts every cycle that no instruction was committed, but counts at the time when commits MOVPRFX only." + }, + { + "EventCode": "0x0191", + "EventName": "_1INST_COMMIT", + "BriefDescription": "This event counts every cycle that one instruction is committed." + }, + { + "EventCode": "0x0192", + "EventName": "_2INST_COMMIT", + "BriefDescription": "This event counts every cycle that two instructions are committed." + }, + { + "EventCode": "0x0193", + "EventName": "_3INST_COMMIT", + "BriefDescription": "This event counts every cycle that three instructions are committed." + }, + { + "EventCode": "0x0194", + "EventName": "_4INST_COMMIT", + "BriefDescription": "This event counts every cycle that four instructions are committed." + }, + { + "EventCode": "0x0195", + "EventName": "_5INST_COMMIT", + "BriefDescription": "This event counts every cycle that five instructions are committed." + }, + { + "EventCode": "0x0198", + "EventName": "UOP_ONLY_COMMIT", + "BriefDescription": "This event counts every cycle that only any micro-operations are committed." + }, + { + "EventCode": "0x0199", + "EventName": "SINGLE_MOVPRFX_COMMIT", + "BriefDescription": "This event counts every cycle that only the MOVPRFX instruction is committed." + }, + { + "EventCode": "0x019C", + "EventName": "LD_COMP_WAIT_L2_MISS", + "BriefDescription": "This event counts every cycle that no instruction was committed because the oldest and uncommitted load/store/prefetch operation waits for L2 cache miss." + }, + { + "EventCode": "0x019D", + "EventName": "LD_COMP_WAIT_L2_MISS_EX", + "BriefDescription": "This event counts every cycle that no instruction was committed because the oldest and uncommitted integer load operation waits for L2 cache miss." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/energy.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/energy.json new file mode 100644 index 000000000000..b55173f71e42 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/energy.json @@ -0,0 +1,17 @@ +[ + { + "EventCode": "0x01F0", + "EventName": "EA_CORE", + "BriefDescription": "This event counts energy consumption of core." + }, + { + "EventCode": "0x03F0", + "EventName": "EA_L3", + "BriefDescription": "This event counts energy consumption of L3 cache." + }, + { + "EventCode": "0x03F1", + "EventName": "EA_LDO_LOSS", + "BriefDescription": "This event counts energy consumption of LDO loss." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/exception.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/exception.json new file mode 100644 index 000000000000..f231712fe261 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/exception.json @@ -0,0 +1,42 @@ +[ + { + "ArchStdEvent": "EXC_TAKEN", + "BriefDescription": "This event counts each exception taken." + }, + { + "ArchStdEvent": "EXC_RETURN", + "BriefDescription": "This event counts each executed exception return instruction." + }, + { + "ArchStdEvent": "EXC_UNDEF", + "BriefDescription": "This event counts only other synchronous exceptions that are taken locally." + }, + { + "ArchStdEvent": "EXC_SVC", + "BriefDescription": "This event counts only Supervisor Call exceptions that are taken locally." + }, + { + "ArchStdEvent": "EXC_PABORT", + "BriefDescription": "This event counts only Instruction Abort exceptions that are taken locally." + }, + { + "ArchStdEvent": "EXC_DABORT", + "BriefDescription": "This event counts only Data Abort or SError interrupt exceptions that are taken locally." + }, + { + "ArchStdEvent": "EXC_IRQ", + "BriefDescription": "This event counts only IRQ exceptions that are taken locally, including Virtual IRQ exceptions." + }, + { + "ArchStdEvent": "EXC_FIQ", + "BriefDescription": "This event counts only FIQ exceptions that are taken locally, including Virtual FIQ exceptions." + }, + { + "ArchStdEvent": "EXC_SMC", + "BriefDescription": "This event counts only Secure Monitor Call exceptions. The counter does not increment on SMC instructions trapped as a Hyp Trap exception." + }, + { + "ArchStdEvent": "EXC_HVC", + "BriefDescription": "This event counts for both Hypervisor Call exceptions taken locally in the hypervisor and those taken as an exception from Non-secure EL1." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/fp_operation.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/fp_operation.json new file mode 100644 index 000000000000..a3c368959199 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/fp_operation.json @@ -0,0 +1,209 @@ +[ + { + "EventCode": "0x0105", + "EventName": "FP_MV_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point move operations." + }, + { + "EventCode": "0x0112", + "EventName": "FP_LD_SPEC", + "BriefDescription": "This event counts architecturally executed NOSIMD load operations that using SIMD&FP registers." + }, + { + "EventCode": "0x0113", + "EventName": "FP_ST_SPEC", + "BriefDescription": "This event counts architecturally executed NOSIMD store operations that using SIMD&FP registers." + }, + { + "ArchStdEvent": "ASE_FP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point operation." + }, + { + "ArchStdEvent": "SVE_FP_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point operations." + }, + { + "ArchStdEvent": "FP_HP_SPEC", + "BriefDescription": "This event counts architecturally executed half-precision floating-point operation." + }, + { + "ArchStdEvent": "ASE_FP_HP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD half-precision floating-point operation." + }, + { + "ArchStdEvent": "SVE_FP_HP_SPEC", + "BriefDescription": "This event counts architecturally executed SVE half-precision floating-point operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_HP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE half-precision floating-point operations." + }, + { + "ArchStdEvent": "FP_SP_SPEC", + "BriefDescription": "This event counts architecturally executed single-precision floating-point operation." + }, + { + "ArchStdEvent": "ASE_FP_SP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD single-precision floating-point operation." + }, + { + "ArchStdEvent": "SVE_FP_SP_SPEC", + "BriefDescription": "This event counts architecturally executed SVE single-precision floating-point operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_SP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE single-precision floating-point operations." + }, + { + "ArchStdEvent": "FP_DP_SPEC", + "BriefDescription": "This event counts architecturally executed double-precision floating-point operation." + }, + { + "ArchStdEvent": "ASE_FP_DP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD double-precision floating-point operation." + }, + { + "ArchStdEvent": "SVE_FP_DP_SPEC", + "BriefDescription": "This event counts architecturally executed SVE double-precision floating-point operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_DP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE double-precision floating-point operations." + }, + { + "ArchStdEvent": "FP_DIV_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point divide operation." + }, + { + "ArchStdEvent": "ASE_FP_DIV_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point divide operation." + }, + { + "ArchStdEvent": "SVE_FP_DIV_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point divide operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_DIV_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point divide operations." + }, + { + "ArchStdEvent": "FP_SQRT_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point square root operation." + }, + { + "ArchStdEvent": "ASE_FP_SQRT_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point square root operation." + }, + { + "ArchStdEvent": "SVE_FP_SQRT_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point square root operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_SQRT_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point square root operations." + }, + { + "ArchStdEvent": "ASE_FP_FMA_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point FMA operation." + }, + { + "ArchStdEvent": "SVE_FP_FMA_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point FMA operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_FMA_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point FMA operations." + }, + { + "ArchStdEvent": "FP_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point multiply operations." + }, + { + "ArchStdEvent": "ASE_FP_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point multiply operation." + }, + { + "ArchStdEvent": "SVE_FP_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point multiply operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point multiply operations." + }, + { + "ArchStdEvent": "FP_ADDSUB_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point add or subtract operations." + }, + { + "ArchStdEvent": "ASE_FP_ADDSUB_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point add or subtract operation." + }, + { + "ArchStdEvent": "SVE_FP_ADDSUB_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point add or subtract operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_ADDSUB_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point add or subtract operations." + }, + { + "ArchStdEvent": "ASE_FP_RECPE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point reciprocal estimate operations." + }, + { + "ArchStdEvent": "SVE_FP_RECPE_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point reciprocal estimate operations." + }, + { + "ArchStdEvent": "ASE_SVE_FP_RECPE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point reciprocal estimate operations." + }, + { + "ArchStdEvent": "ASE_FP_CVT_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point convert operation." + }, + { + "ArchStdEvent": "SVE_FP_CVT_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point convert operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_CVT_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point convert operations." + }, + { + "ArchStdEvent": "SVE_FP_AREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point accumulating reduction operations." + }, + { + "ArchStdEvent": "ASE_FP_PREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD floating-point pairwise add step operations." + }, + { + "ArchStdEvent": "SVE_FP_VREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed SVE floating-point vector reduction operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_VREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE floating-point vector reduction operations." + }, + { + "ArchStdEvent": "FP_SCALE_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed SVE arithmetic operations. See FP_SCALE_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by (128 / CSIZE) and by twice that amount for operations that would also be counted by SVE_FP_FMA_SPEC." + }, + { + "ArchStdEvent": "FP_FIXED_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed v8SIMD&FP arithmetic operations. See FP_FIXED_OPS_SPEC of ARMv9 Reference Manual for more information. The event counter is incremented by the specified number of elements for Advanced SIMD operations or by 1 for scalar operations, and by twice those amounts for operations that would also be counted by FP_FMA_SPEC." + }, + { + "ArchStdEvent": "ASE_SVE_FP_DOT_SPEC", + "BriefDescription": "This event counts architecturally executed microarchitectural Advanced SIMD or SVE floating-point dot-product operation." + }, + { + "ArchStdEvent": "ASE_SVE_FP_MMLA_SPEC", + "BriefDescription": "This event counts architecturally executed microarchitectural Advanced SIMD or SVE floating-point matrix multiply operation." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/gcycle.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/gcycle.json new file mode 100644 index 000000000000..b4ceddc0d25e --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/gcycle.json @@ -0,0 +1,97 @@ +[ + { + "EventCode": "0x0880", + "EventName": "GCYCLES", + "BriefDescription": "This event counts the number of cycles at 100MHz." + }, + { + "EventCode": "0x0890", + "EventName": "FL0_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 0." + }, + { + "EventCode": "0x0891", + "EventName": "FL1_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 1." + }, + { + "EventCode": "0x0892", + "EventName": "FL2_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 2." + }, + { + "EventCode": "0x0893", + "EventName": "FL3_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 3." + }, + { + "EventCode": "0x0894", + "EventName": "FL4_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 4." + }, + { + "EventCode": "0x0895", + "EventName": "FL5_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 5." + }, + { + "EventCode": "0x0896", + "EventName": "FL6_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 6." + }, + { + "EventCode": "0x0897", + "EventName": "FL7_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 7." + }, + { + "EventCode": "0x0898", + "EventName": "FL8_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 8." + }, + { + "EventCode": "0x0899", + "EventName": "FL9_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 9." + }, + { + "EventCode": "0x089A", + "EventName": "FL10_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 10." + }, + { + "EventCode": "0x089B", + "EventName": "FL11_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 11." + }, + { + "EventCode": "0x089C", + "EventName": "FL12_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 12." + }, + { + "EventCode": "0x089D", + "EventName": "FL13_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 13." + }, + { + "EventCode": "0x089E", + "EventName": "FL14_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 14." + }, + { + "EventCode": "0x089F", + "EventName": "FL15_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the Frequency Level 15." + }, + { + "EventCode": "0x08A0", + "EventName": "RETENTION_GCYCLES", + "BriefDescription": "This event counts the number of cycles where the measured core is staying in the RETENTION state." + }, + { + "EventCode": "0x08A1", + "EventName": "RETENTION_COUNT", + "BriefDescription": "This event counts the number of changes from the normal state to the RETENTION state." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/general.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/general.json new file mode 100644 index 000000000000..32f0fbfc4de4 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/general.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "CPU_CYCLES", + "BriefDescription": "This event counts every cycle." + }, + { + "ArchStdEvent": "CNT_CYCLES", + "BriefDescription": "This event counts the constant frequency cycles counter increments at a constant frequency equal to the rate of increment of the System counter." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/hwpf.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/hwpf.json new file mode 100644 index 000000000000..a784a032f353 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/hwpf.json @@ -0,0 +1,52 @@ +[ + { + "EventCode": "0x0230", + "EventName": "L1HWPF_STREAM_PF", + "BriefDescription": "This event counts streaming prefetch requests to L1D cache generated by hardware prefetcher." + }, + { + "EventCode": "0x0231", + "EventName": "L1HWPF_STRIDE_PF", + "BriefDescription": "This event counts stride prefetch requests to L1D cache generated by hardware prefetcher." + }, + { + "EventCode": "0x0232", + "EventName": "L1HWPF_PFTGT_PF", + "BriefDescription": "This event counts LDS prefetch requests to L1D cache generated by hardware prefetcher." + }, + { + "EventCode": "0x0234", + "EventName": "L2HWPF_STREAM_PF", + "BriefDescription": "This event counts streaming prefetch requests to L2 cache generated by hardware prefetcher." + }, + { + "EventCode": "0x0235", + "EventName": "L2HWPF_STRIDE_PF", + "BriefDescription": "This event counts stride prefetch requests to L2 cache generated by hardware prefetcher." + }, + { + "EventCode": "0x0237", + "EventName": "L2HWPF_OTHER", + "BriefDescription": "This event counts prefetch requests to L2 cache generated by the other causes." + }, + { + "EventCode": "0x0238", + "EventName": "L3HWPF_STREAM_PF", + "BriefDescription": "This event counts streaming prefetch requests to L3 cache generated by hardware prefetcher." + }, + { + "EventCode": "0x0239", + "EventName": "L3HWPF_STRIDE_PF", + "BriefDescription": "This event counts stride prefetch requests to L3 cache generated by hardware prefetcher." + }, + { + "EventCode": "0x023B", + "EventName": "L3HWPF_OTHER", + "BriefDescription": "This event counts prefetch requests to L3 cache generated by the other causes." + }, + { + "EventCode": "0x023C", + "EventName": "L1IHWPF_NEXTLINE_PF", + "BriefDescription": "This event counts next line's prefetch requests to L1I cache generated by hardware prefetcher." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l1d_cache.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l1d_cache.json new file mode 100644 index 000000000000..b0818a2fedb0 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l1d_cache.json @@ -0,0 +1,113 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_REFILL", + "BriefDescription": "This event counts operations that cause a refill of the L1D cache. See L1D_CACHE_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1D_CACHE", + "BriefDescription": "This event counts operations that cause a cache access to the L1D cache. See L1D_CACHE of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1D_CACHE_WB", + "BriefDescription": "This event counts every write-back of data from the L1D cache. See L1D_CACHE_WB of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1D_CACHE_LMISS_RD", + "BriefDescription": "This event counts operations that cause a refill of the L1D cache that incurs additional latency." + }, + { + "ArchStdEvent": "L1D_CACHE_RD", + "BriefDescription": "This event counts L1D CACHE caused by read access." + }, + { + "ArchStdEvent": "L1D_CACHE_WR", + "BriefDescription": "This event counts L1D CACHE caused by write access." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD", + "BriefDescription": "This event counts L1D_CACHE_REFILL caused by read access." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR", + "BriefDescription": "This event counts L1D_CACHE_REFILL caused by write access." + }, + { + "EventCode": "0x0200", + "EventName": "L1D_CACHE_DM", + "BriefDescription": "This event counts L1D_CACHE caused by demand access." + }, + { + "EventCode": "0x0201", + "EventName": "L1D_CACHE_DM_RD", + "BriefDescription": "This event counts L1D_CACHE caused by demand read access." + }, + { + "EventCode": "0x0202", + "EventName": "L1D_CACHE_DM_WR", + "BriefDescription": "This event counts L1D_CACHE caused by demand write access." + }, + { + "EventCode": "0x0208", + "EventName": "L1D_CACHE_REFILL_DM", + "BriefDescription": "This event counts L1D_CACHE_REFILL caused by demand access." + }, + { + "EventCode": "0x0209", + "EventName": "L1D_CACHE_REFILL_DM_RD", + "BriefDescription": "This event counts L1D_CACHE_REFILL caused by demand read access." + }, + { + "EventCode": "0x020A", + "EventName": "L1D_CACHE_REFILL_DM_WR", + "BriefDescription": "This event counts L1D_CACHE_REFILL caused by demand write access." + }, + { + "EventCode": "0x020D", + "EventName": "L1D_CACHE_BTC", + "BriefDescription": "This event counts demand access that hits cache line with shared status and requests exclusive access in the Level 1 data cache, causing a coherence access to outside of the Level 1 caches of this PE." + }, + { + "ArchStdEvent": "L1D_CACHE_MISS", + "BriefDescription": "This event counts demand access that misses in the Level 1 data cache, causing an access to outside of the Level 1 caches of this PE." + }, + { + "ArchStdEvent": "L1D_CACHE_HWPRF", + "BriefDescription": "This event counts access counted by L1D_CACHE that is due to a hardware prefetch." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_HWPRF", + "BriefDescription": "This event counts hardware prefetch counted by L1D_CACHE_HWPRF that causes a refill of the Level 1 data cache from outside of the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_CACHE_HIT_RD", + "BriefDescription": "This event counts demand read counted by L1D_CACHE_RD that hits in the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_CACHE_HIT_WR", + "BriefDescription": "This event counts demand write counted by L1D_CACHE_WR that hits in the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_CACHE_HIT", + "BriefDescription": "This event counts access counted by L1D_CACHE that hits in the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_LFB_HIT_RD", + "BriefDescription": "This event counts demand access counted by L1D_CACHE_HIT_RD that hits a cache line that is in the process of being loaded into the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_LFB_HIT_WR", + "BriefDescription": "This event counts demand access counted by L1D_CACHE_HIT_WR that hits a cache line that is in the process of being loaded into the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_CACHE_PRF", + "BriefDescription": "This event counts fetch counted by either Level 1 data hardware prefetch or Level 1 data software prefetch." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_PRF", + "BriefDescription": "This event counts hardware prefetch counted by L1D_CACHE_PRF that causes a refill of the Level 1 data cache from outside of the Level 1 data cache." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_PERCYC", + "BriefDescription": "The counter counts by the number of cache refills counted by L1D_CACHE_REFILL in progress on each Processor cycle." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l1i_cache.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l1i_cache.json new file mode 100644 index 000000000000..8680d8ec461d --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l1i_cache.json @@ -0,0 +1,52 @@ +[ + { + "ArchStdEvent": "L1I_CACHE_REFILL", + "BriefDescription": "This event counts operations that cause a refill of the L1I cache. See L1I_CACHE_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1I_CACHE", + "BriefDescription": "This event counts operations that cause a cache access to the L1I cache. See L1I_CACHE of ARMv9 Reference Manual for more information." + }, + { + "EventCode": "0x0207", + "EventName": "L1I_CACHE_DM_RD", + "BriefDescription": "This event counts L1I_CACHE caused by demand read access." + }, + { + "EventCode": "0x020F", + "EventName": "L1I_CACHE_REFILL_DM_RD", + "BriefDescription": "This event counts L1I_CACHE_REFILL caused by demand read access." + }, + { + "ArchStdEvent": "L1I_CACHE_LMISS", + "BriefDescription": "This event counts operations that cause a refill of the L1I cache that incurs additional latency." + }, + { + "ArchStdEvent": "L1I_CACHE_HWPRF", + "BriefDescription": "This event counts access counted by L1I_CACHE that is due to a hardware prefetch." + }, + { + "ArchStdEvent": "L1I_CACHE_REFILL_HWPRF", + "BriefDescription": "This event counts hardware prefetch counted by L1I_CACHE_HWPRF that causes a refill of the Level 1 instruction cache from outside of the Level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_CACHE_HIT_RD", + "BriefDescription": "This event counts demand fetch counted by L1I_CACHE_DM_RD that hits in the Level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_CACHE_HIT", + "BriefDescription": "This event counts access counted by L1I_CACHE that hits in the Level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_LFB_HIT_RD", + "BriefDescription": "This event counts demand access counted by L1I_CACHE_HIT_RD that hits a cache line that is in the process of being loaded into the Level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_CACHE_REFILL_PRF", + "BriefDescription": "This event counts hardware prefetch counted by L1I_CACHE_PRF that causes a refill of the Level 1 instruction cache from outside of the Level 1 instruction cache." + }, + { + "ArchStdEvent": "L1I_CACHE_REFILL_PERCYC", + "BriefDescription": "The counter counts by the number of cache refills counted by L1I_CACHE_REFILL in progress on each Processor cycle." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l2_cache.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l2_cache.json new file mode 100644 index 000000000000..9e092752e6db --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l2_cache.json @@ -0,0 +1,160 @@ +[ + { + "ArchStdEvent": "L2D_CACHE", + "BriefDescription": "This event counts operations that cause a cache access to the L2 cache. See L2D_CACHE of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL", + "BriefDescription": "This event counts operations that cause a refill of the L2 cache. See L2D_CACHE_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L2D_CACHE_WB", + "BriefDescription": "This event counts every write-back of data from the L2 cache caused by L2 replace, non-temporal-store and DC ZVA." + }, + { + "ArchStdEvent": "L2I_TLB_REFILL", + "BriefDescription": "This event counts operations that cause a TLB refill of the L2I TLB. See L2I_TLB_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L2I_TLB", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I TLB. See L2I_TLB of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L2D_CACHE_RD", + "BriefDescription": "This event counts L2D CACHE caused by read access." + }, + { + "ArchStdEvent": "L2D_CACHE_WR", + "BriefDescription": "This event counts L2D CACHE caused by write access." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD", + "BriefDescription": "This event counts L2D CACHE_REFILL caused by read access." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR", + "BriefDescription": "This event counts L2D CACHE_REFILL caused by write access." + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM", + "BriefDescription": "This event counts every write-back of data from the L2 cache caused by L2 replace." + }, + { + "EventCode": "0x0300", + "EventName": "L2D_CACHE_DM", + "BriefDescription": "This event counts L2D_CACHE caused by demand access." + }, + { + "EventCode": "0x0301", + "EventName": "L2D_CACHE_DM_RD", + "BriefDescription": "This event counts L2D_CACHE caused by demand read access." + }, + { + "EventCode": "0x0302", + "EventName": "L2D_CACHE_DM_WR", + "BriefDescription": "This event counts L2D_CACHE caused by demand write access." + }, + { + "EventCode": "0x0305", + "EventName": "L2D_CACHE_HWPRF_ADJACENT", + "BriefDescription": "This event counts L2D_CACHE caused by hardware adjacent prefetch access." + }, + { + "EventCode": "0x0308", + "EventName": "L2D_CACHE_REFILL_DM", + "BriefDescription": "This event counts L2D_CACHE_REFILL caused by demand access." + }, + { + "EventCode": "0x0309", + "EventName": "L2D_CACHE_REFILL_DM_RD", + "BriefDescription": "This event counts L2D_CACHE_REFILL caused by demand read access." + }, + { + "EventCode": "0x030A", + "EventName": "L2D_CACHE_REFILL_DM_WR", + "BriefDescription": "This event counts L2D_CACHE_REFILL caused by demand write access." + }, + { + "EventCode": "0x030B", + "EventName": "L2D_CACHE_REFILL_DM_WR_EXCL", + "BriefDescription": "This event counts L2D_CACHE_REFILL caused by demand write exclusive access." + }, + { + "EventCode": "0x030C", + "EventName": "L2D_CACHE_REFILL_DM_WR_ATOM", + "BriefDescription": "This event counts L2D_CACHE_REFILL caused by demand write atomic access." + }, + { + "EventCode": "0x030D", + "EventName": "L2D_CACHE_BTC", + "BriefDescription": "This event counts demand access that hits cache line with shared status and requests exclusive access in the Level 1 data and Level 2 caches, causing a coherence access to outside of the Level 1 and Level 2 caches of this PE." + }, + { + "EventCode": "0x03B0", + "EventName": "L2D_CACHE_WB_VICTIM_CLEAN", + "BriefDescription": "This event counts every write-back of data from the L2 cache caused by L2 replace where the data is clean. In this case, the data will usually be written to L3 cache." + }, + { + "EventCode": "0x03B1", + "EventName": "L2D_CACHE_WB_NT", + "BriefDescription": "This event counts every write-back of data from the L2 cache caused by non-temporal-store." + }, + { + "EventCode": "0x03B2", + "EventName": "L2D_CACHE_WB_DCZVA", + "BriefDescription": "This event counts every write-back of data from the L2 cache caused by DC ZVA." + }, + { + "EventCode": "0x03B3", + "EventName": "L2D_CACHE_FB", + "BriefDescription": "This event counts every flush-back (drop) of data from the L2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_LMISS_RD", + "BriefDescription": "This event counts operations that cause a refill of the L2D cache that incurs additional latency." + }, + { + "ArchStdEvent": "L2D_CACHE_MISS", + "BriefDescription": "This event counts demand access that misses in the Level 1 data and Level 2 caches, causing an access to outside of the Level 1 and Level 2 caches of this PE." + }, + { + "ArchStdEvent": "L2D_CACHE_HWPRF", + "BriefDescription": "This event counts access counted by L2D_CACHE that is due to a hardware prefetch." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_HWPRF", + "BriefDescription": "This event counts hardware prefetch counted by L2D_CACHE_HWPRF that causes a refill of the Level 2 cache, or any Level 1 data and instruction cache of this PE, from outside of those caches." + }, + { + "ArchStdEvent": "L2D_CACHE_HIT_RD", + "BriefDescription": "This event counts demand read counted by L2D_CACHE_RD that hits in the Level 2 data cache." + }, + { + "ArchStdEvent": "L2D_CACHE_HIT_WR", + "BriefDescription": "This event counts demand write counted by L2D_CACHE_WR that hits in the Level 2 data cache." + }, + { + "ArchStdEvent": "L2D_CACHE_HIT", + "BriefDescription": "This event counts access counted by L2D_CACHE that hits in the Level 2 data cache." + }, + { + "ArchStdEvent": "L2D_LFB_HIT_RD", + "BriefDescription": "This event counts demand access counted by L2D_CACHE_HIT_RD that hits a recently fetched line in the Level 2 cache." + }, + { + "ArchStdEvent": "L2D_LFB_HIT_WR", + "BriefDescription": "This event counts demand access counted by L2D_CACHE_HIT_WR that hits a recently fetched line in the Level 2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_PRF", + "BriefDescription": "This event counts fetch counted by either Level 2 data hardware prefetch or Level 2 data software prefetch." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_PRF", + "BriefDescription": "This event counts hardware prefetch counted by L2D_CACHE_PRF that causes a refill of the Level 2 data cache from outside of the Level 1 data cache." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_PERCYC", + "BriefDescription": "The counter counts by the number of cache refills counted by L2D_CACHE_REFILL in progress on each Processor cycle." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l3_cache.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l3_cache.json new file mode 100644 index 000000000000..3f3e0d22ac68 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/l3_cache.json @@ -0,0 +1,159 @@ +[ + { + "ArchStdEvent": "L3D_CACHE", + "BriefDescription": "This event counts operations that cause a cache access to the L3 cache, as defined by the sum of L2D_CACHE_REFILL_L3D_CACHE and L2D_CACHE_WB_VICTIM_CLEAN events." + }, + { + "ArchStdEvent": "L3D_CACHE_RD", + "BriefDescription": "This event counts access counted by L3D_CACHE that is a Memory-read operation, as defined by the L2D_CACHE_REFILL_L3D_CACHE events." + }, + { + "EventCode": "0x0390", + "EventName": "L2D_CACHE_REFILL_L3D_CACHE", + "BriefDescription": "This event counts operations that cause a cache access to the L3 cache." + }, + { + "EventCode": "0x0391", + "EventName": "L2D_CACHE_REFILL_L3D_CACHE_DM", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_CACHE caused by demand access." + }, + { + "EventCode": "0x0392", + "EventName": "L2D_CACHE_REFILL_L3D_CACHE_DM_RD", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_CACHE caused by demand read access." + }, + { + "EventCode": "0x0393", + "EventName": "L2D_CACHE_REFILL_L3D_CACHE_DM_WR", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_CACHE caused by demand write access." + }, + { + "EventCode": "0x0394", + "EventName": "L2D_CACHE_REFILL_L3D_CACHE_PRF", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_CACHE caused by prefetch access." + }, + { + "EventCode": "0x0395", + "EventName": "L2D_CACHE_REFILL_L3D_CACHE_HWPRF", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_CACHE caused by hardware prefetch access." + }, + { + "EventCode": "0x0396", + "EventName": "L2D_CACHE_REFILL_L3D_MISS", + "BriefDescription": "This event counts operations that cause a miss of the L3 cache." + }, + { + "EventCode": "0x0397", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_DM", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS caused by demand access." + }, + { + "EventCode": "0x0398", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_DM_RD", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS caused by demand read access." + }, + { + "EventCode": "0x0399", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_DM_WR", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS caused by demand write access." + }, + { + "EventCode": "0x039A", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_PRF", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS caused by prefetch access." + }, + { + "EventCode": "0x039B", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_HWPRF", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS caused by hardware prefetch access." + }, + { + "EventCode": "0x039C", + "EventName": "L2D_CACHE_REFILL_L3D_HIT", + "BriefDescription": "This event counts operations that cause a hit of the L3 cache." + }, + { + "EventCode": "0x039D", + "EventName": "L2D_CACHE_REFILL_L3D_HIT_DM", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_HIT caused by demand access." + }, + { + "EventCode": "0x039E", + "EventName": "L2D_CACHE_REFILL_L3D_HIT_DM_RD", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_HIT caused by demand read access." + }, + { + "EventCode": "0x039F", + "EventName": "L2D_CACHE_REFILL_L3D_HIT_DM_WR", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_HIT caused by demand write access." + }, + { + "EventCode": "0x03A0", + "EventName": "L2D_CACHE_REFILL_L3D_HIT_PRF", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_HIT caused by prefetch access." + }, + { + "EventCode": "0x03A1", + "EventName": "L2D_CACHE_REFILL_L3D_HIT_HWPRF", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_HIT caused by hardware prefetch access." + }, + { + "EventCode": "0x03A2", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT", + "BriefDescription": "This event counts the number of L3 cache misses where the requests hit the PFTGT buffer." + }, + { + "EventCode": "0x03A3", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT_DM", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT caused by demand access." + }, + { + "EventCode": "0x03A4", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT_DM_RD", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT caused by demand read access." + }, + { + "EventCode": "0x03A5", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT_DM_WR", + "BriefDescription": "This event counts L2D_CACHE_REFILL_L3D_MISS_PFTGT_HIT caused by demand write access." + }, + { + "EventCode": "0x03A6", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_L_MEM", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access the memory in the same socket as the requests." + }, + { + "EventCode": "0x03A7", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_FR_MEM", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access the memory in the different socket from the requests." + }, + { + "EventCode": "0x03A8", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_L_L2", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access the different L2 cache from the requests in the same Numa nodes as the requests." + }, + { + "EventCode": "0x03A9", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_NR_L2", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access L2 cache in the different Numa nodes from the requests in the same socket as the requests." + }, + { + "EventCode": "0x03AA", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_NR_L3", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access L3 cache in the different Numa nodes from the requests in the same socket as the requests." + }, + { + "EventCode": "0x03AB", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_FR_L2", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access L2 cache in the different socket from the requests." + }, + { + "EventCode": "0x03AC", + "EventName": "L2D_CACHE_REFILL_L3D_MISS_FR_L3", + "BriefDescription": "This event counts the number of L3 cache misses where the requests access L3 cache in the different socket from the requests." + }, + { + "ArchStdEvent": "L3D_CACHE_LMISS_RD", + "BriefDescription": "This event counts access counted by L3D_CACHE that is not completed by the L3D cache, and a Memory-read operation, as defined by the L2D_CACHE_REFILL_L3D_MISS events." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/ll_cache.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/ll_cache.json new file mode 100644 index 000000000000..a441b84729ab --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/ll_cache.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "LL_CACHE_RD", + "BriefDescription": "This event counts access counted by L3D_CACHE that is a Memory-read operation, as defined by the L2D_CACHE_REFILL_L3D_CACHE events." + }, + { + "ArchStdEvent": "LL_CACHE_MISS_RD", + "BriefDescription": "This event counts access counted by L3D_CACHE that is not completed by the L3D cache, and a Memory-read operation, as defined by the L2D_CACHE_REFILL_L3D_MISS events." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/memory.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/memory.json new file mode 100644 index 000000000000..4ef125e3a253 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/memory.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "MEM_ACCESS", + "BriefDescription": "This event counts architecturally executed memory-reading instructions and memory-writing instructions, as defined by the LDST_SPEC events." + }, + { + "ArchStdEvent": "MEM_ACCESS_RD", + "BriefDescription": "This event counts architecturally executed memory-reading instructions, as defined by the LD_SPEC events." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/pipeline.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/pipeline.json new file mode 100644 index 000000000000..3cc3105f4a5e --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/pipeline.json @@ -0,0 +1,208 @@ +[ + { + "EventCode": "0x01A0", + "EventName": "EAGA_VAL", + "BriefDescription": "This event counts valid cycles of EAGA pipeline." + }, + { + "EventCode": "0x01A1", + "EventName": "EAGB_VAL", + "BriefDescription": "This event counts valid cycles of EAGB pipeline." + }, + { + "EventCode": "0x01A3", + "EventName": "PRX_VAL", + "BriefDescription": "This event counts valid cycles of PRX pipeline." + }, + { + "EventCode": "0x01A4", + "EventName": "EXA_VAL", + "BriefDescription": "This event counts valid cycles of EXA pipeline." + }, + { + "EventCode": "0x01A5", + "EventName": "EXB_VAL", + "BriefDescription": "This event counts valid cycles of EXB pipeline." + }, + { + "EventCode": "0x01A6", + "EventName": "EXC_VAL", + "BriefDescription": "This event counts valid cycles of EXC pipeline." + }, + { + "EventCode": "0x01A7", + "EventName": "EXD_VAL", + "BriefDescription": "This event counts valid cycles of EXD pipeline." + }, + { + "EventCode": "0x01A8", + "EventName": "FLA_VAL", + "BriefDescription": "This event counts valid cycles of FLA pipeline." + }, + { + "EventCode": "0x01A9", + "EventName": "FLB_VAL", + "BriefDescription": "This event counts valid cycles of FLB pipeline." + }, + { + "EventCode": "0x01AA", + "EventName": "STEA_VAL", + "BriefDescription": "This event counts valid cycles of STEA pipeline." + }, + { + "EventCode": "0x01AB", + "EventName": "STEB_VAL", + "BriefDescription": "This event counts valid cycles of STEB pipeline." + }, + { + "EventCode": "0x01AC", + "EventName": "STFL_VAL", + "BriefDescription": "This event counts valid cycles of STFL pipeline." + }, + { + "EventCode": "0x01AD", + "EventName": "STPX_VAL", + "BriefDescription": "This event counts valid cycles of STPX pipeline." + }, + { + "EventCode": "0x01B0", + "EventName": "FLA_VAL_PRD_CNT", + "BriefDescription": "This event counts the number of 1's in the predicate bits of request in FLA pipeline, where it is corrected so that it becomes 32 when all bits are 1." + }, + { + "EventCode": "0x01B1", + "EventName": "FLB_VAL_PRD_CNT", + "BriefDescription": "This event counts the number of 1's in the predicate bits of request in FLB pipeline, where it is corrected so that it becomes 32 when all bits are 1." + }, + { + "EventCode": "0x01B2", + "EventName": "FLA_VAL_FOR_PRD", + "BriefDescription": "This event counts valid cycles of FLA pipeline." + }, + { + "EventCode": "0x01B3", + "EventName": "FLB_VAL_FOR_PRD", + "BriefDescription": "This event counts valid cycles of FLB pipeline." + }, + { + "EventCode": "0x0240", + "EventName": "L1_PIPE0_VAL", + "BriefDescription": "This event counts valid cycles of L1D cache pipeline#0." + }, + { + "EventCode": "0x0241", + "EventName": "L1_PIPE1_VAL", + "BriefDescription": "This event counts valid cycles of L1D cache pipeline#1." + }, + { + "EventCode": "0x0242", + "EventName": "L1_PIPE2_VAL", + "BriefDescription": "This event counts valid cycles of L1D cache pipeline#2." + }, + { + "EventCode": "0x0250", + "EventName": "L1_PIPE0_COMP", + "BriefDescription": "This event counts completed requests in L1D cache pipeline#0." + }, + { + "EventCode": "0x0251", + "EventName": "L1_PIPE1_COMP", + "BriefDescription": "This event counts completed requests in L1D cache pipeline#1." + }, + { + "EventCode": "0x025A", + "EventName": "L1_PIPE_ABORT_STLD_INTLK", + "BriefDescription": "This event counts aborted requests in L1D pipelines that due to store-load interlock." + }, + { + "EventCode": "0x026C", + "EventName": "L1I_PIPE_COMP", + "BriefDescription": "This event counts completed requests in L1I cache pipeline." + }, + { + "EventCode": "0x026D", + "EventName": "L1I_PIPE_VAL", + "BriefDescription": "This event counts valid cycles of L1I cache pipeline." + }, + { + "EventCode": "0x0278", + "EventName": "L1_PIPE0_VAL_IU_TAG_ADRS_SCE", + "BriefDescription": "This event counts requests in L1D cache pipeline#0 that its sce bit of tagged address is 1." + }, + { + "EventCode": "0x0279", + "EventName": "L1_PIPE1_VAL_IU_TAG_ADRS_SCE", + "BriefDescription": "This event counts requests in L1D cache pipeline#1 that its sce bit of tagged address is 1." + }, + { + "EventCode": "0x02A0", + "EventName": "L1_PIPE0_VAL_IU_NOT_SEC0", + "BriefDescription": "This event counts requests in L1D cache pipeline#0 that its sector cache ID is not 0." + }, + { + "EventCode": "0x02A1", + "EventName": "L1_PIPE1_VAL_IU_NOT_SEC0", + "BriefDescription": "This event counts requests in L1D cache pipeline#1 that its sector cache ID is not 0." + }, + { + "EventCode": "0x02B0", + "EventName": "L1_PIPE_COMP_GATHER_2FLOW", + "BriefDescription": "This event counts the number of times where 2 elements of the gather instructions became 2 flows because 2 elements could not be combined." + }, + { + "EventCode": "0x02B1", + "EventName": "L1_PIPE_COMP_GATHER_1FLOW", + "BriefDescription": "This event counts the number of times where 2 elements of the gather instructions became 1 flow because 2 elements could be combined." + }, + { + "EventCode": "0x02B2", + "EventName": "L1_PIPE_COMP_GATHER_0FLOW", + "BriefDescription": "This event counts the number of times where 2 elements of the gather instructions became 0 flow because both predicate values are 0." + }, + { + "EventCode": "0x02B3", + "EventName": "L1_PIPE_COMP_SCATTER_1FLOW", + "BriefDescription": "This event counts the number of flows of the scatter instructions." + }, + { + "EventCode": "0x02B8", + "EventName": "L1_PIPE0_COMP_PRD_CNT", + "BriefDescription": "This event counts the number of 1's in the predicate bits of request in L1D cache pipeline#0, where it is corrected so that it becomes 64 when all bits are 1." + }, + { + "EventCode": "0x02B9", + "EventName": "L1_PIPE1_COMP_PRD_CNT", + "BriefDescription": "This event counts the number of 1's in the predicate bits of request in L1D cache pipeline#1, where it is corrected so that it becomes 64 when all bits are 1." + }, + { + "EventCode": "0x0330", + "EventName": "L2_PIPE_VAL", + "BriefDescription": "This event counts valid cycles of L2 cache pipeline." + }, + { + "EventCode": "0x0350", + "EventName": "L2_PIPE_COMP_ALL", + "BriefDescription": "This event counts completed requests in L2 cache pipeline." + }, + { + "EventCode": "0x0370", + "EventName": "L2_PIPE_COMP_PF_L2MIB_MCH", + "BriefDescription": "This event counts operations where software or hardware prefetch hits an L2 cache refill buffer allocated by demand access." + }, + { + "ArchStdEvent": "STALL_FRONTEND_TLB", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_MEMBOUND when there is a demand instruction miss in the instruction TLB." + }, + { + "ArchStdEvent": "STALL_BACKEND_TLB", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_MEMBOUND when there is a demand data miss in the data TLB." + }, + { + "ArchStdEvent": "STALL_BACKEND_ST", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_MEMBOUND when the backend is stalled waiting for a store." + }, + { + "ArchStdEvent": "STALL_BACKEND_ILOCK", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND when operations are available from the frontend but at least one is not ready to be sent to the backend because of an input dependency." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/pmu.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/pmu.json new file mode 100644 index 000000000000..65bd6cdd0dd5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/pmu.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "PMU_OVFS", + "BriefDescription": "This event counts the event generated each time one of the condition occurs described in Arm Architecture Reference Manual for A-profile architecture. This event is only for output to the trace unit." + }, + { + "ArchStdEvent": "PMU_HOVFS", + "BriefDescription": "This event counts the event generated each time an event is counted by an event counter <n> and all of the condition occur described in Arm Architecture Reference Manual for A-profile architecture. This event is only for output to the trace unit." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/retired.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/retired.json new file mode 100644 index 000000000000..de56aafec2dc --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/retired.json @@ -0,0 +1,30 @@ +[ + { + "ArchStdEvent": "SW_INCR", + "BriefDescription": "This event counts on writes to the PMSWINC register." + }, + { + "ArchStdEvent": "INST_RETIRED", + "BriefDescription": "This event counts every architecturally executed instruction." + }, + { + "ArchStdEvent": "CID_WRITE_RETIRED", + "BriefDescription": "This event counts every write to CONTEXTIDR." + }, + { + "ArchStdEvent": "BR_RETIRED", + "BriefDescription": "This event counts architecturally executed branch instruction." + }, + { + "ArchStdEvent": "BR_MIS_PRED_RETIRED", + "BriefDescription": "This event counts architecturally executed branch instruction which was mispredicted." + }, + { + "ArchStdEvent": "OP_RETIRED", + "BriefDescription": "This event counts every architecturally executed micro-operation." + }, + { + "ArchStdEvent": "UOP_RETIRED", + "BriefDescription": "This event counts micro-operation that would be executed in a Simple sequential execution of the program." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/spec_operation.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/spec_operation.json new file mode 100644 index 000000000000..4841b43e2871 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/spec_operation.json @@ -0,0 +1,171 @@ +[ + { + "ArchStdEvent": "BR_MIS_PRED", + "BriefDescription": "This event counts each correction to the predicted program flow that occurs because of a misprediction from, or no prediction from, the branch prediction resources and that relates to instructions that the branch prediction resources are capable of predicting." + }, + { + "ArchStdEvent": "BR_PRED", + "BriefDescription": "This event counts every branch or other change in the program flow that the branch prediction resources are capable of predicting." + }, + { + "ArchStdEvent": "INST_SPEC", + "BriefDescription": "This event counts every architecturally executed instruction." + }, + { + "ArchStdEvent": "OP_SPEC", + "BriefDescription": "This event counts every speculatively executed micro-operation." + }, + { + "ArchStdEvent": "LDREX_SPEC", + "BriefDescription": "This event counts architecturally executed load-exclusive instructions." + }, + { + "ArchStdEvent": "STREX_SPEC", + "BriefDescription": "This event counts architecturally executed store-exclusive instructions." + }, + { + "ArchStdEvent": "LD_SPEC", + "BriefDescription": "This event counts architecturally executed memory-reading instructions, as defined by the LD_RETIRED event." + }, + { + "ArchStdEvent": "ST_SPEC", + "BriefDescription": "This event counts architecturally executed memory-writing instructions, as defined by the ST_RETIRED event. This event counts DCZVA as a store operation." + }, + { + "ArchStdEvent": "LDST_SPEC", + "BriefDescription": "This event counts architecturally executed memory-reading instructions and memory-writing instructions, as defined by the LD_RETIRED and ST_RETIRED events." + }, + { + "ArchStdEvent": "DP_SPEC", + "BriefDescription": "This event counts architecturally executed integer data-processing instructions. See DP_SPEC of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "ASE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD data-processing instructions." + }, + { + "ArchStdEvent": "VFP_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point data-processing instructions." + }, + { + "ArchStdEvent": "PC_WRITE_SPEC", + "BriefDescription": "This event counts only software changes of the PC that defined by the instruction architecturally executed, condition code check pass, software change of the PC event." + }, + { + "ArchStdEvent": "CRYPTO_SPEC", + "BriefDescription": "This event counts architecturally executed cryptographic instructions, except PMULL and VMULL." + }, + { + "ArchStdEvent": "BR_IMMED_SPEC", + "BriefDescription": "This event counts architecturally executed immediate branch instructions." + }, + { + "ArchStdEvent": "BR_RETURN_SPEC", + "BriefDescription": "This event counts architecturally executed procedure return operations that defined by the BR_RETURN_RETIRED event." + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC", + "BriefDescription": "This event counts architecturally executed indirect branch instructions that includes software change of the PC other than exception-generating instructions and immediate branch instructions." + }, + { + "ArchStdEvent": "ISB_SPEC", + "BriefDescription": "This event counts architecturally executed Instruction Synchronization Barrier instructions." + }, + { + "ArchStdEvent": "DSB_SPEC", + "BriefDescription": "This event counts architecturally executed Data Synchronization Barrier instructions." + }, + { + "ArchStdEvent": "DMB_SPEC", + "BriefDescription": "This event counts architecturally executed Data Memory Barrier instructions, excluding the implied barrier operations of load/store operations with release consistency semantics." + }, + { + "ArchStdEvent": "CSDB_SPEC", + "BriefDescription": "This event counts speculatively executed control speculation barrier instructions." + }, + { + "EventCode": "0x0108", + "EventName": "PRD_SPEC", + "BriefDescription": "This event counts architecturally executed operations that using predicate register." + }, + { + "EventCode": "0x0109", + "EventName": "IEL_SPEC", + "BriefDescription": "This event counts architecturally executed inter-element manipulation operations." + }, + { + "EventCode": "0x010A", + "EventName": "IREG_SPEC", + "BriefDescription": "This event counts architecturally executed inter-register manipulation operations." + }, + { + "EventCode": "0x011A", + "EventName": "BC_LD_SPEC", + "BriefDescription": "This event counts architecturally executed SIMD broadcast floating-point load operations." + }, + { + "EventCode": "0x011B", + "EventName": "DCZVA_SPEC", + "BriefDescription": "This event counts architecturally executed zero blocking operations due to the DC ZVA instruction." + }, + { + "EventCode": "0x0121", + "EventName": "EFFECTIVE_INST_SPEC", + "BriefDescription": "This event counts architecturally executed instructions, excluding the MOVPRFX instruction." + }, + { + "EventCode": "0x0123", + "EventName": "PRE_INDEX_SPEC", + "BriefDescription": "This event counts architecturally executed operations that uses pre-index as its addressing mode." + }, + { + "EventCode": "0x0124", + "EventName": "POST_INDEX_SPEC", + "BriefDescription": "This event counts architecturally executed operations that uses post-index as its addressing mode." + }, + { + "EventCode": "0x0139", + "EventName": "UOP_SPLIT", + "BriefDescription": "This event counts the occurrence count of the micro-operation split." + }, + { + "ArchStdEvent": "ASE_INST_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD operations." + }, + { + "ArchStdEvent": "INT_SPEC", + "BriefDescription": "This event counts architecturally executed operations due to scalar, Advanced SIMD, and SVE instructions listed in Integer instructions section of ARMv9 Reference Manual." + }, + { + "ArchStdEvent": "INT_DIV_SPEC", + "BriefDescription": "This event counts architecturally executed integer divide operation." + }, + { + "ArchStdEvent": "INT_DIV64_SPEC", + "BriefDescription": "This event counts architecturally executed 64-bit integer divide operation." + }, + { + "ArchStdEvent": "INT_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed integer multiply operation." + }, + { + "ArchStdEvent": "INT_MUL64_SPEC", + "BriefDescription": "This event counts architecturally executed integer 64-bit x 64-bit multiply operation." + }, + { + "ArchStdEvent": "INT_MULH64_SPEC", + "BriefDescription": "This event counts architecturally executed integer 64-bit x 64-bit multiply returning high part operation." + }, + { + "ArchStdEvent": "NONFP_SPEC", + "BriefDescription": "This event counts architecturally executed non-floating-point operations." + }, + { + "ArchStdEvent": "INT_SCALE_OPS_SPEC", + "BriefDescription": "This event counts each integer ALU operation counted by SVE_INT_SPEC. See ALU operation counts section of ARMv9 Reference Manual for information on the counter increment for different types of instruction." + }, + { + "ArchStdEvent": "INT_FIXED_OPS_SPEC", + "BriefDescription": "This event counts each integer ALU operation counted by INT_SPEC that is not counted by SVE_INT_SPEC. See ALU operation counts section of ARMv9 Reference Manual for information on the counter increment for different types of instruction." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/stall.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/stall.json new file mode 100644 index 000000000000..5fb81e2a0a07 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/stall.json @@ -0,0 +1,94 @@ +[ + { + "ArchStdEvent": "STALL_FRONTEND", + "BriefDescription": "This event counts every cycle counted by the CPU_CYCLES event on that no operation was issued because there are no operations available to issue for this PE from the frontend." + }, + { + "ArchStdEvent": "STALL_BACKEND", + "BriefDescription": "This event counts every cycle counted by the CPU_CYCLES event on that no operation was issued because the backend is unable to accept any operations." + }, + { + "ArchStdEvent": "STALL", + "BriefDescription": "This event counts every cycle that no instruction was dispatched from decode unit." + }, + { + "ArchStdEvent": "STALL_SLOT_BACKEND", + "BriefDescription": "This event counts every cycle that no instruction was dispatched from decode unit due to the backend." + }, + { + "ArchStdEvent": "STALL_SLOT_FRONTEND", + "BriefDescription": "This event counts every cycle that no instruction was dispatched from decode unit due to the frontend." + }, + { + "ArchStdEvent": "STALL_SLOT", + "BriefDescription": "This event counts every cycle that no instruction or operation Slot was dispatched from decode unit." + }, + { + "ArchStdEvent": "STALL_BACKEND_MEM", + "BriefDescription": "This event counts every cycle that no instruction was dispatched from decode unit due to memory stall." + }, + { + "ArchStdEvent": "STALL_FRONTEND_MEMBOUND", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND when no instructions are delivered from the memory system." + }, + { + "ArchStdEvent": "STALL_FRONTEND_L1I", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_MEMBOUND when there is a demand instruction miss in the first level of instruction cache." + }, + { + "ArchStdEvent": "STALL_FRONTEND_L2I", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_MEMBOUND when there is a demand instruction miss in the second level of instruction cache." + }, + { + "ArchStdEvent": "STALL_FRONTEND_MEM", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_MEMBOUND when there is a demand instruction miss in the last level of instruction cache within the PE clock domain or a non-cacheable instruction fetch in progress." + }, + { + "ArchStdEvent": "STALL_FRONTEND_CPUBOUND", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND when the frontend is stalled on a frontend processor resource, not including memory." + }, + { + "ArchStdEvent": "STALL_FRONTEND_FLOW", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_CPUBOUND when the frontend is stalled on unavailability of prediction flow resources." + }, + { + "ArchStdEvent": "STALL_FRONTEND_FLUSH", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_CPUBOUND when the frontend is recovering from a pipeline flush." + }, + { + "ArchStdEvent": "STALL_FRONTEND_RENAME", + "BriefDescription": "This event counts every cycle counted by STALL_FRONTEND_CPUBOUND when operations are available from the frontend but at least one is not ready to be sent to the backend because no rename register is available." + }, + { + "ArchStdEvent": "STALL_BACKEND_MEMBOUND", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND when the backend is waiting for a memory access to complete." + }, + { + "ArchStdEvent": "STALL_BACKEND_L1D", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_MEMBOUND when there is a demand data miss in L1D cache." + }, + { + "ArchStdEvent": "STALL_BACKEND_L2D", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_MEMBOUND when there is a demand data miss in L2D cache." + }, + { + "ArchStdEvent": "STALL_BACKEND_CPUBOUND", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND when the backend is stalled on a processor resource, not including memory." + }, + { + "ArchStdEvent": "STALL_BACKEND_BUSY", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND when operations are available from the frontend but the backend is not able to accept an operation because an execution unit is busy." + }, + { + "ArchStdEvent": "STALL_BACKEND_RENAME", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_CPUBOUND when operations are available from the frontend but at least one is not ready to be sent to the backend because no rename register is available." + }, + { + "ArchStdEvent": "STALL_BACKEND_ATOMIC", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_MEMBOUND when the backend is processing an Atomic operation." + }, + { + "ArchStdEvent": "STALL_BACKEND_MEMCPYSET", + "BriefDescription": "This event counts every cycle counted by STALL_BACKEND_MEMBOUND when the backend is processing a Memory Copy or Set instruction." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/sve.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/sve.json new file mode 100644 index 000000000000..e66b5af00f90 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/sve.json @@ -0,0 +1,254 @@ +[ + { + "ArchStdEvent": "SIMD_INST_RETIRED", + "BriefDescription": "This event counts architecturally executed SIMD instructions, excluding the Advanced SIMD scalar instructions and the instructions listed in Non-SIMD SVE instructions section of ARMv9 Reference Manual." + }, + { + "ArchStdEvent": "SVE_INST_RETIRED", + "BriefDescription": "This event counts architecturally executed SVE instructions, including the instructions listed in Non-SIMD SVE instructions section of ARMv9 Reference Manual." + }, + { + "ArchStdEvent": "SVE_INST_SPEC", + "BriefDescription": "This event counts architecturally executed SVE instructions, including the instructions listed in Non-SIMD SVE instructions section of ARMv9 Reference Manual." + }, + { + "ArchStdEvent": "ASE_SVE_INST_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE operations." + }, + { + "ArchStdEvent": "UOP_SPEC", + "BriefDescription": "This event counts all architecturally executed micro-operations." + }, + { + "ArchStdEvent": "SVE_MATH_SPEC", + "BriefDescription": "This event counts architecturally executed math function operations due to the SVE FTSMUL, FTMAD, FTSSEL, and FEXPA instructions." + }, + { + "ArchStdEvent": "FP_SPEC", + "BriefDescription": "This event counts architecturally executed operations due to scalar, Advanced SIMD, and SVE instructions listed in Floating-point instructions section of ARMv9 Reference Manual." + }, + { + "ArchStdEvent": "FP_FMA_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point fused multiply-add and multiply-subtract operations." + }, + { + "ArchStdEvent": "FP_RECPE_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point reciprocal estimate operations due to the Advanced SIMD scalar, Advanced SIMD vector, and SVE FRECPE and FRSQRTE instructions." + }, + { + "ArchStdEvent": "FP_CVT_SPEC", + "BriefDescription": "This event counts architecturally executed floating-point convert operations due to the scalar, Advanced SIMD, and SVE floating-point conversion instructions listed in Floating-point conversions section of ARMv9 Reference Manual." + }, + { + "ArchStdEvent": "ASE_INT_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD integer operations." + }, + { + "ArchStdEvent": "SVE_INT_SPEC", + "BriefDescription": "This event counts architecturally executed SVE integer operations." + }, + { + "ArchStdEvent": "ASE_SVE_INT_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE integer operations." + }, + { + "ArchStdEvent": "SVE_INT_DIV_SPEC", + "BriefDescription": "This event counts architecturally executed SVE integer divide operation." + }, + { + "ArchStdEvent": "SVE_INT_DIV64_SPEC", + "BriefDescription": "This event counts architecturally executed SVE 64-bit integer divide operation." + }, + { + "ArchStdEvent": "ASE_INT_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD integer multiply operation." + }, + { + "ArchStdEvent": "SVE_INT_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed SVE integer multiply operation." + }, + { + "ArchStdEvent": "ASE_SVE_INT_MUL_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE integer multiply operations." + }, + { + "ArchStdEvent": "SVE_INT_MUL64_SPEC", + "BriefDescription": "This event counts architecturally executed SVE integer 64-bit x 64-bit multiply operation." + }, + { + "ArchStdEvent": "SVE_INT_MULH64_SPEC", + "BriefDescription": "This event counts architecturally executed SVE integer 64-bit x 64-bit multiply returning high part operations." + }, + { + "ArchStdEvent": "ASE_NONFP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD non-floating-point operations." + }, + { + "ArchStdEvent": "SVE_NONFP_SPEC", + "BriefDescription": "This event counts architecturally executed SVE non-floating-point operations." + }, + { + "ArchStdEvent": "ASE_SVE_NONFP_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE non-floating-point operations." + }, + { + "ArchStdEvent": "ASE_INT_VREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD integer reduction operation." + }, + { + "ArchStdEvent": "SVE_INT_VREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed SVE integer reduction operation." + }, + { + "ArchStdEvent": "ASE_SVE_INT_VREDUCE_SPEC", + "BriefDescription": "This event counts architecturally executed Advanced SIMD and SVE integer reduction operations." + }, + { + "ArchStdEvent": "SVE_PERM_SPEC", + "BriefDescription": "This event counts architecturally executed vector or predicate permute operation." + }, + { + "ArchStdEvent": "SVE_XPIPE_Z2R_SPEC", + "BriefDescription": "This event counts architecturally executed vector to general-purpose scalar cross-pipeline transfer operation." + }, + { + "ArchStdEvent": "SVE_XPIPE_R2Z_SPEC", + "BriefDescription": "This event counts architecturally executed general-purpose scalar to vector cross-pipeline transfer operation." + }, + { + "ArchStdEvent": "SVE_PGEN_SPEC", + "BriefDescription": "This event counts architecturally executed predicate-generating operation." + }, + { + "ArchStdEvent": "SVE_PGEN_FLG_SPEC", + "BriefDescription": "This event counts architecturally executed predicate-generating operation that sets condition flags." + }, + { + "ArchStdEvent": "SVE_PPERM_SPEC", + "BriefDescription": "This event counts architecturally executed predicate permute operation." + }, + { + "ArchStdEvent": "SVE_PRED_SPEC", + "BriefDescription": "This event counts architecturally executed SIMD data-processing and load/store operations due to SVE instructions with a Governing predicate operand that determines the Active elements." + }, + { + "ArchStdEvent": "SVE_MOVPRFX_SPEC", + "BriefDescription": "This event counts architecturally executed operations due to MOVPRFX instructions, whether or not they were fused with the prefixed instruction." + }, + { + "ArchStdEvent": "SVE_MOVPRFX_Z_SPEC", + "BriefDescription": "This event counts architecturally executed operation counted by SVE_MOVPRFX_SPEC where the operation uses zeroing predication." + }, + { + "ArchStdEvent": "SVE_MOVPRFX_M_SPEC", + "BriefDescription": "This event counts architecturally executed operation counted by SVE_MOVPRFX_SPEC where the operation uses merging predication." + }, + { + "ArchStdEvent": "SVE_MOVPRFX_U_SPEC", + "BriefDescription": "This event counts architecturally executed operations due to MOVPRFX instructions that were not fused with the prefixed instruction." + }, + { + "ArchStdEvent": "ASE_SVE_LD_SPEC", + "BriefDescription": "This event counts architecturally executed operations that read from memory due to SVE and Advanced SIMD load instructions." + }, + { + "ArchStdEvent": "ASE_SVE_ST_SPEC", + "BriefDescription": "This event counts architecturally executed operations that write to memory due to SVE and Advanced SIMD store instructions." + }, + { + "ArchStdEvent": "PRF_SPEC", + "BriefDescription": "This event counts architecturally executed prefetch operations due to scalar PRFM, PRFUM and SVE PRF instructions." + }, + { + "ArchStdEvent": "BASE_LD_REG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that read from memory due to an instruction that loads a general-purpose register." + }, + { + "ArchStdEvent": "BASE_ST_REG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that write to memory due to an instruction that stores a general-purpose register, excluding the DC ZVA instruction." + }, + { + "ArchStdEvent": "SVE_LDR_REG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that read from memory due to an SVE LDR instruction." + }, + { + "ArchStdEvent": "SVE_STR_REG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that write to memory due to an SVE STR instruction." + }, + { + "ArchStdEvent": "SVE_LDR_PREG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that read from memory due to an SVE LDR (predicate) instruction." + }, + { + "ArchStdEvent": "SVE_STR_PREG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that write to memory due to an SVE STR (predicate) instruction." + }, + { + "ArchStdEvent": "SVE_PRF_CONTIG_SPEC", + "BriefDescription": "This event counts architecturally executed operations that prefetch memory due to an SVE predicated single contiguous element prefetch instruction." + }, + { + "ArchStdEvent": "SVE_LDNT_CONTIG_SPEC", + "BriefDescription": "This event counts architecturally executed operation that reads from memory with a non-temporal hint due to an SVE non-temporal contiguous element load instruction." + }, + { + "ArchStdEvent": "SVE_STNT_CONTIG_SPEC", + "BriefDescription": "This event counts architecturally executed operation that writes to memory with a non-temporal hint due to an SVE non-temporal contiguous element store instruction." + }, + { + "ArchStdEvent": "ASE_SVE_LD_MULTI_SPEC", + "BriefDescription": "This event counts architecturally executed operations that read from memory due to SVE and Advanced SIMD multiple vector contiguous structure load instructions." + }, + { + "ArchStdEvent": "ASE_SVE_ST_MULTI_SPEC", + "BriefDescription": "This event counts architecturally executed operations that write to memory due to SVE and Advanced SIMD multiple vector contiguous structure store instructions." + }, + { + "ArchStdEvent": "SVE_LD_GATHER_SPEC", + "BriefDescription": "This event counts architecturally executed operations that read from memory due to SVE non-contiguous gather-load instructions." + }, + { + "ArchStdEvent": "SVE_ST_SCATTER_SPEC", + "BriefDescription": "This event counts architecturally executed operations that write to memory due to SVE non-contiguous scatter-store instructions." + }, + { + "ArchStdEvent": "SVE_PRF_GATHER_SPEC", + "BriefDescription": "This event counts architecturally executed operations that prefetch memory due to SVE non-contiguous gather-prefetch instructions." + }, + { + "ArchStdEvent": "SVE_LDFF_SPEC", + "BriefDescription": "This event counts architecturally executed memory read operations due to SVE First-fault and Non-fault load instructions." + }, + { + "ArchStdEvent": "FP_HP_SCALE_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed SVE half-precision arithmetic operations. See FP_HP_SCALE_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by 8, or by 16 for operations that would also be counted by SVE_FP_FMA_SPEC." + }, + { + "ArchStdEvent": "FP_HP_FIXED_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed v8SIMD&FP half-precision arithmetic operations. See FP_HP_FIXED_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by the number of 16-bit elements for Advanced SIMD operations, or by 1 for scalar operations, and by twice those amounts for operations that would also be counted by FP_FMA_SPEC." + }, + { + "ArchStdEvent": "FP_SP_SCALE_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed SVE single-precision arithmetic operations. See FP_SP_SCALE_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by 4, or by 8 for operations that would also be counted by SVE_FP_FMA_SPEC." + }, + { + "ArchStdEvent": "FP_SP_FIXED_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed v8SIMD&FP single-precision arithmetic operations. See FP_SP_FIXED_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by the number of 32-bit elements for Advanced SIMD operations, or by 1 for scalar operations, and by twice those amounts for operations that would also be counted by FP_FMA_SPEC." + }, + { + "ArchStdEvent": "FP_DP_SCALE_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed SVE double-precision arithmetic operations. See FP_DP_SCALE_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by 2, or by 4 for operations that would also be counted by SVE_FP_FMA_SPEC." + }, + { + "ArchStdEvent": "FP_DP_FIXED_OPS_SPEC", + "BriefDescription": "This event counts architecturally executed v8SIMD&FP double-precision arithmetic operations. See FP_DP_FIXED_OPS_SPEC of ARMv9 Reference Manual for more information. This event counter is incremented by 2 for Advanced SIMD operations, or by 1 for scalar operations, and by twice those amounts for operations that would also be counted by FP_FMA_SPEC." + }, + { + "ArchStdEvent": "ASE_SVE_INT_DOT_SPEC", + "BriefDescription": "This event counts architecturally executed microarchitectural Advanced SIMD or SVE integer dot-product operation." + }, + { + "ArchStdEvent": "ASE_SVE_INT_MMLA_SPEC", + "BriefDescription": "This event counts architecturally executed microarchitectural Advanced SIMD or SVE integer matrix multiply operation." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/tlb.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/tlb.json new file mode 100644 index 000000000000..edc7cb8696c8 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/tlb.json @@ -0,0 +1,362 @@ +[ + { + "ArchStdEvent": "L1I_TLB_REFILL", + "BriefDescription": "This event counts operations that cause a TLB refill of the L1I TLB. See L1I_TLB_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL", + "BriefDescription": "This event counts operations that cause a TLB refill of the L1D TLB. See L1D_TLB_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1D_TLB", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D TLB. See L1D_TLB of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L1I_TLB", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I TLB. See L1I_TLB of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL", + "BriefDescription": "This event counts operations that cause a TLB refill of the L2D TLB. See L2D_TLB_REFILL of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "L2D_TLB", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D TLB. See L2D_TLB of ARMv9 Reference Manual for more information." + }, + { + "ArchStdEvent": "DTLB_WALK", + "BriefDescription": "This event counts data TLB access with at least one translation table walk." + }, + { + "ArchStdEvent": "ITLB_WALK", + "BriefDescription": "This event counts instruction TLB access with at least one translation table walk." + }, + { + "EventCode": "0x0C00", + "EventName": "L1I_TLB_4K", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 4KB page." + }, + { + "EventCode": "0x0C01", + "EventName": "L1I_TLB_64K", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 64KB page." + }, + { + "EventCode": "0x0C02", + "EventName": "L1I_TLB_2M", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 2MB page." + }, + { + "EventCode": "0x0C03", + "EventName": "L1I_TLB_32M", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 32MB page." + }, + { + "EventCode": "0x0C04", + "EventName": "L1I_TLB_512M", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 512MB page." + }, + { + "EventCode": "0x0C05", + "EventName": "L1I_TLB_1G", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 1GB page." + }, + { + "EventCode": "0x0C06", + "EventName": "L1I_TLB_16G", + "BriefDescription": "This event counts operations that cause a TLB access to the L1I in 16GB page." + }, + { + "EventCode": "0x0C08", + "EventName": "L1D_TLB_4K", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 4KB page." + }, + { + "EventCode": "0x0C09", + "EventName": "L1D_TLB_64K", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 64KB page." + }, + { + "EventCode": "0x0C0A", + "EventName": "L1D_TLB_2M", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 2MB page." + }, + { + "EventCode": "0x0C0B", + "EventName": "L1D_TLB_32M", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 32MB page." + }, + { + "EventCode": "0x0C0C", + "EventName": "L1D_TLB_512M", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 512MB page." + }, + { + "EventCode": "0x0C0D", + "EventName": "L1D_TLB_1G", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 1GB page." + }, + { + "EventCode": "0x0C0E", + "EventName": "L1D_TLB_16G", + "BriefDescription": "This event counts operations that cause a TLB access to the L1D in 16GB page." + }, + { + "EventCode": "0x0C10", + "EventName": "L1I_TLB_REFILL_4K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 4KB page." + }, + { + "EventCode": "0x0C11", + "EventName": "L1I_TLB_REFILL_64K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 64KB page." + }, + { + "EventCode": "0x0C12", + "EventName": "L1I_TLB_REFILL_2M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 2MB page." + }, + { + "EventCode": "0x0C13", + "EventName": "L1I_TLB_REFILL_32M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 32MB page." + }, + { + "EventCode": "0x0C14", + "EventName": "L1I_TLB_REFILL_512M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 512MB page." + }, + { + "EventCode": "0x0C15", + "EventName": "L1I_TLB_REFILL_1G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 1GB page." + }, + { + "EventCode": "0x0C16", + "EventName": "L1I_TLB_REFILL_16G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1I in 16GB page." + }, + { + "EventCode": "0x0C18", + "EventName": "L1D_TLB_REFILL_4K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 4KB page." + }, + { + "EventCode": "0x0C19", + "EventName": "L1D_TLB_REFILL_64K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 64KB page." + }, + { + "EventCode": "0x0C1A", + "EventName": "L1D_TLB_REFILL_2M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 2MB page." + }, + { + "EventCode": "0x0C1B", + "EventName": "L1D_TLB_REFILL_32M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 32MB page." + }, + { + "EventCode": "0x0C1C", + "EventName": "L1D_TLB_REFILL_512M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 512MB page." + }, + { + "EventCode": "0x0C1D", + "EventName": "L1D_TLB_REFILL_1G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 1GB page." + }, + { + "EventCode": "0x0C1E", + "EventName": "L1D_TLB_REFILL_16G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L1D in 16GB page." + }, + { + "EventCode": "0x0C20", + "EventName": "L2I_TLB_4K", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 4KB page." + }, + { + "EventCode": "0x0C21", + "EventName": "L2I_TLB_64K", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 64KB page." + }, + { + "EventCode": "0x0C22", + "EventName": "L2I_TLB_2M", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 2MB page." + }, + { + "EventCode": "0x0C23", + "EventName": "L2I_TLB_32M", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 32MB page." + }, + { + "EventCode": "0x0C24", + "EventName": "L2I_TLB_512M", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 512MB page." + }, + { + "EventCode": "0x0C25", + "EventName": "L2I_TLB_1G", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 1GB page." + }, + { + "EventCode": "0x0C26", + "EventName": "L2I_TLB_16G", + "BriefDescription": "This event counts operations that cause a TLB access to the L2I in 16GB page." + }, + { + "EventCode": "0x0C28", + "EventName": "L2D_TLB_4K", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 4KB page." + }, + { + "EventCode": "0x0C29", + "EventName": "L2D_TLB_64K", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 64KB page." + }, + { + "EventCode": "0x0C2A", + "EventName": "L2D_TLB_2M", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 2MB page." + }, + { + "EventCode": "0x0C2B", + "EventName": "L2D_TLB_32M", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 32MB page." + }, + { + "EventCode": "0x0C2C", + "EventName": "L2D_TLB_512M", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 512MB page." + }, + { + "EventCode": "0x0C2D", + "EventName": "L2D_TLB_1G", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 1GB page." + }, + { + "EventCode": "0x0C2E", + "EventName": "L2D_TLB_16G", + "BriefDescription": "This event counts operations that cause a TLB access to the L2D in 16GB page." + }, + { + "EventCode": "0x0C30", + "EventName": "L2I_TLB_REFILL_4K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2Iin 4KB page." + }, + { + "EventCode": "0x0C31", + "EventName": "L2I_TLB_REFILL_64K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2I in 64KB page." + }, + { + "EventCode": "0x0C32", + "EventName": "L2I_TLB_REFILL_2M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2I in 2MB page." + }, + { + "EventCode": "0x0C33", + "EventName": "L2I_TLB_REFILL_32M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2I in 32MB page." + }, + { + "EventCode": "0x0C34", + "EventName": "L2I_TLB_REFILL_512M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2I in 512MB page." + }, + { + "EventCode": "0x0C35", + "EventName": "L2I_TLB_REFILL_1G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2I in 1GB page." + }, + { + "EventCode": "0x0C36", + "EventName": "L2I_TLB_REFILL_16G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2I in 16GB page." + }, + { + "EventCode": "0x0C38", + "EventName": "L2D_TLB_REFILL_4K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 4KB page." + }, + { + "EventCode": "0x0C39", + "EventName": "L2D_TLB_REFILL_64K", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 64KB page." + }, + { + "EventCode": "0x0C3A", + "EventName": "L2D_TLB_REFILL_2M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 2MB page." + }, + { + "EventCode": "0x0C3B", + "EventName": "L2D_TLB_REFILL_32M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 32MB page." + }, + { + "EventCode": "0x0C3C", + "EventName": "L2D_TLB_REFILL_512M", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 512MB page." + }, + { + "EventCode": "0x0C3D", + "EventName": "L2D_TLB_REFILL_1G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 1GB page." + }, + { + "EventCode": "0x0C3E", + "EventName": "L2D_TLB_REFILL_16G", + "BriefDescription": "This event counts operations that cause a TLB refill to the L2D in 16GB page." + }, + { + "ArchStdEvent": "DTLB_WALK_PERCYC", + "BriefDescription": "This event counts the number of DTLB_WALK events in progress on each Processor cycle." + }, + { + "ArchStdEvent": "ITLB_WALK_PERCYC", + "BriefDescription": "This event counts the number of ITLB_WALK events in progress on each Processor cycle." + }, + { + "ArchStdEvent": "DTLB_STEP", + "BriefDescription": "This event counts translation table walk access made by a refill of the data TLB." + }, + { + "ArchStdEvent": "ITLB_STEP", + "BriefDescription": "This event counts translation table walk access made by a refill of the instruction TLB." + }, + { + "ArchStdEvent": "DTLB_WALK_LARGE", + "BriefDescription": "This event counts translation table walk counted by DTLB_WALK where the result of the walk yields a large page size." + }, + { + "ArchStdEvent": "ITLB_WALK_LARGE", + "BriefDescription": "This event counts translation table walk counted by ITLB_WALK where the result of the walk yields a large page size." + }, + { + "ArchStdEvent": "DTLB_WALK_SMALL", + "BriefDescription": "This event counts translation table walk counted by DTLB_WALK where the result of the walk yields a small page size." + }, + { + "ArchStdEvent": "ITLB_WALK_SMALL", + "BriefDescription": "This event counts translation table walk counted by ITLB_WALK where the result of the walk yields a small page size." + }, + { + "ArchStdEvent": "DTLB_WALK_BLOCK", + "BriefDescription": "This event counts translation table walk counted by DTLB_WALK where the result of the walk yields a Block." + }, + { + "ArchStdEvent": "ITLB_WALK_BLOCK", + "BriefDescription": "This event counts translation table walk counted by ITLB_WALK where the result of the walk yields a Block." + }, + { + "ArchStdEvent": "DTLB_WALK_PAGE", + "BriefDescription": "This event counts translation table walk counted by DTLB_WALK where the result of the walk yields a Page." + }, + { + "ArchStdEvent": "ITLB_WALK_PAGE", + "BriefDescription": "This event counts translation table walk counted by ITLB_WALK where the result of the walk yields a Page." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/trace.json b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/trace.json new file mode 100644 index 000000000000..0c6e5054c9b5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/fujitsu/monaka/trace.json @@ -0,0 +1,18 @@ +[ + { + "ArchStdEvent": "TRB_WRAP", + "BriefDescription": "This event counts the event generated each time the current write pointer is wrapped to the base pointer." + }, + { + "ArchStdEvent": "TRB_TRIG", + "BriefDescription": "This event counts the event generated when a Trace Buffer Extension Trigger Event occurs." + }, + { + "ArchStdEvent": "TRCEXTOUT0", + "BriefDescription": "This event counts the event generated each time an event is signaled by the trace unit external event 0." + }, + { + "ArchStdEvent": "CTI_TRIGOUT4", + "BriefDescription": "This event counts the event generated each time an event is signaled on CTI output trigger 4." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index f4d1ca4d1493..5c846fe90513 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -39,6 +39,7 @@ 0x00000000420f5160,v1,cavium/thunderx2,core 0x00000000430f0af0,v1,cavium/thunderx2,core 0x00000000460f0010,v1,fujitsu/a64fx,core +0x00000000460f0030,v1,fujitsu/monaka,core 0x00000000480fd010,v1,hisilicon/hip08,core 0x00000000500f0000,v1,ampere/emag,core 0x00000000c00fac30,v1,ampere/ampereone,core diff --git a/tools/perf/pmu-events/arch/arm64/recommended.json b/tools/perf/pmu-events/arch/arm64/recommended.json index 210afa856091..a3b4941ae90c 100644 --- a/tools/perf/pmu-events/arch/arm64/recommended.json +++ b/tools/perf/pmu-events/arch/arm64/recommended.json @@ -318,6 +318,11 @@ "BriefDescription": "Barrier speculatively executed, DMB" }, { + "EventCode": "0x7F", + "EventName": "CSDB_SPEC", + "BriefDescription": "Barrier Speculatively executed, CSDB." + }, + { "PublicDescription": "Exception taken, Other synchronous", "EventCode": "0x81", "EventName": "EXC_UNDEF", diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c index 1c7a2cfa321f..0cb7ba7912e8 100644 --- a/tools/perf/pmu-events/empty-pmu-events.c +++ b/tools/perf/pmu-events/empty-pmu-events.c @@ -422,7 +422,7 @@ int pmu_events_table__for_each_event(const struct pmu_events_table *table, const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; int ret; - if (pmu && !pmu__name_match(pmu, pmu_name)) + if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name)) continue; ret = pmu_events_table__for_each_event_pmu(table, table_pmu, fn, data); @@ -443,7 +443,7 @@ int pmu_events_table__find_event(const struct pmu_events_table *table, const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; int ret; - if (!pmu__name_match(pmu, pmu_name)) + if (!perf_pmu__name_wildcard_match(pmu, pmu_name)) continue; ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data); @@ -462,7 +462,7 @@ size_t pmu_events_table__num_events(const struct pmu_events_table *table, const struct pmu_table_entry *table_pmu = &table->pmus[i]; const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; - if (pmu__name_match(pmu, pmu_name)) + if (perf_pmu__name_wildcard_match(pmu, pmu_name)) count += table_pmu->num_entries; } return count; @@ -581,7 +581,7 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) const struct pmu_table_entry *table_pmu = &map->event_table.pmus[i]; const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; - if (pmu__name_match(pmu, pmu_name)) + if (perf_pmu__name_wildcard_match(pmu, pmu_name)) return &map->event_table; } return NULL; diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index d781a377757a..7499a35bfadd 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -430,8 +430,11 @@ class JsonEvent: def to_c_string(self, metric: bool) -> str: """Representation of the event as a C struct initializer.""" + def fix_comment(s: str) -> str: + return s.replace('*/', r'\*\/') + s = self.build_c_string(metric) - return f'{{ { _bcs.offsets[s] } }}, /* {s} */\n' + return f'{{ { _bcs.offsets[s] } }}, /* {fix_comment(s)} */\n' @lru_cache(maxsize=None) @@ -461,12 +464,16 @@ def preprocess_arch_std_files(archpath: str) -> None: """Read in all architecture standard events.""" global _arch_std_events for item in os.scandir(archpath): - if item.is_file() and item.name.endswith('.json'): + if not item.is_file() or not item.name.endswith('.json'): + continue + try: for event in read_json_events(item.path, topic=''): if event.name: _arch_std_events[event.name.lower()] = event if event.metric_name: _arch_std_events[event.metric_name.lower()] = event + except Exception as e: + raise RuntimeError(f'Failure processing \'{item.name}\' in \'{archpath}\'') from e def add_events_table_entries(item: os.DirEntry, topic: str) -> None: @@ -938,7 +945,7 @@ int pmu_events_table__for_each_event(const struct pmu_events_table *table, const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; int ret; - if (pmu && !pmu__name_match(pmu, pmu_name)) + if (pmu && !perf_pmu__name_wildcard_match(pmu, pmu_name)) continue; ret = pmu_events_table__for_each_event_pmu(table, table_pmu, fn, data); @@ -959,7 +966,7 @@ int pmu_events_table__find_event(const struct pmu_events_table *table, const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; int ret; - if (!pmu__name_match(pmu, pmu_name)) + if (!perf_pmu__name_wildcard_match(pmu, pmu_name)) continue; ret = pmu_events_table__find_event_pmu(table, table_pmu, name, fn, data); @@ -978,7 +985,7 @@ size_t pmu_events_table__num_events(const struct pmu_events_table *table, const struct pmu_table_entry *table_pmu = &table->pmus[i]; const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; - if (pmu__name_match(pmu, pmu_name)) + if (perf_pmu__name_wildcard_match(pmu, pmu_name)) count += table_pmu->num_entries; } return count; @@ -1097,7 +1104,7 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) const struct pmu_table_entry *table_pmu = &map->event_table.pmus[i]; const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; - if (pmu__name_match(pmu, pmu_name)) + if (perf_pmu__name_wildcard_match(pmu, pmu_name)) return &map->event_table; } return NULL; @@ -1252,7 +1259,10 @@ def main() -> None: item_path = '/'.join(parents) + ('/' if len(parents) > 0 else '') + item.name if 'test' not in item_path and 'common' not in item_path and item_path not in _args.model.split(','): continue - action(parents, item) + try: + action(parents, item) + except Exception as e: + raise RuntimeError(f'Action failure for \'{item.name}\' in {parents}') from e if item.is_dir(): ftw(item.path, parents + [item.name], action) diff --git a/tools/perf/scripts/Makefile.syscalls b/tools/perf/scripts/Makefile.syscalls new file mode 100644 index 000000000000..8bf55333262e --- /dev/null +++ b/tools/perf/scripts/Makefile.syscalls @@ -0,0 +1,61 @@ +# SPDX-License-Identifier: GPL-2.0 +# This Makefile generates headers in +# tools/perf/arch/$(SRCARCH)/include/generated/asm from the architecture's +# syscall table. This will either be from the generic syscall table, or from a +# table that is specific to that architecture. + +PHONY := all +all: + +obj := $(OUTPUT)arch/$(SRCARCH)/include/generated/asm + +syscall_abis_32 := common,32 +syscall_abis_64 := common,64 +syscalltbl := $(srctree)/tools/scripts/syscall.tbl + +# let architectures override $(syscall_abis_%) and $(syscalltbl) +-include $(srctree)/tools/perf/arch/$(SRCARCH)/entry/syscalls/Makefile.syscalls +include $(srctree)/tools/build/Build.include +-include $(srctree)/tools/perf/arch/$(SRCARCH)/entry/syscalls/Kbuild + +systbl := $(srctree)/tools/perf/scripts/syscalltbl.sh + +syscall-y := $(addprefix $(obj)/, $(syscall-y)) + +# Remove stale wrappers when the corresponding files are removed from generic-y +old-headers := $(wildcard $(obj)/*.h) +unwanted := $(filter-out $(syscall-y),$(old-headers)) + +quiet_cmd_remove = REMOVE $(unwanted) + cmd_remove = rm -f $(unwanted) + +quiet_cmd_systbl = SYSTBL $@ + cmd_systbl = $(CONFIG_SHELL) $(systbl) \ + $(if $(systbl-args-$*),$(systbl-args-$*),$(systbl-args)) \ + --abis $(subst $(space),$(comma),$(strip $(syscall_abis_$*))) \ + $< $@ + +all: $(syscall-y) + $(if $(unwanted),$(call cmd,remove)) + @: + +$(obj)/syscalls_%.h: $(syscalltbl) $(systbl) FORCE + $(call if_changed,systbl) + +targets := $(syscall-y) + +# Create output directory. Skip it if at least one old header exists +# since we know the output directory already exists. +ifeq ($(old-headers),) +$(shell mkdir -p $(obj)) +endif + +PHONY += FORCE + +FORCE: + +existing-targets := $(wildcard $(sort $(targets))) + +-include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd) + +.PHONY: $(PHONY) diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c index 01f54d6724a5..60dcfe56d4d9 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c +++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c @@ -24,16 +24,6 @@ #include "../../../util/srcline.h" #include "../../../util/srccode.h" -#if PY_MAJOR_VERSION < 3 -#define _PyCapsule_GetPointer(arg1, arg2) \ - PyCObject_AsVoidPtr(arg1) -#define _PyBytes_FromStringAndSize(arg1, arg2) \ - PyString_FromStringAndSize((arg1), (arg2)) -#define _PyUnicode_AsUTF8(arg) \ - PyString_AsString(arg) - -PyMODINIT_FUNC initperf_trace_context(void); -#else #define _PyCapsule_GetPointer(arg1, arg2) \ PyCapsule_GetPointer((arg1), (arg2)) #define _PyBytes_FromStringAndSize(arg1, arg2) \ @@ -42,7 +32,6 @@ PyMODINIT_FUNC initperf_trace_context(void); PyUnicode_AsUTF8(arg) PyMODINIT_FUNC PyInit_perf_trace_context(void); -#endif static struct scripting_context *get_args(PyObject *args, const char *name, PyObject **arg2) { @@ -104,7 +93,7 @@ static PyObject *perf_sample_insn(PyObject *obj, PyObject *args) if (c->sample->ip && !c->sample->insn_len && thread__maps(c->al->thread)) { struct machine *machine = maps__machine(thread__maps(c->al->thread)); - script_fetch_insn(c->sample, c->al->thread, machine); + script_fetch_insn(c->sample, c->al->thread, machine, /*native_arch=*/true); } if (!c->sample->insn_len) Py_RETURN_NONE; /* N.B. This is a return statement */ @@ -213,12 +202,6 @@ static PyMethodDef ContextMethods[] = { { NULL, NULL, 0, NULL} }; -#if PY_MAJOR_VERSION < 3 -PyMODINIT_FUNC initperf_trace_context(void) -{ - (void) Py_InitModule("perf_trace_context", ContextMethods); -} -#else PyMODINIT_FUNC PyInit_perf_trace_context(void) { static struct PyModuleDef moduledef = { @@ -240,4 +223,3 @@ PyMODINIT_FUNC PyInit_perf_trace_context(void) return mod; } -#endif diff --git a/tools/perf/scripts/python/mem-phys-addr.py b/tools/perf/scripts/python/mem-phys-addr.py index 1f332e72b9b0..5e237a5a5f1b 100644 --- a/tools/perf/scripts/python/mem-phys-addr.py +++ b/tools/perf/scripts/python/mem-phys-addr.py @@ -3,98 +3,125 @@ # # Copyright (c) 2018, Intel Corporation. -from __future__ import division -from __future__ import print_function - import os import sys -import struct import re import bisect import collections +from dataclasses import dataclass +from typing import (Dict, Optional) sys.path.append(os.environ['PERF_EXEC_PATH'] + \ - '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +@dataclass(frozen=True) +class IomemEntry: + """Read from a line in /proc/iomem""" + begin: int + end: int + indent: int + label: str -#physical address ranges for System RAM -system_ram = [] -#physical address ranges for Persistent Memory -pmem = [] -#file object for proc iomem -f = None -#Count for each type of memory -load_mem_type_cnt = collections.Counter() -#perf event name -event_name = None +# Physical memory layout from /proc/iomem. Key is the indent and then +# a list of ranges. +iomem: Dict[int, list[IomemEntry]] = collections.defaultdict(list) +# Child nodes from the iomem parent. +children: Dict[IomemEntry, set[IomemEntry]] = collections.defaultdict(set) +# Maximum indent seen before an entry in the iomem file. +max_indent: int = 0 +# Count for each range of memory. +load_mem_type_cnt: Dict[IomemEntry, int] = collections.Counter() +# Perf event name set from the first sample in the data. +event_name: Optional[str] = None def parse_iomem(): - global f - f = open('/proc/iomem', 'r') - for i, j in enumerate(f): - m = re.split('-|:',j,2) - if m[2].strip() == 'System RAM': - system_ram.append(int(m[0], 16)) - system_ram.append(int(m[1], 16)) - if m[2].strip() == 'Persistent Memory': - pmem.append(int(m[0], 16)) - pmem.append(int(m[1], 16)) + """Populate iomem from /proc/iomem file""" + global iomem + global max_indent + global children + with open('/proc/iomem', 'r', encoding='ascii') as f: + for line in f: + indent = 0 + while line[indent] == ' ': + indent += 1 + if indent > max_indent: + max_indent = indent + m = re.split('-|:', line, 2) + begin = int(m[0], 16) + end = int(m[1], 16) + label = m[2].strip() + entry = IomemEntry(begin, end, indent, label) + # Before adding entry, search for a parent node using its begin. + if indent > 0: + parent = find_memory_type(begin) + assert parent, f"Given indent expected a parent for {label}" + children[parent].add(entry) + iomem[indent].append(entry) -def print_memory_type(): - print("Event: %s" % (event_name)) - print("%-40s %10s %10s\n" % ("Memory type", "count", "percentage"), end='') - print("%-40s %10s %10s\n" % ("----------------------------------------", - "-----------", "-----------"), - end=''); - total = sum(load_mem_type_cnt.values()) - for mem_type, count in sorted(load_mem_type_cnt.most_common(), \ - key = lambda kv: (kv[1], kv[0]), reverse = True): - print("%-40s %10d %10.1f%%\n" % - (mem_type, count, 100 * count / total), - end='') +def find_memory_type(phys_addr) -> Optional[IomemEntry]: + """Search iomem for the range containing phys_addr with the maximum indent""" + for i in range(max_indent, -1, -1): + if i not in iomem: + continue + position = bisect.bisect_right(iomem[i], phys_addr, + key=lambda entry: entry.begin) + if position is None: + continue + iomem_entry = iomem[i][position-1] + if iomem_entry.begin <= phys_addr <= iomem_entry.end: + return iomem_entry + print(f"Didn't find {phys_addr}") + return None -def trace_begin(): - parse_iomem() +def print_memory_type(): + print(f"Event: {event_name}") + print(f"{'Memory type':<40} {'count':>10} {'percentage':>10}") + print(f"{'-' * 40:<40} {'-' * 10:>10} {'-' * 10:>10}") + total = sum(load_mem_type_cnt.values()) + # Add count from children into the parent. + for i in range(max_indent, -1, -1): + if i not in iomem: + continue + for entry in iomem[i]: + global children + for child in children[entry]: + if load_mem_type_cnt[child] > 0: + load_mem_type_cnt[entry] += load_mem_type_cnt[child] -def trace_end(): - print_memory_type() - f.close() + def print_entries(entries): + """Print counts from parents down to their children""" + global children + for entry in sorted(entries, + key = lambda entry: load_mem_type_cnt[entry], + reverse = True): + count = load_mem_type_cnt[entry] + if count > 0: + mem_type = ' ' * entry.indent + f"{entry.begin:x}-{entry.end:x} : {entry.label}" + percent = 100 * count / total + print(f"{mem_type:<40} {count:>10} {percent:>10.1f}") + print_entries(children[entry]) -def is_system_ram(phys_addr): - #/proc/iomem is sorted - position = bisect.bisect(system_ram, phys_addr) - if position % 2 == 0: - return False - return True + print_entries(iomem[0]) -def is_persistent_mem(phys_addr): - position = bisect.bisect(pmem, phys_addr) - if position % 2 == 0: - return False - return True +def trace_begin(): + parse_iomem() -def find_memory_type(phys_addr): - if phys_addr == 0: - return "N/A" - if is_system_ram(phys_addr): - return "System RAM" +def trace_end(): + print_memory_type() - if is_persistent_mem(phys_addr): - return "Persistent Memory" +def process_event(param_dict): + if "sample" not in param_dict: + return - #slow path, search all - f.seek(0, 0) - for j in f: - m = re.split('-|:',j,2) - if int(m[0], 16) <= phys_addr <= int(m[1], 16): - return m[2] - return "N/A" + sample = param_dict["sample"] + if "phys_addr" not in sample: + return -def process_event(param_dict): - name = param_dict["ev_name"] - sample = param_dict["sample"] - phys_addr = sample["phys_addr"] + phys_addr = sample["phys_addr"] + entry = find_memory_type(phys_addr) + if entry: + load_mem_type_cnt[entry] += 1 - global event_name - if event_name == None: - event_name = name - load_mem_type_cnt[find_memory_type(phys_addr)] += 1 + global event_name + if event_name is None: + event_name = param_dict["ev_name"] diff --git a/tools/perf/scripts/syscalltbl.sh b/tools/perf/scripts/syscalltbl.sh new file mode 100755 index 000000000000..1ce0d5aa8b50 --- /dev/null +++ b/tools/perf/scripts/syscalltbl.sh @@ -0,0 +1,86 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate a syscall table header. +# +# Each line of the syscall table should have the following format: +# +# NR ABI NAME [NATIVE] [COMPAT] +# +# NR syscall number +# ABI ABI name +# NAME syscall name +# NATIVE native entry point (optional) +# COMPAT compat entry point (optional) + +set -e + +usage() { + echo >&2 "usage: $0 [--abis ABIS] INFILE OUTFILE" >&2 + echo >&2 + echo >&2 " INFILE input syscall table" + echo >&2 " OUTFILE output header file" + echo >&2 + echo >&2 "options:" + echo >&2 " --abis ABIS ABI(s) to handle (By default, all lines are handled)" + exit 1 +} + +# default unless specified by options +abis= + +while [ $# -gt 0 ] +do + case $1 in + --abis) + abis=$(echo "($2)" | tr ',' '|') + shift 2;; + -*) + echo "$1: unknown option" >&2 + usage;; + *) + break;; + esac +done + +if [ $# -ne 2 ]; then + usage +fi + +infile="$1" +outfile="$2" + +nxt=0 + +syscall_macro() { + nr="$1" + name="$2" + + echo " [$nr] = \"$name\"," +} + +emit() { + nr="$1" + entry="$2" + + syscall_macro "$nr" "$entry" +} + +echo "static const char *const syscalltbl[] = {" > $outfile + +sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX) +grep -E "^[0-9]+[[:space:]]+$abis" "$infile" | sort -n > $sorted_table + +max_nr=0 +# the params are: nr abi name entry compat +# use _ for intentionally unused variables according to SC2034 +while read nr _ name _ _; do + emit "$nr" "$name" >> $outfile + max_nr=$nr +done < $sorted_table + +rm -f $sorted_table + +echo "};" >> $outfile + +echo "#define SYSCALLTBL_MAX_ID ${max_nr}" >> $outfile diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index ec4e1f034742..4bf8d3f5eae7 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -5,10 +5,10 @@ perf-test-y += tests-scripts.o perf-test-y += parse-events.o perf-test-y += dso-data.o perf-test-y += vmlinux-kallsyms.o -perf-test-$(CONFIG_LIBTRACEEVENT) += openat-syscall.o -perf-test-$(CONFIG_LIBTRACEEVENT) += openat-syscall-all-cpus.o +perf-test-y += openat-syscall.o +perf-test-y += openat-syscall-all-cpus.o perf-test-$(CONFIG_LIBTRACEEVENT) += openat-syscall-tp-fields.o -perf-test-$(CONFIG_LIBTRACEEVENT) += mmap-basic.o +perf-test-y += mmap-basic.o perf-test-y += perf-record.o perf-test-y += evsel-roundtrip-name.o perf-test-$(CONFIG_LIBTRACEEVENT) += evsel-tp-sched.o diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 4751dd3c6f67..14d30a5053be 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -42,6 +42,8 @@ static bool dont_fork; /* Fork the tests in parallel and wait for their completion. */ static bool sequential; +/* Number of times each test is run. */ +static unsigned int runs_per_test = 1; const char *dso_to_test; const char *test_objdump_path = "objdump"; @@ -60,11 +62,9 @@ static struct test_suite *arch_tests[] = { static struct test_suite *generic_tests[] = { &suite__vmlinux_matches_kallsyms, -#ifdef HAVE_LIBTRACEEVENT &suite__openat_syscall_event, &suite__openat_syscall_event_on_all_cpus, &suite__basic_mmap, -#endif &suite__mem, &suite__parse_events, &suite__expr, @@ -151,58 +151,51 @@ static struct test_workload *workloads[] = { #define workloads__for_each(workload) \ for (unsigned i = 0; i < ARRAY_SIZE(workloads) && ({ workload = workloads[i]; 1; }); i++) -static int num_subtests(const struct test_suite *t) +#define test_suite__for_each_test_case(suite, idx) \ + for (idx = 0; (suite)->test_cases && (suite)->test_cases[idx].name != NULL; idx++) + +static int test_suite__num_test_cases(const struct test_suite *t) { int num; - if (!t->test_cases) - return 0; - - num = 0; - while (t->test_cases[num].name) - num++; + test_suite__for_each_test_case(t, num); return num; } -static bool has_subtests(const struct test_suite *t) -{ - return num_subtests(t) > 1; -} - -static const char *skip_reason(const struct test_suite *t, int subtest) +static const char *skip_reason(const struct test_suite *t, int test_case) { if (!t->test_cases) return NULL; - return t->test_cases[subtest >= 0 ? subtest : 0].skip_reason; + return t->test_cases[test_case >= 0 ? test_case : 0].skip_reason; } -static const char *test_description(const struct test_suite *t, int subtest) +static const char *test_description(const struct test_suite *t, int test_case) { - if (t->test_cases && subtest >= 0) - return t->test_cases[subtest].desc; + if (t->test_cases && test_case >= 0) + return t->test_cases[test_case].desc; return t->desc; } -static test_fnptr test_function(const struct test_suite *t, int subtest) +static test_fnptr test_function(const struct test_suite *t, int test_case) { - if (subtest <= 0) + if (test_case <= 0) return t->test_cases[0].run_case; - return t->test_cases[subtest].run_case; + return t->test_cases[test_case].run_case; } -static bool test_exclusive(const struct test_suite *t, int subtest) +static bool test_exclusive(const struct test_suite *t, int test_case) { - if (subtest <= 0) + if (test_case <= 0) return t->test_cases[0].exclusive; - return t->test_cases[subtest].exclusive; + return t->test_cases[test_case].exclusive; } -static bool perf_test__matches(const char *desc, int curr, int argc, const char *argv[]) +static bool perf_test__matches(const char *desc, int suite_num, int argc, const char *argv[]) { int i; @@ -214,7 +207,7 @@ static bool perf_test__matches(const char *desc, int curr, int argc, const char long nr = strtoul(argv[i], &end, 10); if (*end == '\0') { - if (nr == curr + 1) + if (nr == suite_num + 1) return true; continue; } @@ -229,8 +222,8 @@ static bool perf_test__matches(const char *desc, int curr, int argc, const char struct child_test { struct child_process process; struct test_suite *test; - int test_num; - int subtest; + int suite_num; + int test_case_num; }; static jmp_buf run_test_jmp_buf; @@ -260,7 +253,7 @@ static int run_test_child(struct child_process *process) pr_debug("--- start ---\n"); pr_debug("test child forked, pid %d\n", getpid()); - err = test_function(child->test, child->subtest)(child->test, child->subtest); + err = test_function(child->test, child->test_case_num)(child->test, child->test_case_num); pr_debug("---- end(%d) ----\n", err); err_out: @@ -272,15 +265,16 @@ err_out: #define TEST_RUNNING -3 -static int print_test_result(struct test_suite *t, int i, int subtest, int result, int width, - int running) +static int print_test_result(struct test_suite *t, int curr_suite, int curr_test_case, + int result, int width, int running) { - if (has_subtests(t)) { + if (test_suite__num_test_cases(t) > 1) { int subw = width > 2 ? width - 2 : width; - pr_info("%3d.%1d: %-*s:", i + 1, subtest + 1, subw, test_description(t, subtest)); + pr_info("%3d.%1d: %-*s:", curr_suite + 1, curr_test_case + 1, subw, + test_description(t, curr_test_case)); } else - pr_info("%3d: %-*s:", i + 1, width, test_description(t, subtest)); + pr_info("%3d: %-*s:", curr_suite + 1, width, test_description(t, curr_test_case)); switch (result) { case TEST_RUNNING: @@ -290,7 +284,7 @@ static int print_test_result(struct test_suite *t, int i, int subtest, int resul pr_info(" Ok\n"); break; case TEST_SKIP: { - const char *reason = skip_reason(t, subtest); + const char *reason = skip_reason(t, curr_test_case); if (reason) color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (%s)\n", reason); @@ -312,7 +306,7 @@ static void finish_test(struct child_test **child_tests, int running_test, int c { struct child_test *child_test = child_tests[running_test]; struct test_suite *t; - int i, subi, err; + int curr_suite, curr_test_case, err; bool err_done = false; struct strbuf err_output = STRBUF_INIT; int last_running = -1; @@ -323,15 +317,15 @@ static void finish_test(struct child_test **child_tests, int running_test, int c return; } t = child_test->test; - i = child_test->test_num; - subi = child_test->subtest; + curr_suite = child_test->suite_num; + curr_test_case = child_test->test_case_num; err = child_test->process.err; /* * For test suites with subtests, display the suite name ahead of the * sub test names. */ - if (has_subtests(t) && subi == 0) - pr_info("%3d: %-*s:\n", i + 1, width, test_description(t, -1)); + if (test_suite__num_test_cases(t) > 1 && curr_test_case == 0) + pr_info("%3d: %-*s:\n", curr_suite + 1, width, test_description(t, -1)); /* * Busy loop reading from the child's stdout/stderr that are set to be @@ -340,10 +334,11 @@ static void finish_test(struct child_test **child_tests, int running_test, int c if (err > 0) fcntl(err, F_SETFL, O_NONBLOCK); if (verbose > 1) { - if (has_subtests(t)) - pr_info("%3d.%1d: %s:\n", i + 1, subi + 1, test_description(t, subi)); + if (test_suite__num_test_cases(t) > 1) + pr_info("%3d.%1d: %s:\n", curr_suite + 1, curr_test_case + 1, + test_description(t, curr_test_case)); else - pr_info("%3d: %s:\n", i + 1, test_description(t, -1)); + pr_info("%3d: %s:\n", curr_suite + 1, test_description(t, -1)); } while (!err_done) { struct pollfd pfds[1] = { @@ -368,7 +363,8 @@ static void finish_test(struct child_test **child_tests, int running_test, int c */ fprintf(debug_file(), PERF_COLOR_DELETE_LINE); } - print_test_result(t, i, subi, TEST_RUNNING, width, running); + print_test_result(t, curr_suite, curr_test_case, TEST_RUNNING, + width, running); last_running = running; } } @@ -406,14 +402,14 @@ static void finish_test(struct child_test **child_tests, int running_test, int c fprintf(stderr, "%s", err_output.buf); strbuf_release(&err_output); - print_test_result(t, i, subi, ret, width, /*running=*/0); + print_test_result(t, curr_suite, curr_test_case, ret, width, /*running=*/0); if (err > 0) close(err); zfree(&child_tests[running_test]); } -static int start_test(struct test_suite *test, int i, int subi, struct child_test **child, - int width, int pass) +static int start_test(struct test_suite *test, int curr_suite, int curr_test_case, + struct child_test **child, int width, int pass) { int err; @@ -421,17 +417,18 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes if (dont_fork) { if (pass == 1) { pr_debug("--- start ---\n"); - err = test_function(test, subi)(test, subi); + err = test_function(test, curr_test_case)(test, curr_test_case); pr_debug("---- end ----\n"); - print_test_result(test, i, subi, err, width, /*running=*/0); + print_test_result(test, curr_suite, curr_test_case, err, width, + /*running=*/0); } return 0; } - if (pass == 1 && !sequential && test_exclusive(test, subi)) { + if (pass == 1 && !sequential && test_exclusive(test, curr_test_case)) { /* When parallel, skip exclusive tests on the first pass. */ return 0; } - if (pass != 1 && (sequential || !test_exclusive(test, subi))) { + if (pass != 1 && (sequential || !test_exclusive(test, curr_test_case))) { /* Sequential and non-exclusive tests were run on the first pass. */ return 0; } @@ -440,8 +437,8 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes return -ENOMEM; (*child)->test = test; - (*child)->test_num = i; - (*child)->subtest = subi; + (*child)->suite_num = curr_suite; + (*child)->test_case_num = curr_test_case; (*child)->process.pid = -1; (*child)->process.no_stdin = 1; if (verbose <= 0) { @@ -481,20 +478,16 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[], int err = 0; for (struct test_suite **t = suites; *t; t++) { - int len = strlen(test_description(*t, -1)); + int i, len = strlen(test_description(*t, -1)); if (width < len) width = len; - if (has_subtests(*t)) { - for (int subi = 0, subn = num_subtests(*t); subi < subn; subi++) { - len = strlen(test_description(*t, subi)); - if (width < len) - width = len; - num_tests++; - } - } else { - num_tests++; + test_suite__for_each_test_case(*t, i) { + len = strlen(test_description(*t, i)); + if (width < len) + width = len; + num_tests += runs_per_test; } } child_tests = calloc(num_tests, sizeof(*child_tests)); @@ -512,7 +505,7 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[], continue; pr_debug3("Killing %d pid %d\n", - child_test->test_num + 1, + child_test->suite_num + 1, child_test->process.pid); kill(child_test->process.pid, err); } @@ -528,50 +521,48 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[], */ for (int pass = 1; pass <= 2; pass++) { int child_test_num = 0; - int i = 0; + int curr_suite = 0; - for (struct test_suite **t = suites; *t; t++) { - int curr = i++; + for (struct test_suite **t = suites; *t; t++, curr_suite++) { + int curr_test_case; - if (!perf_test__matches(test_description(*t, -1), curr, argc, argv)) { + if (!perf_test__matches(test_description(*t, -1), curr_suite, argc, argv)) { /* * Test suite shouldn't be run based on - * description. See if subtest should. + * description. See if any test case should. */ bool skip = true; - for (int subi = 0, subn = num_subtests(*t); subi < subn; subi++) { - if (perf_test__matches(test_description(*t, subi), - curr, argc, argv)) + test_suite__for_each_test_case(*t, curr_test_case) { + if (perf_test__matches(test_description(*t, curr_test_case), + curr_suite, argc, argv)) { skip = false; + break; + } } - if (skip) continue; } - if (intlist__find(skiplist, i)) { - pr_info("%3d: %-*s:", curr + 1, width, test_description(*t, -1)); + if (intlist__find(skiplist, curr_suite + 1)) { + pr_info("%3d: %-*s:", curr_suite + 1, width, + test_description(*t, -1)); color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n"); continue; } - if (!has_subtests(*t)) { - err = start_test(*t, curr, -1, &child_tests[child_test_num++], - width, pass); - if (err) - goto err_out; - continue; - } - for (int subi = 0, subn = num_subtests(*t); subi < subn; subi++) { - if (!perf_test__matches(test_description(*t, subi), - curr, argc, argv)) - continue; - - err = start_test(*t, curr, subi, &child_tests[child_test_num++], - width, pass); - if (err) - goto err_out; + for (unsigned int run = 0; run < runs_per_test; run++) { + test_suite__for_each_test_case(*t, curr_test_case) { + if (!perf_test__matches(test_description(*t, curr_test_case), + curr_suite, argc, argv)) + continue; + + err = start_test(*t, curr_suite, curr_test_case, + &child_tests[child_test_num++], + width, pass); + if (err) + goto err_out; + } } } if (!sequential) { @@ -592,25 +583,24 @@ err_out: return err; } -static int perf_test__list(struct test_suite **suites, int argc, const char **argv) +static int perf_test__list(FILE *fp, struct test_suite **suites, int argc, const char **argv) { - int i = 0; + int curr_suite = 0; - for (struct test_suite **t = suites; *t; t++) { - int curr = i++; + for (struct test_suite **t = suites; *t; t++, curr_suite++) { + int curr_test_case; - if (!perf_test__matches(test_description(*t, -1), curr, argc, argv)) + if (!perf_test__matches(test_description(*t, -1), curr_suite, argc, argv)) continue; - pr_info("%3d: %s\n", i, test_description(*t, -1)); + fprintf(fp, "%3d: %s\n", curr_suite + 1, test_description(*t, -1)); - if (has_subtests(*t)) { - int subn = num_subtests(*t); - int subi; + if (test_suite__num_test_cases(*t) <= 1) + continue; - for (subi = 0; subi < subn; subi++) - pr_info("%3d:%1d: %s\n", i, subi + 1, - test_description(*t, subi)); + test_suite__for_each_test_case(*t, curr_test_case) { + fprintf(fp, "%3d.%1d: %s\n", curr_suite + 1, curr_test_case + 1, + test_description(*t, curr_test_case)); } } return 0; @@ -667,27 +657,24 @@ static struct test_suite **build_suites(void) if (suites[2] == NULL) suites[2] = create_script_test_suites(); -#define for_each_test(t) \ +#define for_each_suite(suite) \ for (size_t i = 0, j = 0; i < ARRAY_SIZE(suites); i++, j = 0) \ - while ((t = suites[i][j++]) != NULL) + while ((suite = suites[i][j++]) != NULL) - for_each_test(t) + for_each_suite(t) num_suites++; result = calloc(num_suites + 1, sizeof(struct test_suite *)); for (int pass = 1; pass <= 2; pass++) { - for_each_test(t) { + for_each_suite(t) { bool exclusive = false; + int curr_test_case; - if (!has_subtests(t)) { - exclusive = test_exclusive(t, -1); - } else { - for (int subi = 0, subn = num_subtests(t); subi < subn; subi++) { - if (test_exclusive(t, subi)) { - exclusive = true; - break; - } + test_suite__for_each_test_case(t, curr_test_case) { + if (test_exclusive(t, curr_test_case)) { + exclusive = true; + break; } } if ((!exclusive && pass == 1) || (exclusive && pass == 2)) @@ -695,7 +682,7 @@ static struct test_suite **build_suites(void) } } return result; -#undef for_each_test +#undef for_each_suite } int cmd_test(int argc, const char **argv) @@ -715,6 +702,8 @@ int cmd_test(int argc, const char **argv) "Do not fork for testcase"), OPT_BOOLEAN('S', "sequential", &sequential, "Run the tests one after another rather than in parallel"), + OPT_UINTEGER('r', "runs-per-test", &runs_per_test, + "Run each test the given number of times, default 1"), OPT_STRING('w', "workload", &workload, "work", "workload to run for testing, use '--list-workloads' to list the available ones."), OPT_BOOLEAN(0, "list-workloads", &list_workloads, "List the available builtin workloads to use with -w/--workload"), OPT_STRING(0, "dso", &dso_to_test, "dso", "dso to test"), @@ -738,7 +727,7 @@ int cmd_test(int argc, const char **argv) argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0); if (argc >= 1 && !strcmp(argv[0], "list")) { suites = build_suites(); - ret = perf_test__list(suites, argc - 1, argv + 1); + ret = perf_test__list(stdout, suites, argc - 1, argv + 1); free(suites); return ret; } diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 27c82cfb7e7d..b1abb34d7818 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include <linux/kconfig.h> #include <linux/kernel.h> #include <linux/types.h> #include <inttypes.h> @@ -8,6 +9,7 @@ #include <stdio.h> #include <string.h> #include <sys/param.h> +#include <sys/utsname.h> #include <perf/cpumap.h> #include <perf/evlist.h> #include <perf/mmap.h> @@ -176,16 +178,104 @@ static int read_objdump_output(FILE *f, void *buf, size_t *len, u64 start_addr) return err; } +/* + * Only gets GNU objdump version. Returns 0 for llvm-objdump. + */ +static int objdump_version(void) +{ + size_t line_len; + char cmd[PATH_MAX * 2]; + char *line = NULL; + const char *fmt; + FILE *f; + int ret; + + int version_tmp, version_num = 0; + char *version = 0, *token; + + fmt = "%s --version"; + ret = snprintf(cmd, sizeof(cmd), fmt, test_objdump_path); + if (ret <= 0 || (size_t)ret >= sizeof(cmd)) + return -1; + /* Ignore objdump errors */ + strcat(cmd, " 2>/dev/null"); + f = popen(cmd, "r"); + if (!f) { + pr_debug("popen failed\n"); + return -1; + } + /* Get first line of objdump --version output */ + ret = getline(&line, &line_len, f); + pclose(f); + if (ret < 0) { + pr_debug("getline failed\n"); + return -1; + } + + token = strsep(&line, " "); + if (token != NULL && !strcmp(token, "GNU")) { + // version is last part of first line of objdump --version output. + while ((token = strsep(&line, " "))) + version = token; + + // Convert version into a format we can compare with + token = strsep(&version, "."); + version_num = atoi(token); + if (version_num) + version_num *= 10000; + + token = strsep(&version, "."); + version_tmp = atoi(token); + if (token) + version_num += version_tmp * 100; + + token = strsep(&version, "."); + version_tmp = atoi(token); + if (token) + version_num += version_tmp; + } + + return version_num; +} + static int read_via_objdump(const char *filename, u64 addr, void *buf, size_t len) { + u64 stop_address = addr + len; + struct utsname uname_buf; char cmd[PATH_MAX * 2]; const char *fmt; FILE *f; int ret; + ret = uname(&uname_buf); + if (ret) { + pr_debug("uname failed\n"); + return -1; + } + + if (!strncmp(uname_buf.machine, "riscv", 5)) { + int version = objdump_version(); + + /* Default to this workaround if version parsing fails */ + if (version < 0 || version > 24100) { + /* + * Starting at riscv objdump version 2.41, dumping in + * the middle of an instruction is not supported. riscv + * instructions are aligned along 2-byte intervals and + * can be either 2-bytes or 4-bytes. This makes it + * possible that the stop-address lands in the middle of + * a 4-byte instruction. Increase the stop_address by + * two to ensure an instruction is not cut in half, but + * leave the len as-is so only the expected number of + * bytes are collected. + */ + stop_address += 2; + } + } + fmt = "%s -z -d --start-address=0x%"PRIx64" --stop-address=0x%"PRIx64" %s"; - ret = snprintf(cmd, sizeof(cmd), fmt, test_objdump_path, addr, addr + len, + ret = snprintf(cmd, sizeof(cmd), fmt, test_objdump_path, addr, stop_address, filename); if (ret <= 0 || (size_t)ret >= sizeof(cmd)) return -1; diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 2f0168b2a5a9..2354246afc5a 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -156,21 +156,54 @@ static int test__cpu_map_print(struct test_suite *test __maybe_unused, int subte return 0; } -static int test__cpu_map_merge(struct test_suite *test __maybe_unused, int subtest __maybe_unused) +static int __test__cpu_map_merge(const char *lhs, const char *rhs, int nr, const char *expected) { - struct perf_cpu_map *a = perf_cpu_map__new("4,2,1"); - struct perf_cpu_map *b = perf_cpu_map__new("4,5,7"); - struct perf_cpu_map *c = perf_cpu_map__merge(a, b); + struct perf_cpu_map *a = perf_cpu_map__new(lhs); + struct perf_cpu_map *b = perf_cpu_map__new(rhs); char buf[100]; - TEST_ASSERT_VAL("failed to merge map: bad nr", perf_cpu_map__nr(c) == 5); - cpu_map__snprint(c, buf, sizeof(buf)); - TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, "1-2,4-5,7")); + perf_cpu_map__merge(&a, b); + TEST_ASSERT_VAL("failed to merge map: bad nr", perf_cpu_map__nr(a) == nr); + cpu_map__snprint(a, buf, sizeof(buf)); + TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, expected)); perf_cpu_map__put(b); - perf_cpu_map__put(c); + + /* + * If 'b' is a superset of 'a', 'a' points to the same map with the + * map 'b'. In this case, the owner 'b' has released the resource above + * but 'a' still keeps the ownership, the reference counter should be 1. + */ + TEST_ASSERT_VAL("unexpected refcnt: bad result", + refcount_read(perf_cpu_map__refcnt(a)) == 1); + + perf_cpu_map__put(a); return 0; } +static int test__cpu_map_merge(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + int ret; + + ret = __test__cpu_map_merge("4,2,1", "4,5,7", 5, "1-2,4-5,7"); + if (ret) + return ret; + ret = __test__cpu_map_merge("1-8", "6-9", 9, "1-9"); + if (ret) + return ret; + ret = __test__cpu_map_merge("1-8,12-20", "6-9,15", 18, "1-9,12-20"); + if (ret) + return ret; + ret = __test__cpu_map_merge("4,2,1", "1", 3, "1-2,4"); + if (ret) + return ret; + ret = __test__cpu_map_merge("1", "4,2,1", 3, "1-2,4"); + if (ret) + return ret; + ret = __test__cpu_map_merge("1", "1", 1, "1"); + return ret; +} + static int __test__cpu_map_intersect(const char *lhs, const char *rhs, int nr, const char *expected) { struct perf_cpu_map *a = perf_cpu_map__new(lhs); @@ -219,30 +252,29 @@ static int test__cpu_map_equal(struct test_suite *test __maybe_unused, int subte struct perf_cpu_map *empty = perf_cpu_map__intersect(one, two); struct perf_cpu_map *pair = perf_cpu_map__new("1-2"); struct perf_cpu_map *tmp; - struct perf_cpu_map *maps[] = {empty, any, one, two, pair}; + struct perf_cpu_map **maps[] = {&empty, &any, &one, &two, &pair}; for (size_t i = 0; i < ARRAY_SIZE(maps); i++) { /* Maps equal themself. */ - TEST_ASSERT_VAL("equal", perf_cpu_map__equal(maps[i], maps[i])); + TEST_ASSERT_VAL("equal", perf_cpu_map__equal(*maps[i], *maps[i])); for (size_t j = 0; j < ARRAY_SIZE(maps); j++) { /* Maps dont't equal each other. */ if (i == j) continue; - TEST_ASSERT_VAL("not equal", !perf_cpu_map__equal(maps[i], maps[j])); + TEST_ASSERT_VAL("not equal", !perf_cpu_map__equal(*maps[i], *maps[j])); } } /* Maps equal made maps. */ - tmp = perf_cpu_map__merge(perf_cpu_map__get(one), two); - TEST_ASSERT_VAL("pair", perf_cpu_map__equal(pair, tmp)); - perf_cpu_map__put(tmp); + perf_cpu_map__merge(&two, one); + TEST_ASSERT_VAL("pair", perf_cpu_map__equal(pair, two)); tmp = perf_cpu_map__intersect(pair, one); TEST_ASSERT_VAL("one", perf_cpu_map__equal(one, tmp)); perf_cpu_map__put(tmp); for (size_t i = 0; i < ARRAY_SIZE(maps); i++) - perf_cpu_map__put(maps[i]); + perf_cpu_map__put(*maps[i]); return TEST_OK; } diff --git a/tools/perf/tests/event_groups.c b/tools/perf/tests/event_groups.c index ccd9d8b2903f..c119ff114948 100644 --- a/tools/perf/tests/event_groups.c +++ b/tools/perf/tests/event_groups.c @@ -10,9 +10,10 @@ #include "header.h" #include "../perf-sys.h" -/* hw: cycles, sw: context-switch, uncore: [arch dependent] */ +/* hw: cycles,instructions sw: context-switch, uncore: [arch dependent] */ static int types[] = {0, 1, -1}; static unsigned long configs[] = {0, 3, 0}; +static unsigned long configs_hw[] = {1}; #define NR_UNCORE_PMUS 5 @@ -93,7 +94,18 @@ static int run_test(int i, int j, int k) return erroneous ? 0 : -1; } - sibling_fd2 = event_open(types[k], configs[k], group_fd); + /* + * if all three events (leader and two sibling events) + * are hardware events, use instructions as one of the + * sibling event. There is event constraint in powerpc that + * events using same counter cannot be programmed in a group. + * Since PERF_COUNT_HW_INSTRUCTIONS is a generic hardware + * event and present in all platforms, lets use that. + */ + if (!i && !j && !k) + sibling_fd2 = event_open(types[k], configs_hw[k], group_fd); + else + sibling_fd2 = event_open(types[k], configs[k], group_fd); if (sibling_fd2 == -1) { close(sibling_fd1); close(group_fd); @@ -124,9 +136,18 @@ static int test__event_groups(struct test_suite *text __maybe_unused, int subtes if (r) ret = TEST_FAIL; - pr_debug("0x%x 0x%lx, 0x%x 0x%lx, 0x%x 0x%lx: %s\n", - types[i], configs[i], types[j], configs[j], - types[k], configs[k], r ? "Fail" : "Pass"); + /* + * For all three events as HW events, second sibling + * event is picked from configs_hw. So print accordingly + */ + if (!i && !j && !k) + pr_debug("0x%x 0x%lx, 0x%x 0x%lx, 0x%x 0x%lx: %s\n", + types[i], configs[i], types[j], configs[j], + types[k], configs_hw[k], r ? "Fail" : "Pass"); + else + pr_debug("0x%x 0x%lx, 0x%x 0x%lx, 0x%x 0x%lx: %s\n", + types[i], configs[i], types[j], configs[j], + types[k], configs[k], r ? "Fail" : "Pass"); } } } diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c index d2b066a2b557..0837aca1cdfa 100644 --- a/tools/perf/tests/hwmon_pmu.c +++ b/tools/perf/tests/hwmon_pmu.c @@ -13,17 +13,23 @@ static const struct test_event { const char *name; const char *alias; - long config; + union hwmon_pmu_event_key key; } test_events[] = { { "temp_test_hwmon_event1", "temp1", - 0xA0001, + .key = { + .num = 1, + .type = 10 + }, }, { "temp_test_hwmon_event2", "temp2", - 0xA0002, + .key = { + .num = 2, + .type = 10 + }, }, }; @@ -183,11 +189,11 @@ static int do_test(size_t i, bool with_pmu, bool with_alias) strcmp(evsel->pmu->name, "hwmon_a_test_hwmon_pmu")) continue; - if (evsel->core.attr.config != (u64)test_events[i].config) { + if (evsel->core.attr.config != (u64)test_events[i].key.type_and_num) { pr_debug("FAILED %s:%d Unexpected config for '%s', %lld != %ld\n", __FILE__, __LINE__, str, evsel->core.attr.config, - test_events[i].config); + test_events[i].key.type_and_num); ret = TEST_FAIL; goto out; } diff --git a/tools/perf/tests/make b/tools/perf/tests/make index a7fcbd589752..0ee94caf9ec1 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -86,7 +86,6 @@ make_no_libdw_dwarf_unwind := NO_LIBDW_DWARF_UNWIND=1 make_no_backtrace := NO_BACKTRACE=1 make_no_libcapstone := NO_CAPSTONE=1 make_no_libnuma := NO_LIBNUMA=1 -make_no_libaudit := NO_LIBAUDIT=1 make_no_libbionic := NO_LIBBIONIC=1 make_no_auxtrace := NO_AUXTRACE=1 make_no_libbpf := NO_LIBBPF=1 @@ -97,7 +96,6 @@ make_no_libllvm := NO_LIBLLVM=1 make_with_babeltrace:= LIBBABELTRACE=1 make_with_coresight := CORESIGHT=1 make_no_sdt := NO_SDT=1 -make_no_syscall_tbl := NO_SYSCALL_TABLE=1 make_no_libpfm4 := NO_LIBPFM4=1 make_with_gtk2 := GTK2=1 make_refcnt_check := EXTRA_CFLAGS="-DREFCNT_CHECKING=1" @@ -122,10 +120,10 @@ make_static := LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX3 # all the NO_* variable combined make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_GTK2=1 make_minimal += NO_DEMANGLE=1 NO_LIBELF=1 NO_BACKTRACE=1 -make_minimal += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 +make_minimal += NO_LIBNUMA=1 NO_LIBBIONIC=1 make_minimal += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 make_minimal += NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1 NO_LIBZSTD=1 -make_minimal += NO_LIBCAP=1 NO_SYSCALL_TABLE=1 NO_CAPSTONE=1 +make_minimal += NO_LIBCAP=1 NO_CAPSTONE=1 # $(run) contains all available tests run := make_pure @@ -158,7 +156,6 @@ run += make_no_libdw_dwarf_unwind run += make_no_backtrace run += make_no_libcapstone run += make_no_libnuma -run += make_no_libaudit run += make_no_libbionic run += make_no_auxtrace run += make_no_libbpf diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 82a19674a38f..5ec2e5607987 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -54,8 +54,6 @@ static bool test_perf_config(const struct perf_evsel *evsel, __u64 expected_conf return (evsel->attr.config & PERF_HW_EVENT_MASK) == expected_config; } -#ifdef HAVE_LIBTRACEEVENT - #if defined(__s390x__) /* Return true if kvm module is available and loaded. Test this * and return success when trace point kvm_s390_create_vm @@ -112,7 +110,6 @@ static int test__checkevent_tracepoint_multi(struct evlist *evlist) } return TEST_OK; } -#endif /* HAVE_LIBTRACEEVENT */ static int test__checkevent_raw(struct evlist *evlist) { @@ -311,7 +308,6 @@ static int test__checkevent_breakpoint_rw(struct evlist *evlist) return TEST_OK; } -#ifdef HAVE_LIBTRACEEVENT static int test__checkevent_tracepoint_modifier(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); @@ -340,7 +336,6 @@ test__checkevent_tracepoint_multi_modifier(struct evlist *evlist) return test__checkevent_tracepoint_multi(evlist); } -#endif /* HAVE_LIBTRACEEVENT */ static int test__checkevent_raw_modifier(struct evlist *evlist) { @@ -629,7 +624,6 @@ static int test__checkevent_pmu(struct evlist *evlist) return TEST_OK; } -#ifdef HAVE_LIBTRACEEVENT static int test__checkevent_list(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); @@ -671,7 +665,6 @@ static int test__checkevent_list(struct evlist *evlist) return TEST_OK; } -#endif static int test__checkevent_pmu_name(struct evlist *evlist) { @@ -971,7 +964,6 @@ static int test__group2(struct evlist *evlist) return TEST_OK; } -#ifdef HAVE_LIBTRACEEVENT static int test__group3(struct evlist *evlist __maybe_unused) { struct evsel *evsel, *group1_leader = NULL, *group2_leader = NULL; @@ -1078,7 +1070,6 @@ static int test__group3(struct evlist *evlist __maybe_unused) } return TEST_OK; } -#endif static int test__group4(struct evlist *evlist __maybe_unused) { @@ -1813,7 +1804,6 @@ static int test__term_equal_legacy(struct evlist *evlist) return TEST_OK; } -#ifdef HAVE_LIBTRACEEVENT static int count_tracepoints(void) { struct dirent *events_ent; @@ -1867,7 +1857,6 @@ static int test__all_tracepoints(struct evlist *evlist) return test__checkevent_tracepoint_multi(evlist); } -#endif /* HAVE_LIBTRACEVENT */ struct evlist_test { const char *name; @@ -1876,7 +1865,6 @@ struct evlist_test { }; static const struct evlist_test test__events[] = { -#ifdef HAVE_LIBTRACEEVENT { .name = "syscalls:sys_enter_openat", .check = test__checkevent_tracepoint, @@ -1887,7 +1875,6 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_tracepoint_multi, /* 1 */ }, -#endif { .name = "r1a", .check = test__checkevent_raw, @@ -1938,7 +1925,6 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_breakpoint_w, /* 1 */ }, -#ifdef HAVE_LIBTRACEEVENT { .name = "syscalls:sys_enter_openat:k", .check = test__checkevent_tracepoint_modifier, @@ -1949,7 +1935,6 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_tracepoint_multi_modifier, /* 3 */ }, -#endif { .name = "r1a:kp", .check = test__checkevent_raw_modifier, @@ -1995,13 +1980,11 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_breakpoint_w_modifier, /* 2 */ }, -#ifdef HAVE_LIBTRACEEVENT { .name = "r1,syscalls:sys_enter_openat:k,1:1:hp", .check = test__checkevent_list, /* 3 */ }, -#endif { .name = "instructions:G", .check = test__checkevent_exclude_host_modifier, @@ -2032,13 +2015,11 @@ static const struct evlist_test test__events[] = { .check = test__group2, /* 9 */ }, -#ifdef HAVE_LIBTRACEEVENT { .name = "group1{syscalls:sys_enter_openat:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u", .check = test__group3, /* 0 */ }, -#endif { .name = "{cycles:u,instructions:kp}:p", .check = test__group4, @@ -2049,13 +2030,11 @@ static const struct evlist_test test__events[] = { .check = test__group5, /* 2 */ }, -#ifdef HAVE_LIBTRACEEVENT { .name = "*:*", .check = test__all_tracepoints, /* 3 */ }, -#endif { .name = "{cycles,cache-misses:G}:H", .check = test__group_gh1, @@ -2111,7 +2090,7 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_breakpoint_len_rw_modifier, /* 4 */ }, -#if defined(__s390x__) && defined(HAVE_LIBTRACEEVENT) +#if defined(__s390x__) { .name = "kvm-s390:kvm_s390_create_vm", .check = test__checkevent_tracepoint, @@ -2265,13 +2244,11 @@ static const struct evlist_test test__events[] = { .check = test__checkevent_breakpoint_2_events, /* 3 */ }, -#ifdef HAVE_LIBTRACEEVENT { .name = "9p:9p_client_req", .check = test__checkevent_tracepoint, /* 4 */ }, -#endif }; static const struct evlist_test test__events_pmu[] = { diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 6a681e3fb552..4a9f8e090cf4 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -452,9 +452,9 @@ static int test__name_cmp(struct test_suite *test __maybe_unused, int subtest __ } /** - * Test perf_pmu__match() that's used to search for a PMU given a name passed + * Test perf_pmu__wildcard_match() that's used to search for a PMU given a name passed * on the command line. The name that's passed may also be a filename type glob - * match. If the name does not match, perf_pmu__match() attempts to match the + * match. If the name does not match, perf_pmu__wildcard_match() attempts to match the * alias of the PMU, if provided. */ static int test__pmu_match(struct test_suite *test __maybe_unused, int subtest __maybe_unused) @@ -463,41 +463,44 @@ static int test__pmu_match(struct test_suite *test __maybe_unused, int subtest _ .name = "pmuname", }; - TEST_ASSERT_EQUAL("Exact match", perf_pmu__match(&test_pmu, "pmuname"), true); - TEST_ASSERT_EQUAL("Longer token", perf_pmu__match(&test_pmu, "longertoken"), false); - TEST_ASSERT_EQUAL("Shorter token", perf_pmu__match(&test_pmu, "pmu"), false); +#define TEST_PMU_MATCH(msg, to_match, expect) \ + TEST_ASSERT_EQUAL(msg, perf_pmu__wildcard_match(&test_pmu, to_match), expect) + + TEST_PMU_MATCH("Exact match", "pmuname", true); + TEST_PMU_MATCH("Longer token", "longertoken", false); + TEST_PMU_MATCH("Shorter token", "pmu", false); test_pmu.name = "pmuname_10"; - TEST_ASSERT_EQUAL("Diff suffix_", perf_pmu__match(&test_pmu, "pmuname_2"), false); - TEST_ASSERT_EQUAL("Sub suffix_", perf_pmu__match(&test_pmu, "pmuname_1"), true); - TEST_ASSERT_EQUAL("Same suffix_", perf_pmu__match(&test_pmu, "pmuname_10"), true); - TEST_ASSERT_EQUAL("No suffix_", perf_pmu__match(&test_pmu, "pmuname"), true); - TEST_ASSERT_EQUAL("Underscore_", perf_pmu__match(&test_pmu, "pmuname_"), true); - TEST_ASSERT_EQUAL("Substring_", perf_pmu__match(&test_pmu, "pmuna"), false); + TEST_PMU_MATCH("Diff suffix_", "pmuname_2", false); + TEST_PMU_MATCH("Sub suffix_", "pmuname_1", true); + TEST_PMU_MATCH("Same suffix_", "pmuname_10", true); + TEST_PMU_MATCH("No suffix_", "pmuname", true); + TEST_PMU_MATCH("Underscore_", "pmuname_", true); + TEST_PMU_MATCH("Substring_", "pmuna", false); test_pmu.name = "pmuname_ab23"; - TEST_ASSERT_EQUAL("Diff suffix hex_", perf_pmu__match(&test_pmu, "pmuname_2"), false); - TEST_ASSERT_EQUAL("Sub suffix hex_", perf_pmu__match(&test_pmu, "pmuname_ab"), true); - TEST_ASSERT_EQUAL("Same suffix hex_", perf_pmu__match(&test_pmu, "pmuname_ab23"), true); - TEST_ASSERT_EQUAL("No suffix hex_", perf_pmu__match(&test_pmu, "pmuname"), true); - TEST_ASSERT_EQUAL("Underscore hex_", perf_pmu__match(&test_pmu, "pmuname_"), true); - TEST_ASSERT_EQUAL("Substring hex_", perf_pmu__match(&test_pmu, "pmuna"), false); + TEST_PMU_MATCH("Diff suffix hex_", "pmuname_2", false); + TEST_PMU_MATCH("Sub suffix hex_", "pmuname_ab", true); + TEST_PMU_MATCH("Same suffix hex_", "pmuname_ab23", true); + TEST_PMU_MATCH("No suffix hex_", "pmuname", true); + TEST_PMU_MATCH("Underscore hex_", "pmuname_", true); + TEST_PMU_MATCH("Substring hex_", "pmuna", false); test_pmu.name = "pmuname10"; - TEST_ASSERT_EQUAL("Diff suffix", perf_pmu__match(&test_pmu, "pmuname2"), false); - TEST_ASSERT_EQUAL("Sub suffix", perf_pmu__match(&test_pmu, "pmuname1"), true); - TEST_ASSERT_EQUAL("Same suffix", perf_pmu__match(&test_pmu, "pmuname10"), true); - TEST_ASSERT_EQUAL("No suffix", perf_pmu__match(&test_pmu, "pmuname"), true); - TEST_ASSERT_EQUAL("Underscore", perf_pmu__match(&test_pmu, "pmuname_"), false); - TEST_ASSERT_EQUAL("Substring", perf_pmu__match(&test_pmu, "pmuna"), false); + TEST_PMU_MATCH("Diff suffix", "pmuname2", false); + TEST_PMU_MATCH("Sub suffix", "pmuname1", true); + TEST_PMU_MATCH("Same suffix", "pmuname10", true); + TEST_PMU_MATCH("No suffix", "pmuname", true); + TEST_PMU_MATCH("Underscore", "pmuname_", false); + TEST_PMU_MATCH("Substring", "pmuna", false); test_pmu.name = "pmunameab23"; - TEST_ASSERT_EQUAL("Diff suffix hex", perf_pmu__match(&test_pmu, "pmuname2"), false); - TEST_ASSERT_EQUAL("Sub suffix hex", perf_pmu__match(&test_pmu, "pmunameab"), true); - TEST_ASSERT_EQUAL("Same suffix hex", perf_pmu__match(&test_pmu, "pmunameab23"), true); - TEST_ASSERT_EQUAL("No suffix hex", perf_pmu__match(&test_pmu, "pmuname"), true); - TEST_ASSERT_EQUAL("Underscore hex", perf_pmu__match(&test_pmu, "pmuname_"), false); - TEST_ASSERT_EQUAL("Substring hex", perf_pmu__match(&test_pmu, "pmuna"), false); + TEST_PMU_MATCH("Diff suffix hex", "pmuname2", false); + TEST_PMU_MATCH("Sub suffix hex", "pmunameab", true); + TEST_PMU_MATCH("Same suffix hex", "pmunameab23", true); + TEST_PMU_MATCH("No suffix hex", "pmuname", true); + TEST_PMU_MATCH("Underscore hex", "pmuname_", false); + TEST_PMU_MATCH("Substring hex", "pmuna", false); /* * 2 hex chars or less are not considered suffixes so it shouldn't be @@ -505,7 +508,7 @@ static int test__pmu_match(struct test_suite *test __maybe_unused, int subtest _ * false results here than above. */ test_pmu.name = "pmuname_a3"; - TEST_ASSERT_EQUAL("Diff suffix 2 hex_", perf_pmu__match(&test_pmu, "pmuname_2"), false); + TEST_PMU_MATCH("Diff suffix 2 hex_", "pmuname_2", false); /* * This one should be false, but because pmuname_a3 ends in 3 which is * decimal, it's not possible to determine if it's a short hex suffix or @@ -513,19 +516,19 @@ static int test__pmu_match(struct test_suite *test __maybe_unused, int subtest _ * length of decimal suffix. Run the test anyway and expect the wrong * result. And slightly fuzzy matching shouldn't do too much harm. */ - TEST_ASSERT_EQUAL("Sub suffix 2 hex_", perf_pmu__match(&test_pmu, "pmuname_a"), true); - TEST_ASSERT_EQUAL("Same suffix 2 hex_", perf_pmu__match(&test_pmu, "pmuname_a3"), true); - TEST_ASSERT_EQUAL("No suffix 2 hex_", perf_pmu__match(&test_pmu, "pmuname"), false); - TEST_ASSERT_EQUAL("Underscore 2 hex_", perf_pmu__match(&test_pmu, "pmuname_"), false); - TEST_ASSERT_EQUAL("Substring 2 hex_", perf_pmu__match(&test_pmu, "pmuna"), false); + TEST_PMU_MATCH("Sub suffix 2 hex_", "pmuname_a", true); + TEST_PMU_MATCH("Same suffix 2 hex_", "pmuname_a3", true); + TEST_PMU_MATCH("No suffix 2 hex_", "pmuname", false); + TEST_PMU_MATCH("Underscore 2 hex_", "pmuname_", false); + TEST_PMU_MATCH("Substring 2 hex_", "pmuna", false); test_pmu.name = "pmuname_5"; - TEST_ASSERT_EQUAL("Glob 1", perf_pmu__match(&test_pmu, "pmu*"), true); - TEST_ASSERT_EQUAL("Glob 2", perf_pmu__match(&test_pmu, "nomatch*"), false); - TEST_ASSERT_EQUAL("Seq 1", perf_pmu__match(&test_pmu, "pmuname_[12345]"), true); - TEST_ASSERT_EQUAL("Seq 2", perf_pmu__match(&test_pmu, "pmuname_[67890]"), false); - TEST_ASSERT_EQUAL("? 1", perf_pmu__match(&test_pmu, "pmuname_?"), true); - TEST_ASSERT_EQUAL("? 2", perf_pmu__match(&test_pmu, "pmuname_1?"), false); + TEST_PMU_MATCH("Glob 1", "pmu*", true); + TEST_PMU_MATCH("Glob 2", "nomatch*", false); + TEST_PMU_MATCH("Seq 1", "pmuname_[12345]", true); + TEST_PMU_MATCH("Seq 2", "pmuname_[67890]", false); + TEST_PMU_MATCH("? 1", "pmuname_?", true); + TEST_PMU_MATCH("? 2", "pmuname_1?", false); return TEST_OK; } diff --git a/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh b/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh index bead723e34af..8226449ac5c3 100755 --- a/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh +++ b/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh @@ -1,5 +1,5 @@ #!/bin/bash - +# perf_probe :: Reject blacklisted probes (exclusive) # SPDX-License-Identifier: GPL-2.0 # @@ -22,7 +22,7 @@ TEST_RESULT=0 BLACKFUNC_LIST=`head -n 5 /sys/kernel/debug/kprobes/blacklist 2> /dev/null | cut -f2` if [ -z "$BLACKFUNC_LIST" ]; then print_overall_skipped - exit 0 + exit 2 fi # try to find vmlinux with DWARF debug info diff --git a/tools/perf/tests/shell/base_probe/test_adding_kernel.sh b/tools/perf/tests/shell/base_probe/test_adding_kernel.sh index d541ffd44a93..df288cf90cd6 100755 --- a/tools/perf/tests/shell/base_probe/test_adding_kernel.sh +++ b/tools/perf/tests/shell/base_probe/test_adding_kernel.sh @@ -1,5 +1,5 @@ #!/bin/bash -# Add 'perf probe's, list and remove them +# perf_probe :: Add probes, list and remove them (exclusive) # SPDX-License-Identifier: GPL-2.0 # @@ -33,7 +33,7 @@ fi check_kprobes_available if [ $? -ne 0 ]; then print_overall_skipped - exit 0 + exit 2 fi @@ -169,7 +169,7 @@ print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "force-adding probes :: second pr (( TEST_RESULT += $? )) # adding existing probe with '--force' should pass -NO_OF_PROBES=`$CMD_PERF probe -l | wc -l` +NO_OF_PROBES=`$CMD_PERF probe -l $TEST_PROBE| wc -l` $CMD_PERF probe --force --add $TEST_PROBE 2> $LOGS_DIR/adding_kernel_forceadd_03.err PERF_EXIT_CODE=$? @@ -205,7 +205,7 @@ print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "using doubled probe" $CMD_PERF probe --del \* 2> $LOGS_DIR/adding_kernel_removing_wildcard.err PERF_EXIT_CODE=$? -../common/check_all_lines_matched.pl "Removed event: probe:$TEST_PROBE" "Removed event: probe:${TEST_PROBE}_1" < $LOGS_DIR/adding_kernel_removing_wildcard.err +../common/check_all_patterns_found.pl "Removed event: probe:$TEST_PROBE" "Removed event: probe:${TEST_PROBE}_1" < $LOGS_DIR/adding_kernel_removing_wildcard.err CHECK_EXIT_CODE=$? print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "removing multiple probes" diff --git a/tools/perf/tests/shell/base_probe/test_basic.sh b/tools/perf/tests/shell/base_probe/test_basic.sh index 09669ec479f2..9d8b5afbeddd 100755 --- a/tools/perf/tests/shell/base_probe/test_basic.sh +++ b/tools/perf/tests/shell/base_probe/test_basic.sh @@ -1,5 +1,5 @@ #!/bin/bash - +# perf_probe :: Basic perf probe functionality (exclusive) # SPDX-License-Identifier: GPL-2.0 # @@ -19,7 +19,7 @@ TEST_RESULT=0 if ! check_kprobes_available; then print_overall_skipped - exit 0 + exit 2 fi diff --git a/tools/perf/tests/shell/base_probe/test_invalid_options.sh b/tools/perf/tests/shell/base_probe/test_invalid_options.sh index 1fedfd8b0d0d..92f7254eb32a 100755 --- a/tools/perf/tests/shell/base_probe/test_invalid_options.sh +++ b/tools/perf/tests/shell/base_probe/test_invalid_options.sh @@ -1,5 +1,5 @@ #!/bin/bash - +# perf_probe :: Reject invalid options (exclusive) # SPDX-License-Identifier: GPL-2.0 # @@ -19,9 +19,12 @@ TEST_RESULT=0 if ! check_kprobes_available; then print_overall_skipped - exit 0 + exit 2 fi +# Check for presence of DWARF +$CMD_PERF check feature -q dwarf +[ $? -ne 0 ] && HINT_FAIL="Some of the tests need DWARF to run" ### missing argument @@ -75,5 +78,5 @@ done # print overall results -print_overall_results "$TEST_RESULT" +print_overall_results "$TEST_RESULT" $HINT_FAIL exit $? diff --git a/tools/perf/tests/shell/base_probe/test_line_semantics.sh b/tools/perf/tests/shell/base_probe/test_line_semantics.sh index d8f4bde0f585..20435b6bf6bc 100755 --- a/tools/perf/tests/shell/base_probe/test_line_semantics.sh +++ b/tools/perf/tests/shell/base_probe/test_line_semantics.sh @@ -1,5 +1,5 @@ #!/bin/bash - +# perf_probe :: Check patterns for line semantics (exclusive) # SPDX-License-Identifier: GPL-2.0 # @@ -20,9 +20,12 @@ TEST_RESULT=0 if ! check_kprobes_available; then print_overall_skipped - exit 0 + exit 2 fi +# Check for presence of DWARF +$CMD_PERF check feature -q dwarf +[ $? -ne 0 ] && HINT_FAIL="Some of the tests need DWARF to run" ### acceptable --line descriptions @@ -51,5 +54,5 @@ done # print overall results -print_overall_results "$TEST_RESULT" +print_overall_results "$TEST_RESULT" $HINT_FAIL exit $? diff --git a/tools/perf/tests/shell/base_report/setup.sh b/tools/perf/tests/shell/base_report/setup.sh index 4caa496660c6..b03501b2e8fc 100755 --- a/tools/perf/tests/shell/base_report/setup.sh +++ b/tools/perf/tests/shell/base_report/setup.sh @@ -1,5 +1,5 @@ #!/bin/bash - +# perftool-testsuite :: perf_report # SPDX-License-Identifier: GPL-2.0 # diff --git a/tools/perf/tests/shell/base_report/test_basic.sh b/tools/perf/tests/shell/base_report/test_basic.sh index 47677cbd4df3..2398eba4d3fd 100755 --- a/tools/perf/tests/shell/base_report/test_basic.sh +++ b/tools/perf/tests/shell/base_report/test_basic.sh @@ -1,5 +1,5 @@ #!/bin/bash - +# perf_report :: Basic perf report options (exclusive) # SPDX-License-Identifier: GPL-2.0 # diff --git a/tools/perf/tests/shell/common/init.sh b/tools/perf/tests/shell/common/init.sh index 075f17623c8e..26c7525651e0 100644 --- a/tools/perf/tests/shell/common/init.sh +++ b/tools/perf/tests/shell/common/init.sh @@ -46,10 +46,13 @@ print_results() print_overall_results() { RETVAL="$1"; shift + TASK_COMMENT="$*" + test -n "$TASK_COMMENT" && TASK_COMMENT=":: $TASK_COMMENT" + if [ $RETVAL -eq 0 ]; then _echo "$MALLPASS## [ PASS ] ##$MEND $TEST_NAME :: $THIS_TEST_NAME SUMMARY" else - _echo "$MALLFAIL## [ FAIL ] ##$MEND $TEST_NAME :: $THIS_TEST_NAME SUMMARY :: $RETVAL failures found" + _echo "$MALLFAIL## [ FAIL ] ##$MEND $TEST_NAME :: $THIS_TEST_NAME SUMMARY :: $RETVAL failures found $TASK_COMMENT" fi return $RETVAL } @@ -85,7 +88,7 @@ consider_skipping() # the runmode of a testcase needs to be at least the current suite's runmode if [ $PERFTOOL_TESTSUITE_RUNMODE -lt $TESTCASE_RUNMODE ]; then print_overall_skipped - exit 0 + exit 2 fi } diff --git a/tools/perf/tests/shell/coresight/Makefile b/tools/perf/tests/shell/coresight/Makefile index b070e779703e..fa08fd9a5991 100644 --- a/tools/perf/tests/shell/coresight/Makefile +++ b/tools/perf/tests/shell/coresight/Makefile @@ -24,6 +24,6 @@ CLEANDIRS = $(SUBDIRS:%=clean-%) clean: $(CLEANDIRS) $(CLEANDIRS): - $(call QUIET_CLEAN, test-$(@:clean-%=%)) $(Q)$(MAKE) -C $(@:clean-%=%) clean >/dev/null + $(call QUIET_CLEAN, test-$(@:clean-%=%)) $(MAKE) -C $(@:clean-%=%) clean >/dev/null .PHONY: all clean $(SUBDIRS) $(CLEANDIRS) $(INSTALLDIRS) diff --git a/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S b/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S index 75cf084a927d..577760046772 100644 --- a/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S +++ b/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S @@ -26,3 +26,5 @@ skip: mov x0, #0 mov x8, #93 // __NR_exit syscall svc #0 + +.section .note.GNU-stack, "", @progbits diff --git a/tools/perf/tests/shell/ftrace.sh b/tools/perf/tests/shell/ftrace.sh index 2df05052c324..c243731d2fbf 100755 --- a/tools/perf/tests/shell/ftrace.sh +++ b/tools/perf/tests/shell/ftrace.sh @@ -67,11 +67,8 @@ test_ftrace_latency() { test_ftrace_profile() { echo "perf ftrace profile test" - perf ftrace profile -m 16M sleep 0.1 > "${output}" + perf ftrace profile --graph-opts depth=5 sleep 0.1 > "${output}" grep ^# "${output}" - grep sleep "${output}" - grep schedule "${output}" - grep execve "${output}" time_re="[[:space:]]+1[[:digit:]]{5}\.[[:digit:]]{3}" # 100283.000 100283.000 100283.000 1 __x64_sys_clock_nanosleep # Check for one *clock_nanosleep line with a Count of just 1 that takes a bit more than 0.1 seconds diff --git a/tools/perf/tests/shell/perftool-testsuite_probe.sh b/tools/perf/tests/shell/perftool-testsuite_probe.sh index a0fec33a0358..7b1bfd0f888f 100755 --- a/tools/perf/tests/shell/perftool-testsuite_probe.sh +++ b/tools/perf/tests/shell/perftool-testsuite_probe.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perftool-testsuite_probe +# perftool-testsuite_probe (exclusive) # SPDX-License-Identifier: GPL-2.0 test -d "$(dirname "$0")/base_probe" || exit 2 diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 47a26f25db9f..d5e5193cceb6 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -1,5 +1,5 @@ #!/bin/sh -# probe libc's inet_pton & backtrace it with ping +# probe libc's inet_pton & backtrace it with ping (exclusive) # Installs a probe on libc's inet_pton function, that will use uprobes, # then use 'perf trace' on a ping to localhost asking for just one packet @@ -43,17 +43,8 @@ trace_libc_inet_pton_backtrace() { echo "((__GI_)?getaddrinfo|text_to_binary_address)\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected echo "(gaih_inet|main)\+0x[[:xdigit:]]+[[:space:]]\(inlined|.*/bin/ping.*\)$" >> $expected ;; - ppc64|ppc64le) - eventattr='max-stack=4' - # Add gaih_inet to expected backtrace only if it is part of libc. - if nm $libc | grep -F -q gaih_inet.; then - echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected - fi - echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected - echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected - ;; *) - eventattr='max-stack=3' + eventattr='max-stack=4' echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected ;; esac @@ -76,14 +67,25 @@ trace_libc_inet_pton_backtrace() { fi perf script -i $perf_data | tac | grep -m1 ^ping -B9 | tac > $perf_script - exec 3<$perf_script exec 4<$expected - while read line <&3 && read -r pattern <&4; do + while read -r pattern <&4; do + echo "Pattern: $pattern" [ -z "$pattern" ] && break - echo $line - echo "$line" | grep -E -q "$pattern" - if [ $? -ne 0 ] ; then - printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line" + + found=0 + + # Search lines in the perf script result + exec 3<$perf_script + while read line <&3; do + [ -z "$line" ] && break + echo " Matching: $line" + ! echo "$line" | grep -E -q "$pattern" + found=$? + [ $found -eq 1 ] && break + done + + if [ $found -ne 1 ] ; then + printf "FAIL: Didn't find the expected backtrace entry \"%s\"\n" "$pattern" return 1 fi done diff --git a/tools/perf/tests/shell/record_bpf_filter.sh b/tools/perf/tests/shell/record_bpf_filter.sh index 1b58ccc1fd88..4d6c3c1b7fb9 100755 --- a/tools/perf/tests/shell/record_bpf_filter.sh +++ b/tools/perf/tests/shell/record_bpf_filter.sh @@ -89,7 +89,7 @@ test_bpf_filter_fail() { test_bpf_filter_group() { echo "Group bpf-filter test" - if ! perf record -e task-clock --filter 'period > 1000 || ip > 0' \ + if ! perf record -e task-clock --filter 'period > 1000, ip > 0' \ -o /dev/null true 2>/dev/null then echo "Group bpf-filter test [Failed should succeed]" @@ -97,7 +97,7 @@ test_bpf_filter_group() { return fi - if ! perf record -e task-clock --filter 'cpu > 0 || ip > 0' \ + if ! perf record -e task-clock --filter 'period > 1000 , cpu > 0 || ip > 0' \ -o /dev/null true 2>&1 | grep -q PERF_SAMPLE_CPU then echo "Group bpf-filter test [Failed forbidden CPU]" diff --git a/tools/perf/tests/shell/stat+std_output.sh b/tools/perf/tests/shell/stat+std_output.sh index cbf2894b2c84..0f7967be60af 100755 --- a/tools/perf/tests/shell/stat+std_output.sh +++ b/tools/perf/tests/shell/stat+std_output.sh @@ -13,7 +13,7 @@ stat_output=$(mktemp /tmp/__perf_test.stat_output.std.XXXXX) event_name=(cpu-clock task-clock context-switches cpu-migrations page-faults stalled-cycles-frontend stalled-cycles-backend cycles instructions branches branch-misses) event_metric=("CPUs utilized" "CPUs utilized" "/sec" "/sec" "/sec" "frontend cycles idle" "backend cycles idle" "GHz" "insn per cycle" "/sec" "of all branches") -skip_metric=("stalled cycles per insn" "tma_" "retiring" "frontend_bound" "bad_speculation" "backend_bound") +skip_metric=("stalled cycles per insn" "tma_" "retiring" "frontend_bound" "bad_speculation" "backend_bound" "TopdownL1" "percent of slots") cleanup() { rm -f "${stat_output}" diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh index 8b148b300be1..9c466c0efa85 100755 --- a/tools/perf/tests/shell/stat_all_pmu.sh +++ b/tools/perf/tests/shell/stat_all_pmu.sh @@ -2,7 +2,6 @@ # perf all PMU test (exclusive) # SPDX-License-Identifier: GPL-2.0 -set -e err=0 result="" @@ -16,34 +15,55 @@ trap trap_cleanup EXIT TERM INT # Test all PMU events; however exclude parameterized ones (name contains '?') for p in $(perf list --raw-dump pmu | sed 's/[[:graph:]]\+?[[:graph:]]\+[[:space:]]//g') do - echo "Testing $p" - result=$(perf stat -e "$p" true 2>&1) - if echo "$result" | grep -q "$p" + echo -n "Testing $p -- " + output=$(perf stat -e "$p" true 2>&1) + stat_result=$? + if echo "$output" | grep -q "$p" then # Event seen in output. - continue - fi - if echo "$result" | grep -q "<not supported>" - then - # Event not supported, so ignore. - continue + if [ $stat_result -eq 0 ] && ! echo "$output" | grep -q "<not supported>" + then + # Event supported. + echo "supported" + continue + elif echo "$output" | grep -q "<not supported>" + then + # Event not supported, so ignore. + echo "not supported" + continue + elif echo "$output" | grep -q "No permission to enable" + then + # No permissions, so ignore. + echo "no permission to enable" + continue + elif echo "$output" | grep -q "Bad event name" + then + # Non-existent event. + echo "Error: Bad event name" + echo "$output" + err=1 + continue + fi fi - if echo "$result" | grep -q "Access to performance monitoring and observability operations is limited." + + if echo "$output" | grep -q "Access to performance monitoring and observability operations is limited." then # Access is limited, so ignore. + echo "access limited" continue fi # We failed to see the event and it is supported. Possibly the workload was # too small so retry with something longer. - result=$(perf stat -e "$p" perf bench internals synthesize 2>&1) - if echo "$result" | grep -q "$p" + output=$(perf stat -e "$p" perf bench internals synthesize 2>&1) + if echo "$output" | grep -q "$p" then # Event seen in output. + echo "supported" continue fi echo "Error: event '$p' not printed in:" - echo "$result" + echo "$output" err=1 done diff --git a/tools/perf/tests/shell/test_arm_spe.sh b/tools/perf/tests/shell/test_arm_spe.sh index 3258368634f7..a69aab70dd8a 100755 --- a/tools/perf/tests/shell/test_arm_spe.sh +++ b/tools/perf/tests/shell/test_arm_spe.sh @@ -107,7 +107,37 @@ arm_spe_system_wide_test() { arm_spe_report "SPE system-wide testing" $err } +arm_spe_discard_test() { + echo "SPE discard mode" + + for f in /sys/bus/event_source/devices/arm_spe_*; do + if [ -e "$f/format/discard" ]; then + cpu=$(cut -c -1 "$f/cpumask") + break + fi + done + + if [ -z $cpu ]; then + arm_spe_report "SPE discard mode not present" 2 + return + fi + + # Test can use wildcard SPE instance and Perf will only open the event + # on instances that have that format flag. But make sure the target + # runs on an instance with discard mode otherwise we're not testing + # anything. + perf record -o ${perfdata} -e arm_spe/discard/ -N -B --no-bpf-event \ + -- taskset --cpu-list $cpu true + + if perf report -i ${perfdata} --stats | grep 'AUX events\|AUXTRACE events'; then + arm_spe_report "SPE discard mode found unexpected data" 1 + else + arm_spe_report "SPE discard mode" 0 + fi +} + arm_spe_snapshot_test arm_spe_system_wide_test +arm_spe_discard_test exit $glb_err diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh index 5f14d0cb013f..e01df7581393 100755 --- a/tools/perf/tests/shell/test_brstack.sh +++ b/tools/perf/tests/shell/test_brstack.sh @@ -30,7 +30,7 @@ test_user_branches() { echo "Testing user branch stack sampling" perf record -o $TMPDIR/perf.data --branch-filter any,save_type,u -- ${TESTPROG} > /dev/null 2>&1 - perf script -i $TMPDIR/perf.data --fields brstacksym | xargs -n1 > $TMPDIR/perf.script + perf script -i $TMPDIR/perf.data --fields brstacksym | tr -s ' ' '\n' > $TMPDIR/perf.script # example of branch entries: # brstack_foo+0x14/brstack_bar+0x40/P/-/-/0/CALL @@ -59,7 +59,7 @@ test_filter() { echo "Testing branch stack filtering permutation ($test_filter_filter,$test_filter_expect)" perf record -o $TMPDIR/perf.data --branch-filter $test_filter_filter,save_type,u -- ${TESTPROG} > /dev/null 2>&1 - perf script -i $TMPDIR/perf.data --fields brstack | xargs -n1 > $TMPDIR/perf.script + perf script -i $TMPDIR/perf.data --fields brstack | tr -s ' ' '\n' | grep '.' > $TMPDIR/perf.script # fail if we find any branch type that doesn't match any of the expected ones # also consider UNKNOWN branch types (-) diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh index c86da0235059..7da606db97cb 100755 --- a/tools/perf/tests/shell/test_data_symbol.sh +++ b/tools/perf/tests/shell/test_data_symbol.sh @@ -18,7 +18,7 @@ skip_if_no_mem_event() { skip_if_no_mem_event || exit 2 -skip_test_missing_symbol buf1 +skip_test_missing_symbol workload_datasym_buf1 TEST_PROGRAM="perf test -w datasym" PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX) @@ -26,18 +26,19 @@ ERR_FILE=$(mktemp /tmp/__perf_test.stderr.XXXXX) check_result() { # The memory report format is as below: - # 99.92% ... [.] buf1+0x38 + # 99.92% ... [.] workload_datasym_buf1+0x38 result=$(perf mem report -i ${PERF_DATA} -s symbol_daddr -q 2>&1 | - awk '/buf1/ { print $4 }') + awk '/workload_datasym_buf1/ { print $4 }') - # Testing is failed if has no any sample for "buf1" + # Testing is failed if has no any sample for "workload_datasym_buf1" [ -z "$result" ] && return 1 while IFS= read -r line; do - # The "data1" and "data2" fields in structure "buf1" have - # offset "0x0" and "0x38", returns failure if detect any - # other offset value. - if [ "$line" != "buf1+0x0" ] && [ "$line" != "buf1+0x38" ]; then + # The "data1" and "data2" fields in structure + # "workload_datasym_buf1" have offset "0x0" and "0x38", returns + # failure if detect any other offset value. + if [ "$line" != "workload_datasym_buf1+0x0" ] && \ + [ "$line" != "workload_datasym_buf1+0x38" ]; then return 1 fi done <<< "$result" diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index e6f0070975f6..f3a9a040bacc 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -644,6 +644,33 @@ test_pipe() return 0 } +test_pause_resume() +{ + echo "--- Test with pause / resume ---" + if ! perf_record_no_decode -o "${perfdatafile}" -e intel_pt/aux-action=start-paused/u uname ; then + echo "SKIP: pause / resume is not supported" + return 2 + fi + if ! perf_record_no_bpf -o "${perfdatafile}" \ + -e intel_pt/aux-action=start-paused/u \ + -e instructions/period=50000,aux-action=resume,name=Resume/u \ + -e instructions/period=100000,aux-action=pause,name=Pause/u uname ; then + echo "perf record with pause / resume failed" + return 1 + fi + if ! perf script -i "${perfdatafile}" --itrace=b -Fperiod,event | \ + awk 'BEGIN {paused=1;branches=0} + /Resume/ {paused=0} + /branches/ {if (paused) exit 1;branches=1} + /Pause/ {paused=1} + END {if (!branches) exit 1}' ; then + echo "perf record with pause / resume failed" + return 1 + fi + echo OK + return 0 +} + count_result() { if [ "$1" -eq 2 ] ; then @@ -672,6 +699,7 @@ test_power_event || ret=$? ; count_result $ret ; ret=0 test_no_tnt || ret=$? ; count_result $ret ; ret=0 test_event_trace || ret=$? ; count_result $ret ; ret=0 test_pipe || ret=$? ; count_result $ret ; ret=0 +test_pause_resume || ret=$? ; count_result $ret ; ret=0 cleanup diff --git a/tools/perf/tests/shell/test_task_analyzer.sh b/tools/perf/tests/shell/test_task_analyzer.sh index 7d76fc63d995..e194fcf61df3 100755 --- a/tools/perf/tests/shell/test_task_analyzer.sh +++ b/tools/perf/tests/shell/test_task_analyzer.sh @@ -1,5 +1,5 @@ #!/bin/bash -# perf script task-analyzer tests +# perf script task-analyzer tests (exclusive) # SPDX-License-Identifier: GPL-2.0 tmpdir=$(mktemp -d /tmp/perf-script-task-analyzer-XXXXX) diff --git a/tools/perf/tests/shell/trace_btf_general.sh b/tools/perf/tests/shell/trace_btf_general.sh new file mode 100755 index 000000000000..e9ee727f3433 --- /dev/null +++ b/tools/perf/tests/shell/trace_btf_general.sh @@ -0,0 +1,94 @@ +#!/bin/bash +# perf trace BTF general tests +# SPDX-License-Identifier: GPL-2.0 + +err=0 +set -e + +# shellcheck source=lib/probe.sh +. "$(dirname $0)"/lib/probe.sh + +file1=$(mktemp /tmp/file1_XXXX) +file2=$(echo $file1 | sed 's/file1/file2/g') + +buffer="buffer content" +perf_config_tmp=$(mktemp /tmp/.perfconfig_XXXXX) + +trap cleanup EXIT TERM INT HUP + +check_vmlinux() { + echo "Checking if vmlinux BTF exists" + if [ ! -f /sys/kernel/btf/vmlinux ] + then + echo "Skipped due to missing vmlinux BTF" + return 2 + fi + return 0 +} + +trace_test_string() { + echo "Testing perf trace's string augmentation" + if ! perf trace -e renameat* --max-events=1 -- mv ${file1} ${file2} 2>&1 | \ + grep -q -E "^mv/[0-9]+ renameat(2)?\(.*, \"${file1}\", .*, \"${file2}\", .*\) += +[0-9]+$" + then + echo "String augmentation test failed" + err=1 + fi +} + +trace_test_buffer() { + echo "Testing perf trace's buffer augmentation" + # echo will insert a newline (\10) at the end of the buffer + if ! perf trace -e write --max-events=1 -- echo "${buffer}" 2>&1 | \ + grep -q -E "^echo/[0-9]+ write\([0-9]+, ${buffer}.*, [0-9]+\) += +[0-9]+$" + then + echo "Buffer augmentation test failed" + err=1 + fi +} + +trace_test_struct_btf() { + echo "Testing perf trace's struct augmentation" + if ! perf trace -e clock_nanosleep --force-btf --max-events=1 -- sleep 1 2>&1 | \ + grep -q -E "^sleep/[0-9]+ clock_nanosleep\(0, 0, \{1,\}, 0x[0-9a-f]+\) += +[0-9]+$" + then + echo "BTF struct augmentation test failed" + err=1 + fi +} + +cleanup() { + rm -rf ${file1} ${file2} ${perf_config_tmp} +} + +trap_cleanup() { + echo "Unexpected signal in ${FUNCNAME[1]}" + cleanup + exit 1 +} + +# don't overwrite user's perf config +trace_config() { + export PERF_CONFIG=${perf_config_tmp} + perf config trace.show_arg_names=false trace.show_duration=false \ + trace.show_timestamp=false trace.args_alignment=0 +} + +skip_if_no_perf_trace || exit 2 +check_vmlinux || exit 2 + +trace_config + +trace_test_string + +if [ $err = 0 ]; then + trace_test_buffer +fi + +if [ $err = 0 ]; then + trace_test_struct_btf +fi + +cleanup + +exit $err diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c index e6fd934b027a..a67c756f90b8 100644 --- a/tools/perf/tests/sigtrap.c +++ b/tools/perf/tests/sigtrap.c @@ -56,6 +56,7 @@ static struct perf_event_attr make_event_attr(void) #ifdef HAVE_BPF_SKEL #include <bpf/btf.h> +#include <util/btf.h> static struct btf *btf; @@ -73,21 +74,6 @@ static void btf__exit(void) btf = NULL; } -static const struct btf_member *__btf_type__find_member_by_name(int type_id, const char *member_name) -{ - const struct btf_type *t = btf__type_by_id(btf, type_id); - const struct btf_member *m; - int i; - - for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) { - const char *current_member_name = btf__name_by_offset(btf, m->name_off); - if (!strcmp(current_member_name, member_name)) - return m; - } - - return NULL; -} - static bool attr_has_sigtrap(void) { int id; @@ -101,7 +87,7 @@ static bool attr_has_sigtrap(void) if (id < 0) return false; - return __btf_type__find_member_by_name(id, "sigtrap") != NULL; + return __btf_type__find_member_by_name(btf, id, "sigtrap") != NULL; } static bool kernel_with_sleepable_spinlocks(void) @@ -119,7 +105,7 @@ static bool kernel_with_sleepable_spinlocks(void) return false; // Only RT has a "lock" member for "struct spinlock" - member = __btf_type__find_member_by_name(id, "lock"); + member = __btf_type__find_member_by_name(btf, id, "lock"); if (member == NULL) return false; diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c index 6468cc0d0204..d60983657bad 100644 --- a/tools/perf/tests/stat.c +++ b/tools/perf/tests/stat.c @@ -27,7 +27,7 @@ static int process_stat_config_event(const struct perf_tool *tool __maybe_unused struct machine *machine __maybe_unused) { struct perf_record_stat_config *config = &event->stat_config; - struct perf_stat_config stat_config = {}; + struct perf_stat_config test_stat_config = {}; #define HAS(term, val) \ has_term(config, PERF_STAT_CONFIG_TERM__##term, val) @@ -39,25 +39,27 @@ static int process_stat_config_event(const struct perf_tool *tool __maybe_unused #undef HAS - perf_event__read_stat_config(&stat_config, config); + perf_event__read_stat_config(&test_stat_config, config); - TEST_ASSERT_VAL("wrong aggr_mode", stat_config.aggr_mode == AGGR_CORE); - TEST_ASSERT_VAL("wrong scale", stat_config.scale == 1); - TEST_ASSERT_VAL("wrong interval", stat_config.interval == 1); + TEST_ASSERT_VAL("wrong aggr_mode", test_stat_config.aggr_mode == AGGR_CORE); + TEST_ASSERT_VAL("wrong scale", test_stat_config.scale == 1); + TEST_ASSERT_VAL("wrong interval", test_stat_config.interval == 1); return 0; } static int test__synthesize_stat_config(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - struct perf_stat_config stat_config = { + struct perf_stat_config test_stat_config = { .aggr_mode = AGGR_CORE, .scale = 1, .interval = 1, }; TEST_ASSERT_VAL("failed to synthesize stat_config", - !perf_event__synthesize_stat_config(NULL, &stat_config, process_stat_config_event, NULL)); + !perf_event__synthesize_stat_config(NULL, &test_stat_config, + process_stat_config_event, + NULL)); return 0; } diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 5cab17a1942e..576f82a15015 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -583,4 +583,4 @@ out_err: goto out; } -DEFINE_SUITE("Track with sched_switch", switch_tracking); +DEFINE_SUITE_EXCLUSIVE("Track with sched_switch", switch_tracking); diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c index cf3ae0c1d871..1d5759d08141 100644 --- a/tools/perf/tests/tests-scripts.c +++ b/tools/perf/tests/tests-scripts.c @@ -174,7 +174,7 @@ static void append_script(int dir_fd, const char *name, char *desc, char filename[PATH_MAX], link[128]; struct test_suite *test_suite, **result_tmp; struct test_case *tests; - size_t len; + ssize_t len; char *exclusive; snprintf(link, sizeof(link), "/proc/%d/fd/%d", getpid(), dir_fd); diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index cb58b43aa063..8aea344536b8 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -81,6 +81,16 @@ struct test_suite { .test_cases = tests__##_name, \ } +#define DEFINE_SUITE_EXCLUSIVE(description, _name) \ + struct test_case tests__##_name[] = { \ + TEST_CASE_EXCLUSIVE(description, _name),\ + { .name = NULL, } \ + }; \ + struct test_suite suite__##_name = { \ + .desc = description, \ + .test_cases = tests__##_name, \ + } + /* Tests */ DECLARE_SUITE(vmlinux_matches_kallsyms); DECLARE_SUITE(openat_syscall_event); diff --git a/tools/perf/tests/tool_pmu.c b/tools/perf/tests/tool_pmu.c index 187942b749b7..1e900ef92e37 100644 --- a/tools/perf/tests/tool_pmu.c +++ b/tools/perf/tests/tool_pmu.c @@ -27,7 +27,7 @@ static int do_test(enum tool_pmu_event ev, bool with_pmu) parse_events_error__init(&err); ret = parse_events(evlist, str, &err); if (ret) { - if (tool_pmu__skip_event(tool_pmu__event_to_str(ev))) { + if (!tool_pmu__event_to_str(ev)) { ret = TEST_OK; goto out; } @@ -59,7 +59,7 @@ static int do_test(enum tool_pmu_event ev, bool with_pmu) } } - if (!found && !tool_pmu__skip_event(tool_pmu__event_to_str(ev))) { + if (!found && tool_pmu__event_to_str(ev)) { pr_debug("FAILED %s:%d Didn't find tool event '%s' in parsed evsels\n", __FILE__, __LINE__, str); ret = TEST_FAIL; diff --git a/tools/perf/tests/workloads/datasym.c b/tools/perf/tests/workloads/datasym.c index 8e08fc75a973..1d0b7d64e1ba 100644 --- a/tools/perf/tests/workloads/datasym.c +++ b/tools/perf/tests/workloads/datasym.c @@ -1,3 +1,6 @@ +#include <stdlib.h> +#include <signal.h> +#include <unistd.h> #include <linux/compiler.h> #include "../tests.h" @@ -7,16 +10,33 @@ typedef struct _buf { char data2; } buf __attribute__((aligned(64))); -static buf buf1 = { +/* volatile to try to avoid the compiler seeing reserved as unused. */ +static volatile buf workload_datasym_buf1 = { /* to have this in the data section */ .reserved[0] = 1, }; -static int datasym(int argc __maybe_unused, const char **argv __maybe_unused) +static volatile sig_atomic_t done; + +static void sighandler(int sig __maybe_unused) +{ + done = 1; +} + +static int datasym(int argc, const char **argv) { - for (;;) { - buf1.data1++; - if (buf1.data1 == 123) { + int sec = 1; + + if (argc > 0) + sec = atoi(argv[0]); + + signal(SIGINT, sighandler); + signal(SIGALRM, sighandler); + alarm(sec); + + while (!done) { + workload_datasym_buf1.data1++; + if (workload_datasym_buf1.data1 == 123) { /* * Add some 'noise' in the loop to work around errata * 1694299 on Arm N1. @@ -30,9 +50,9 @@ static int datasym(int argc __maybe_unused, const char **argv __maybe_unused) * longer a continuous repeating pattern that interacts * badly with the bias. */ - buf1.data1++; + workload_datasym_buf1.data1++; } - buf1.data2 += buf1.data1; + workload_datasym_buf1.data2 += workload_datasym_buf1.data1; } return 0; } diff --git a/tools/perf/tests/workloads/landlock.c b/tools/perf/tests/workloads/landlock.c index e2b5ef647c09..1f285b7b6236 100644 --- a/tools/perf/tests/workloads/landlock.c +++ b/tools/perf/tests/workloads/landlock.c @@ -10,7 +10,7 @@ * 'perf test' workload) we just add the required types and defines here instead * of including linux/landlock, that isn't available in older systems. * - * We are not interested in the the result of the syscall, just in intercepting + * We are not interested in the result of the syscall, just in intercepting * its arguments. */ diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh index 30d3889b2957..b22890b8d272 100755 --- a/tools/perf/trace/beauty/arch_errno_names.sh +++ b/tools/perf/trace/beauty/arch_errno_names.sh @@ -57,7 +57,8 @@ create_arch_errno_table_func() archlist="$1" default="$2" - printf 'arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch)\n' + printf 'static arch_syscalls__strerrno_t *\n' + printf 'arch_syscalls__strerrno_function(const char *arch)\n' printf '{\n' for arch in $archlist; do arch_str=$(arch_string "$arch") diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index d7e727345dab..135d6ce88fb3 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -754,7 +754,7 @@ static int annotate_browser__run(struct annotate_browser *browser, hbt->timer(hbt->arg); if (delay_secs != 0) { - symbol__annotate_decay_histogram(sym, evsel->core.idx); + symbol__annotate_decay_histogram(sym, evsel); hists__scnprintf_title(hists, title, sizeof(title)); annotate_browser__show(&browser->b, title, help); } diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index e437d7889de6..2d04ece833aa 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -1,16 +1,18 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../../builtin.h" -#include "../../perf.h" #include "../../util/util.h" // perf_exe() #include "../util.h" +#include "../../util/evlist.h" #include "../../util/hist.h" #include "../../util/debug.h" +#include "../../util/session.h" #include "../../util/symbol.h" #include "../browser.h" #include "../libslang.h" #include "config.h" +#include <linux/err.h> #include <linux/string.h> #include <linux/zalloc.h> +#include <subcmd/exec-cmd.h> #include <stdlib.h> #define SCRIPT_NAMELEN 128 @@ -78,6 +80,177 @@ static int scripts_config(const char *var, const char *value, void *data) } /* + * Some scripts specify the required events in their "xxx-record" file, + * this function will check if the events in perf.data match those + * mentioned in the "xxx-record". + * + * Fixme: All existing "xxx-record" are all in good formats "-e event ", + * which is covered well now. And new parsing code should be added to + * cover the future complex formats like event groups etc. + */ +static int check_ev_match(int dir_fd, const char *scriptname, struct perf_session *session) +{ + char line[BUFSIZ]; + FILE *fp; + + { + char filename[FILENAME_MAX + 5]; + int fd; + + scnprintf(filename, sizeof(filename), "bin/%s-record", scriptname); + fd = openat(dir_fd, filename, O_RDONLY); + if (fd == -1) + return -1; + fp = fdopen(fd, "r"); + if (!fp) + return -1; + } + + while (fgets(line, sizeof(line), fp)) { + char *p = skip_spaces(line); + + if (*p == '#') + continue; + + while (strlen(p)) { + int match, len; + struct evsel *pos; + char evname[128]; + + p = strstr(p, "-e"); + if (!p) + break; + + p += 2; + p = skip_spaces(p); + len = strcspn(p, " \t"); + if (!len) + break; + + snprintf(evname, len + 1, "%s", p); + + match = 0; + evlist__for_each_entry(session->evlist, pos) { + if (evsel__name_is(pos, evname)) { + match = 1; + break; + } + } + + if (!match) { + fclose(fp); + return -1; + } + } + } + + fclose(fp); + return 0; +} + +/* + * Return -1 if none is found, otherwise the actual scripts number. + * + * Currently the only user of this function is the script browser, which + * will list all statically runnable scripts, select one, execute it and + * show the output in a perf browser. + */ +static int find_scripts(char **scripts_array, char **scripts_path_array, int num, + int pathlen) +{ + struct dirent *script_dirent, *lang_dirent; + int scripts_dir_fd, lang_dir_fd; + DIR *scripts_dir, *lang_dir; + struct perf_session *session; + struct perf_data data = { + .path = input_name, + .mode = PERF_DATA_MODE_READ, + }; + char *temp; + int i = 0; + const char *exec_path = get_argv_exec_path(); + + session = perf_session__new(&data, NULL); + if (IS_ERR(session)) + return PTR_ERR(session); + + { + char scripts_path[PATH_MAX]; + + snprintf(scripts_path, sizeof(scripts_path), "%s/scripts", exec_path); + scripts_dir_fd = open(scripts_path, O_DIRECTORY); + pr_err("Failed to open directory '%s'", scripts_path); + if (scripts_dir_fd == -1) { + perf_session__delete(session); + return -1; + } + } + scripts_dir = fdopendir(scripts_dir_fd); + if (!scripts_dir) { + close(scripts_dir_fd); + perf_session__delete(session); + return -1; + } + + while ((lang_dirent = readdir(scripts_dir)) != NULL) { + if (lang_dirent->d_type != DT_DIR && + (lang_dirent->d_type == DT_UNKNOWN && + !is_directory_at(scripts_dir_fd, lang_dirent->d_name))) + continue; + if (!strcmp(lang_dirent->d_name, ".") || !strcmp(lang_dirent->d_name, "..")) + continue; + +#ifndef HAVE_LIBPERL_SUPPORT + if (strstr(lang_dirent->d_name, "perl")) + continue; +#endif +#ifndef HAVE_LIBPYTHON_SUPPORT + if (strstr(lang_dirent->d_name, "python")) + continue; +#endif + + lang_dir_fd = openat(scripts_dir_fd, lang_dirent->d_name, O_DIRECTORY); + if (lang_dir_fd == -1) + continue; + lang_dir = fdopendir(lang_dir_fd); + if (!lang_dir) { + close(lang_dir_fd); + continue; + } + while ((script_dirent = readdir(lang_dir)) != NULL) { + if (script_dirent->d_type == DT_DIR) + continue; + if (script_dirent->d_type == DT_UNKNOWN && + is_directory_at(lang_dir_fd, script_dirent->d_name)) + continue; + /* Skip those real time scripts: xxxtop.p[yl] */ + if (strstr(script_dirent->d_name, "top.")) + continue; + if (i >= num) + break; + scnprintf(scripts_path_array[i], pathlen, "%s/scripts/%s/%s", + exec_path, + lang_dirent->d_name, + script_dirent->d_name); + temp = strchr(script_dirent->d_name, '.'); + snprintf(scripts_array[i], + (temp - script_dirent->d_name) + 1, + "%s", script_dirent->d_name); + + if (check_ev_match(lang_dir_fd, scripts_array[i], session)) + continue; + + i++; + } + closedir(lang_dir); + } + + closedir(scripts_dir); + perf_session__delete(session); + return i; +} + +/* * When success, will copy the full path of the selected script * into the buffer pointed by script_name, and return 0. * Return -1 on failure. diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index 6da24aa039eb..8920e298420a 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -3,6 +3,7 @@ #include "util/sort.h" #include "util/debug.h" #include "util/annotate.h" +#include "util/evlist.h" #include "util/evsel.h" #include "util/map.h" #include "util/dso.h" @@ -26,7 +27,7 @@ static const char *const col_names[] = { }; static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym, - struct disasm_line *dl, int evidx) + struct disasm_line *dl, const struct evsel *evsel) { struct annotation *notes; struct sym_hist *symhist; @@ -42,8 +43,8 @@ static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym, return 0; notes = symbol__annotation(sym); - symhist = annotation__histogram(notes, evidx); - entry = annotated_source__hist_entry(notes->src, evidx, dl->al.offset); + symhist = annotation__histogram(notes, evsel); + entry = annotated_source__hist_entry(notes->src, evsel, dl->al.offset); if (entry) nr_samples = entry->nr_samples; @@ -139,16 +140,17 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct map_symbol *ms, gtk_list_store_append(store, &iter); if (evsel__is_group_event(evsel)) { - for (i = 0; i < evsel->core.nr_members; i++) { + struct evsel *cur_evsel; + + for_each_group_evsel(cur_evsel, evsel__leader(evsel)) { ret += perf_gtk__get_percent(s + ret, sizeof(s) - ret, sym, pos, - evsel->core.idx + i); + cur_evsel); ret += scnprintf(s + ret, sizeof(s) - ret, " "); } } else { - ret = perf_gtk__get_percent(s, sizeof(s), sym, pos, - evsel->core.idx); + ret = perf_gtk__get_percent(s, sizeof(s), sym, pos, evsel); } if (ret) diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index e5491995adf0..34fda1d5eccb 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -121,7 +121,7 @@ int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, const char *fmtstr, hpp_snprint_fn print_fn, enum perf_hpp_fmt_type fmtype) { - int len = fmt->user_len ?: fmt->len; + int len = max(fmt->user_len ?: fmt->len, (int)strlen(fmt->name)); if (symbol_conf.field_sep) { return __hpp__fmt(hpp, he, get_field, fmtstr, 1, diff --git a/tools/perf/util/Build b/tools/perf/util/Build index c06d2ee9024c..5ec97e8d6b6d 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -86,7 +86,7 @@ perf-util-y += pmu-bison.o perf-util-y += hwmon_pmu.o perf-util-y += tool_pmu.o perf-util-y += svghelper.o -perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event-info.o +perf-util-y += trace-event-info.o perf-util-y += trace-event-scripting.o perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event.o perf-util-$(CONFIG_LIBTRACEEVENT) += trace-event-parse.o @@ -121,8 +121,10 @@ perf-util-y += spark.o perf-util-y += topdown.o perf-util-y += iostat.o perf-util-y += stream.o +perf-util-y += kvm-stat.o +perf-util-y += lock-contention.o perf-util-$(CONFIG_AUXTRACE) += auxtrace.o -perf-util-$(CONFIG_AUXTRACE) += intel-pt-decoder/ +perf-util-y += intel-pt-decoder/ perf-util-$(CONFIG_AUXTRACE) += intel-pt.o perf-util-$(CONFIG_AUXTRACE) += intel-bts.o perf-util-$(CONFIG_AUXTRACE) += arm-spe.o @@ -168,6 +170,7 @@ perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_off_cpu.o perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter.o perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-flex.o perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-bison.o +perf-util-$(CONFIG_PERF_BPF_SKEL) += btf.o ifeq ($(CONFIG_LIBTRACEEVENT),y) perf-util-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 31dce9b87bff..31bb326b07a6 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -209,7 +209,7 @@ static int __symbol__account_cycles(struct cyc_hist *ch, } static int __symbol__inc_addr_samples(struct map_symbol *ms, - struct annotated_source *src, int evidx, u64 addr, + struct annotated_source *src, struct evsel *evsel, u64 addr, struct perf_sample *sample) { struct symbol *sym = ms->sym; @@ -228,14 +228,14 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms, } offset = addr - sym->start; - h = annotated_source__histogram(src, evidx); + h = annotated_source__histogram(src, evsel); if (h == NULL) { pr_debug("%s(%d): ENOMEM! sym->name=%s, start=%#" PRIx64 ", addr=%#" PRIx64 ", end=%#" PRIx64 ", func: %d\n", __func__, __LINE__, sym->name, sym->start, addr, sym->end, sym->type == STT_FUNC); return -ENOMEM; } - hash_key = offset << 16 | evidx; + hash_key = offset << 16 | evsel->core.idx; if (!hashmap__find(src->samples, hash_key, &entry)) { entry = zalloc(sizeof(*entry)); if (entry == NULL) @@ -252,7 +252,7 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms, pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64 ", evidx=%d] => nr_samples: %" PRIu64 ", period: %" PRIu64 "\n", - sym->start, sym->name, addr, addr - sym->start, evidx, + sym->start, sym->name, addr, addr - sym->start, evsel->core.idx, entry->nr_samples, entry->period); return 0; } @@ -323,7 +323,7 @@ static int symbol__inc_addr_samples(struct map_symbol *ms, if (sym == NULL) return 0; src = symbol__hists(sym, evsel->evlist->core.nr_entries); - return src ? __symbol__inc_addr_samples(ms, src, evsel->core.idx, addr, sample) : 0; + return src ? __symbol__inc_addr_samples(ms, src, evsel, addr, sample) : 0; } static int symbol__account_br_cntr(struct annotated_branch *branch, @@ -861,15 +861,14 @@ static void calc_percent(struct annotation *notes, s64 offset, s64 end) { struct hists *hists = evsel__hists(evsel); - int evidx = evsel->core.idx; - struct sym_hist *sym_hist = annotation__histogram(notes, evidx); + struct sym_hist *sym_hist = annotation__histogram(notes, evsel); unsigned int hits = 0; u64 period = 0; while (offset < end) { struct sym_hist_entry *entry; - entry = annotated_source__hist_entry(notes->src, evidx, offset); + entry = annotated_source__hist_entry(notes->src, evsel, offset); if (entry) { hits += entry->nr_samples; period += entry->period; @@ -1140,15 +1139,14 @@ static void print_summary(struct rb_root *root, const char *filename) static void symbol__annotate_hits(struct symbol *sym, struct evsel *evsel) { - int evidx = evsel->core.idx; struct annotation *notes = symbol__annotation(sym); - struct sym_hist *h = annotation__histogram(notes, evidx); + struct sym_hist *h = annotation__histogram(notes, evsel); u64 len = symbol__size(sym), offset; for (offset = 0; offset < len; ++offset) { struct sym_hist_entry *entry; - entry = annotated_source__hist_entry(notes->src, evidx, offset); + entry = annotated_source__hist_entry(notes->src, evsel, offset); if (entry && entry->nr_samples != 0) printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2, sym->start + offset, entry->nr_samples); @@ -1178,7 +1176,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) const char *d_filename; const char *evsel_name = evsel__name(evsel); struct annotation *notes = symbol__annotation(sym); - struct sym_hist *h = annotation__histogram(notes, evsel->core.idx); + struct sym_hist *h = annotation__histogram(notes, evsel); struct annotation_line *pos, *queue = NULL; struct annotation_options *opts = &annotate_opts; u64 start = map__rip_2objdump(map, sym->start); @@ -1364,18 +1362,18 @@ out_free_filename: return err; } -void symbol__annotate_zero_histogram(struct symbol *sym, int evidx) +void symbol__annotate_zero_histogram(struct symbol *sym, struct evsel *evsel) { struct annotation *notes = symbol__annotation(sym); - struct sym_hist *h = annotation__histogram(notes, evidx); + struct sym_hist *h = annotation__histogram(notes, evsel); memset(h, 0, sizeof(*notes->src->histograms) * notes->src->nr_histograms); } -void symbol__annotate_decay_histogram(struct symbol *sym, int evidx) +void symbol__annotate_decay_histogram(struct symbol *sym, struct evsel *evsel) { struct annotation *notes = symbol__annotation(sym); - struct sym_hist *h = annotation__histogram(notes, evidx); + struct sym_hist *h = annotation__histogram(notes, evsel); struct annotation_line *al; h->nr_samples = 0; @@ -1385,7 +1383,7 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx) if (al->offset == -1) continue; - entry = annotated_source__hist_entry(notes->src, evidx, al->offset); + entry = annotated_source__hist_entry(notes->src, evsel, al->offset); if (entry == NULL) continue; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 858912157e01..98db1b88daf4 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -15,6 +15,7 @@ #include "hashmap.h" #include "disasm.h" #include "branch.h" +#include "evsel.h" struct hist_browser_timer; struct hist_entry; @@ -23,7 +24,6 @@ struct map_symbol; struct addr_map_symbol; struct option; struct perf_sample; -struct evsel; struct symbol; struct annotated_data_type; @@ -378,21 +378,23 @@ static inline u8 annotation__br_cntr_width(void) void annotation__update_column_widths(struct annotation *notes); void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *ms); -static inline struct sym_hist *annotated_source__histogram(struct annotated_source *src, int idx) +static inline struct sym_hist *annotated_source__histogram(struct annotated_source *src, + const struct evsel *evsel) { - return &src->histograms[idx]; + return &src->histograms[evsel->core.idx]; } -static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx) +static inline struct sym_hist *annotation__histogram(struct annotation *notes, + const struct evsel *evsel) { - return annotated_source__histogram(notes->src, idx); + return annotated_source__histogram(notes->src, evsel); } static inline struct sym_hist_entry * -annotated_source__hist_entry(struct annotated_source *src, int idx, u64 offset) +annotated_source__hist_entry(struct annotated_source *src, const struct evsel *evsel, u64 offset) { struct sym_hist_entry *entry; - long key = offset << 16 | idx; + long key = offset << 16 | evsel->core.idx; if (!hashmap__find(src->samples, key, &entry)) return NULL; @@ -446,6 +448,7 @@ enum symbol_disassemble_errno { SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP, SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE, SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF, + SYMBOL_ANNOTATE_ERRNO__COULDNT_DETERMINE_FILE_TYPE, __SYMBOL_ANNOTATE_ERRNO__END, }; @@ -453,8 +456,8 @@ enum symbol_disassemble_errno { int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen); int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel); -void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); -void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); +void symbol__annotate_zero_histogram(struct symbol *sym, struct evsel *evsel); +void symbol__annotate_decay_histogram(struct symbol *sym, struct evsel *evsel); void annotated_source__purge(struct annotated_source *as); int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel); diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h index 358c611eeddb..4bcd627e859f 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h @@ -67,6 +67,15 @@ enum arm_spe_common_data_source { ARM_SPE_COMMON_DS_DRAM = 0xe, }; +enum arm_spe_ampereone_data_source { + ARM_SPE_AMPEREONE_LOCAL_CHIP_CACHE_OR_DEVICE = 0x0, + ARM_SPE_AMPEREONE_SLC = 0x3, + ARM_SPE_AMPEREONE_REMOTE_CHIP_CACHE = 0x5, + ARM_SPE_AMPEREONE_DDR = 0x7, + ARM_SPE_AMPEREONE_L1D = 0x8, + ARM_SPE_AMPEREONE_L2D = 0x9, +}; + struct arm_spe_record { enum arm_spe_sample_type type; int err; diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index dbf13f47879c..f1365ce69ba0 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -37,6 +37,8 @@ #include "../../arch/arm64/include/asm/cputype.h" #define MAX_TIMESTAMP (~0ULL) +#define is_ldst_op(op) (!!((op) & ARM_SPE_OP_LDST)) + struct arm_spe { struct auxtrace auxtrace; struct auxtrace_queues queues; @@ -103,6 +105,18 @@ struct arm_spe_queue { u32 flags; }; +struct data_source_handle { + const struct midr_range *midr_ranges; + void (*ds_synth)(const struct arm_spe_record *record, + union perf_mem_data_src *data_src); +}; + +#define DS(range, func) \ + { \ + .midr_ranges = range, \ + .ds_synth = arm_spe__synth_##func, \ + } + static void arm_spe_dump(struct arm_spe *spe __maybe_unused, unsigned char *buf, size_t len) { @@ -443,6 +457,11 @@ static const struct midr_range common_ds_encoding_cpus[] = { {}, }; +static const struct midr_range ampereone_ds_encoding_cpus[] = { + MIDR_ALL_VERSIONS(MIDR_AMPERE1A), + {}, +}; + static void arm_spe__sample_flags(struct arm_spe_queue *speq) { const struct arm_spe_record *record = &speq->decoder->record; @@ -532,6 +551,49 @@ static void arm_spe__synth_data_source_common(const struct arm_spe_record *recor } } +/* + * Source is IMPDEF. Here we convert the source code used on AmpereOne cores + * to the common (Neoverse, Cortex) to avoid duplicating the decoding code. + */ +static void arm_spe__synth_data_source_ampereone(const struct arm_spe_record *record, + union perf_mem_data_src *data_src) +{ + struct arm_spe_record common_record; + + switch (record->source) { + case ARM_SPE_AMPEREONE_LOCAL_CHIP_CACHE_OR_DEVICE: + common_record.source = ARM_SPE_COMMON_DS_PEER_CORE; + break; + case ARM_SPE_AMPEREONE_SLC: + common_record.source = ARM_SPE_COMMON_DS_SYS_CACHE; + break; + case ARM_SPE_AMPEREONE_REMOTE_CHIP_CACHE: + common_record.source = ARM_SPE_COMMON_DS_REMOTE; + break; + case ARM_SPE_AMPEREONE_DDR: + common_record.source = ARM_SPE_COMMON_DS_DRAM; + break; + case ARM_SPE_AMPEREONE_L1D: + common_record.source = ARM_SPE_COMMON_DS_L1D; + break; + case ARM_SPE_AMPEREONE_L2D: + common_record.source = ARM_SPE_COMMON_DS_L2; + break; + default: + pr_warning_once("AmpereOne: Unknown data source (0x%x)\n", + record->source); + return; + } + + common_record.op = record->op; + arm_spe__synth_data_source_common(&common_record, data_src); +} + +static const struct data_source_handle data_source_handles[] = { + DS(common_ds_encoding_cpus, data_source_common), + DS(ampereone_ds_encoding_cpus, data_source_ampereone), +}; + static void arm_spe__synth_memory_level(const struct arm_spe_record *record, union perf_mem_data_src *data_src) { @@ -555,12 +617,14 @@ static void arm_spe__synth_memory_level(const struct arm_spe_record *record, data_src->mem_lvl |= PERF_MEM_LVL_REM_CCE1; } -static bool arm_spe__is_common_ds_encoding(struct arm_spe_queue *speq) +static bool arm_spe__synth_ds(struct arm_spe_queue *speq, + const struct arm_spe_record *record, + union perf_mem_data_src *data_src) { struct arm_spe *spe = speq->spe; - bool is_in_cpu_list; u64 *metadata = NULL; - u64 midr = 0; + u64 midr; + unsigned int i; /* Metadata version 1 assumes all CPUs are the same (old behavior) */ if (spe->metadata_ver == 1) { @@ -592,18 +656,24 @@ static bool arm_spe__is_common_ds_encoding(struct arm_spe_queue *speq) midr = metadata[ARM_SPE_CPU_MIDR]; } - is_in_cpu_list = is_midr_in_range_list(midr, common_ds_encoding_cpus); - if (is_in_cpu_list) - return true; - else - return false; + for (i = 0; i < ARRAY_SIZE(data_source_handles); i++) { + if (is_midr_in_range_list(midr, data_source_handles[i].midr_ranges)) { + data_source_handles[i].ds_synth(record, data_src); + return true; + } + } + + return false; } static u64 arm_spe__synth_data_source(struct arm_spe_queue *speq, const struct arm_spe_record *record) { union perf_mem_data_src data_src = { .mem_op = PERF_MEM_OP_NA }; - bool is_common = arm_spe__is_common_ds_encoding(speq); + + /* Only synthesize data source for LDST operations */ + if (!is_ldst_op(record->op)) + return 0; if (record->op & ARM_SPE_OP_LD) data_src.mem_op = PERF_MEM_OP_LOAD; @@ -612,9 +682,7 @@ static u64 arm_spe__synth_data_source(struct arm_spe_queue *speq, else return 0; - if (is_common) - arm_spe__synth_data_source_common(record, &data_src); - else + if (!arm_spe__synth_ds(speq, record, &data_src)) arm_spe__synth_memory_level(record, &data_src); if (record->type & (ARM_SPE_TLB_ACCESS | ARM_SPE_TLB_MISS)) { @@ -705,7 +773,7 @@ static int arm_spe_sample(struct arm_spe_queue *speq) * When data_src is zero it means the record is not a memory operation, * skip to synthesize memory sample for this case. */ - if (spe->sample_memory && data_src) { + if (spe->sample_memory && is_ldst_op(record->op)) { err = arm_spe__synth_mem_sample(speq, spe->memory_id, data_src); if (err) return err; diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index ca8682966fae..4d1633d87eff 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -810,19 +810,76 @@ no_opt: return auxtrace_validate_aux_sample_size(evlist, opts); } -void auxtrace_regroup_aux_output(struct evlist *evlist) +static struct aux_action_opt { + const char *str; + u32 aux_action; + bool aux_event_opt; +} aux_action_opts[] = { + {"start-paused", BIT(0), true}, + {"pause", BIT(1), false}, + {"resume", BIT(2), false}, + {.str = NULL}, +}; + +static const struct aux_action_opt *auxtrace_parse_aux_action_str(const char *str) +{ + const struct aux_action_opt *opt; + + if (!str) + return NULL; + + for (opt = aux_action_opts; opt->str; opt++) + if (!strcmp(str, opt->str)) + return opt; + + return NULL; +} + +int auxtrace_parse_aux_action(struct evlist *evlist) { - struct evsel *evsel, *aux_evsel = NULL; struct evsel_config_term *term; + struct evsel *aux_evsel = NULL; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel__is_aux_event(evsel)) + bool is_aux_event = evsel__is_aux_event(evsel); + const struct aux_action_opt *opt; + + if (is_aux_event) aux_evsel = evsel; - term = evsel__get_config_term(evsel, AUX_OUTPUT); + term = evsel__get_config_term(evsel, AUX_ACTION); + if (!term) { + if (evsel__get_config_term(evsel, AUX_OUTPUT)) + goto regroup; + continue; + } + opt = auxtrace_parse_aux_action_str(term->val.str); + if (!opt) { + pr_err("Bad aux-action '%s'\n", term->val.str); + return -EINVAL; + } + if (opt->aux_event_opt && !is_aux_event) { + pr_err("aux-action '%s' can only be used with AUX area event\n", + term->val.str); + return -EINVAL; + } + if (!opt->aux_event_opt && is_aux_event) { + pr_err("aux-action '%s' cannot be used for AUX area event itself\n", + term->val.str); + return -EINVAL; + } + evsel->core.attr.aux_action = opt->aux_action; +regroup: /* If possible, group with the AUX event */ - if (term && aux_evsel) + if (aux_evsel) evlist__regroup(evlist, aux_evsel, evsel); + if (!evsel__is_aux_event(evsel__leader(evsel))) { + pr_err("Events with aux-action must have AUX area event group leader\n"); + return -EINVAL; + } } + + return 0; } struct auxtrace_record *__weak diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index dddaf4f3ffed..b0db84d27b25 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -578,7 +578,7 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, int auxtrace_parse_sample_options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts, const char *str); -void auxtrace_regroup_aux_output(struct evlist *evlist); +int auxtrace_parse_aux_action(struct evlist *evlist); int auxtrace_record__options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts); @@ -799,8 +799,10 @@ int auxtrace_parse_sample_options(struct auxtrace_record *itr __maybe_unused, } static inline -void auxtrace_regroup_aux_output(struct evlist *evlist __maybe_unused) +int auxtrace_parse_aux_action(struct evlist *evlist __maybe_unused) { + pr_err("AUX area tracing not supported\n"); + return -EINVAL; } static inline diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l index f313404f95a9..6aa65ade3385 100644 --- a/tools/perf/util/bpf-filter.l +++ b/tools/perf/util/bpf-filter.l @@ -76,7 +76,7 @@ static int path_or_error(void) num_dec [0-9]+ num_hex 0[Xx][0-9a-fA-F]+ space [ \t]+ -path [^ \t\n]+ +path [^ \t\n,]+ ident [_a-zA-Z][_a-zA-Z0-9]+ %% diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c index 06d1c4018407..25fc280e414a 100644 --- a/tools/perf/util/bpf_ftrace.c +++ b/tools/perf/util/bpf_ftrace.c @@ -11,6 +11,7 @@ #include "util/debug.h" #include "util/evlist.h" #include "util/bpf_counter.h" +#include "util/stat.h" #include "util/bpf_skel/func_latency.skel.h" @@ -36,6 +37,9 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) return -1; } + skel->rodata->bucket_range = ftrace->bucket_range; + skel->rodata->min_latency = ftrace->min_latency; + /* don't need to set cpu filter for system-wide mode */ if (ftrace->target.cpu_list) { ncpus = perf_cpu_map__nr(ftrace->evlist->core.user_requested_cpus); @@ -83,6 +87,8 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) } } + skel->bss->min = INT64_MAX; + skel->links.func_begin = bpf_program__attach_kprobe(skel->progs.func_begin, false, func->name); if (IS_ERR(skel->links.func_begin)) { @@ -119,7 +125,7 @@ int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused) } int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, - int buckets[]) + int buckets[], struct stats *stats) { int i, fd, err; u32 idx; @@ -143,6 +149,13 @@ int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, buckets[idx] += hist[i]; } + if (skel->bss->count) { + stats->mean = skel->bss->total / skel->bss->count; + stats->n = skel->bss->count; + stats->max = skel->bss->max; + stats->min = skel->bss->min; + } + free(hist); return 0; } diff --git a/tools/perf/util/bpf_kwork.c b/tools/perf/util/bpf_kwork.c index 6c7126b7670d..5cff755c71fa 100644 --- a/tools/perf/util/bpf_kwork.c +++ b/tools/perf/util/bpf_kwork.c @@ -285,7 +285,7 @@ static int add_work(struct perf_kwork *kwork, (bpf_trace->get_work_name(key, &tmp.name))) return -1; - work = perf_kwork_add_work(kwork, tmp.class, &tmp); + work = kwork->add_work(kwork, tmp.class, &tmp); if (work == NULL) return -1; diff --git a/tools/perf/util/bpf_kwork_top.c b/tools/perf/util/bpf_kwork_top.c index 7261cad43468..b6f187dd9136 100644 --- a/tools/perf/util/bpf_kwork_top.c +++ b/tools/perf/util/bpf_kwork_top.c @@ -255,7 +255,7 @@ static int add_work(struct perf_kwork *kwork, struct work_key *key, bpf_trace = kwork_class_bpf_supported_list[type]; tmp.class = bpf_trace->class; - work = perf_kwork_add_work(kwork, tmp.class, &tmp); + work = kwork->add_work(kwork, tmp.class, &tmp); if (!work) return -1; diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index 41a1ad087895..fc8666222399 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -2,6 +2,7 @@ #include "util/cgroup.h" #include "util/debug.h" #include "util/evlist.h" +#include "util/hashmap.h" #include "util/machine.h" #include "util/map.h" #include "util/symbol.h" @@ -12,17 +13,106 @@ #include <linux/zalloc.h> #include <linux/string.h> #include <bpf/bpf.h> +#include <bpf/btf.h> #include <inttypes.h> #include "bpf_skel/lock_contention.skel.h" #include "bpf_skel/lock_data.h" static struct lock_contention_bpf *skel; +static bool has_slab_iter; +static struct hashmap slab_hash; + +static size_t slab_cache_hash(long key, void *ctx __maybe_unused) +{ + return key; +} + +static bool slab_cache_equal(long key1, long key2, void *ctx __maybe_unused) +{ + return key1 == key2; +} + +static void check_slab_cache_iter(struct lock_contention *con) +{ + struct btf *btf = btf__load_vmlinux_btf(); + s32 ret; + + hashmap__init(&slab_hash, slab_cache_hash, slab_cache_equal, /*ctx=*/NULL); + + if (btf == NULL) { + pr_debug("BTF loading failed: %s\n", strerror(errno)); + return; + } + + ret = btf__find_by_name_kind(btf, "bpf_iter__kmem_cache", BTF_KIND_STRUCT); + if (ret < 0) { + bpf_program__set_autoload(skel->progs.slab_cache_iter, false); + pr_debug("slab cache iterator is not available: %d\n", ret); + goto out; + } + + has_slab_iter = true; + + bpf_map__set_max_entries(skel->maps.slab_caches, con->map_nr_entries); +out: + btf__free(btf); +} + +static void run_slab_cache_iter(void) +{ + int fd; + char buf[256]; + long key, *prev_key; + + if (!has_slab_iter) + return; + + fd = bpf_iter_create(bpf_link__fd(skel->links.slab_cache_iter)); + if (fd < 0) { + pr_debug("cannot create slab cache iter: %d\n", fd); + return; + } + + /* This will run the bpf program */ + while (read(fd, buf, sizeof(buf)) > 0) + continue; + + close(fd); + + /* Read the slab cache map and build a hash with IDs */ + fd = bpf_map__fd(skel->maps.slab_caches); + prev_key = NULL; + while (!bpf_map_get_next_key(fd, prev_key, &key)) { + struct slab_cache_data *data; + + data = malloc(sizeof(*data)); + if (data == NULL) + break; + + if (bpf_map_lookup_elem(fd, &key, data) < 0) + break; + + hashmap__add(&slab_hash, data->id, data); + prev_key = &key; + } +} + +static void exit_slab_cache_iter(void) +{ + struct hashmap_entry *cur; + unsigned bkt; + + hashmap__for_each_entry(&slab_hash, cur, bkt) + free(cur->pvalue); + + hashmap__clear(&slab_hash); +} int lock_contention_prepare(struct lock_contention *con) { int i, fd; - int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1, ncgrps = 1; + int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1, ncgrps = 1, nslabs = 1; struct evlist *evlist = con->evlist; struct target *target = con->target; @@ -109,6 +199,15 @@ int lock_contention_prepare(struct lock_contention *con) skel->rodata->use_cgroup_v2 = 1; } + check_slab_cache_iter(con); + + if (con->filters->nr_slabs && has_slab_iter) { + skel->rodata->has_slab = 1; + nslabs = con->filters->nr_slabs; + } + + bpf_map__set_max_entries(skel->maps.slab_filter, nslabs); + if (lock_contention_bpf__load(skel) < 0) { pr_err("Failed to load lock-contention BPF skeleton\n"); return -1; @@ -179,6 +278,36 @@ int lock_contention_prepare(struct lock_contention *con) bpf_program__set_autoload(skel->progs.collect_lock_syms, false); lock_contention_bpf__attach(skel); + + /* run the slab iterator after attaching */ + run_slab_cache_iter(); + + if (con->filters->nr_slabs) { + u8 val = 1; + int cache_fd; + long key, *prev_key; + + fd = bpf_map__fd(skel->maps.slab_filter); + + /* Read the slab cache map and build a hash with its address */ + cache_fd = bpf_map__fd(skel->maps.slab_caches); + prev_key = NULL; + while (!bpf_map_get_next_key(cache_fd, prev_key, &key)) { + struct slab_cache_data data; + + if (bpf_map_lookup_elem(cache_fd, &key, &data) < 0) + break; + + for (i = 0; i < con->filters->nr_slabs; i++) { + if (!strcmp(con->filters->slabs[i], data.name)) { + bpf_map_update_elem(fd, &key, &val, BPF_ANY); + break; + } + } + prev_key = &key; + } + } + return 0; } @@ -347,6 +476,7 @@ static const char *lock_contention_get_name(struct lock_contention *con, if (con->aggr_mode == LOCK_AGGR_ADDR) { int lock_fd = bpf_map__fd(skel->maps.lock_syms); + struct slab_cache_data *slab_data; /* per-process locks set upper bits of the flags */ if (flags & LCD_F_MMAP_LOCK) @@ -365,6 +495,12 @@ static const char *lock_contention_get_name(struct lock_contention *con, return "rq_lock"; } + /* look slab_hash for dynamic locks in a slab object */ + if (hashmap__find(&slab_hash, flags & LCB_F_SLAB_ID_MASK, &slab_data)) { + snprintf(name_buf, sizeof(name_buf), "&%s", slab_data->name); + return name_buf; + } + return ""; } @@ -458,7 +594,7 @@ int lock_contention_read(struct lock_contention *con) if (con->save_callstack) { bpf_map_lookup_elem(stack, &key.stack_id, stack_trace); - if (!match_callstack_filter(machine, stack_trace)) { + if (!match_callstack_filter(machine, stack_trace, con->max_stack)) { con->nr_filtered += data.count; goto next; } @@ -539,5 +675,7 @@ int lock_contention_finish(struct lock_contention *con) cgroup__put(cgrp); } + exit_slab_cache_iter(); + return 0; } diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c index a590a8ac1f9d..4269b41d1771 100644 --- a/tools/perf/util/bpf_off_cpu.c +++ b/tools/perf/util/bpf_off_cpu.c @@ -100,6 +100,11 @@ static void check_sched_switch_args(void) const struct btf_type *t1, *t2, *t3; u32 type_id; + if (!btf) { + pr_debug("Missing btf, check if CONFIG_DEBUG_INFO_BTF is enabled\n"); + goto cleanup; + } + type_id = btf__find_by_name_kind(btf, "btf_trace_sched_switch", BTF_KIND_TYPEDEF); if ((s32)type_id < 0) diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c index f613dc9cb123..fb144811b34f 100644 --- a/tools/perf/util/bpf_skel/func_latency.bpf.c +++ b/tools/perf/util/bpf_skel/func_latency.bpf.c @@ -38,9 +38,18 @@ struct { int enabled = 0; +// stats +__s64 total; +__s64 count; +__s64 max; +__s64 min; + const volatile int has_cpu = 0; const volatile int has_task = 0; const volatile int use_nsec = 0; +const volatile unsigned int bucket_range; +const volatile unsigned int min_latency; +const volatile unsigned int max_latency; SEC("kprobe/func") int BPF_PROG(func_begin) @@ -92,7 +101,7 @@ int BPF_PROG(func_end) start = bpf_map_lookup_elem(&functime, &tid); if (start) { __s64 delta = bpf_ktime_get_ns() - *start; - __u32 key; + __u32 key = 0; __u64 *hist; bpf_map_delete_elem(&functime, &tid); @@ -100,17 +109,52 @@ int BPF_PROG(func_end) if (delta < 0) return 0; + if (bucket_range != 0) { + delta /= cmp_base; + + if (min_latency > 0) { + if (delta > min_latency) + delta -= min_latency; + else + goto do_lookup; + } + + // Less than 1 unit (ms or ns), or, in the future, + // than the min latency desired. + if (delta > 0) { // 1st entry: [ 1 unit .. bucket_range units ) + // clang 12 doesn't like s64 / u32 division + key = (__u64)delta / bucket_range + 1; + if (key >= NUM_BUCKET || + delta >= max_latency - min_latency) + key = NUM_BUCKET - 1; + } + + delta += min_latency; + goto do_lookup; + } // calculate index using delta for (key = 0; key < (NUM_BUCKET - 1); key++) { if (delta < (cmp_base << key)) break; } +do_lookup: hist = bpf_map_lookup_elem(&latency, &key); if (!hist) return 0; *hist += 1; + + if (bucket_range == 0) + delta /= cmp_base; + + __sync_fetch_and_add(&total, delta); + __sync_fetch_and_add(&count, 1); + + if (delta > max) + max = delta; + if (delta < min) + min = delta; } return 0; diff --git a/tools/perf/util/bpf_skel/kwork_top.bpf.c b/tools/perf/util/bpf_skel/kwork_top.bpf.c index 594da91965a2..73e32e063030 100644 --- a/tools/perf/util/bpf_skel/kwork_top.bpf.c +++ b/tools/perf/util/bpf_skel/kwork_top.bpf.c @@ -18,7 +18,9 @@ enum kwork_class_type { }; #define MAX_ENTRIES 102400 -#define MAX_NR_CPUS 2048 +#ifndef MAX_NR_CPUS +#define MAX_NR_CPUS 4096 +#endif #define PF_KTHREAD 0x00200000 #define MAX_COMMAND_LEN 16 diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 1069bda5d733..6533ea9b044c 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -100,6 +100,20 @@ struct { __uint(max_entries, 1); } cgroup_filter SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(long)); + __uint(value_size, sizeof(__u8)); + __uint(max_entries, 1); +} slab_filter SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(long)); + __uint(value_size, sizeof(struct slab_cache_data)); + __uint(max_entries, 1); +} slab_caches SEC(".maps"); + struct rw_semaphore___old { struct task_struct *owner; } __attribute__((preserve_access_index)); @@ -116,12 +130,15 @@ struct mm_struct___new { struct rw_semaphore mmap_lock; } __attribute__((preserve_access_index)); +extern struct kmem_cache *bpf_get_kmem_cache(u64 addr) __ksym __weak; + /* control flags */ const volatile int has_cpu; const volatile int has_task; const volatile int has_type; const volatile int has_addr; const volatile int has_cgroup; +const volatile int has_slab; const volatile int needs_callstack; const volatile int stack_skip; const volatile int lock_owner; @@ -136,6 +153,8 @@ int perf_subsys_id = -1; __u64 end_ts; +__u32 slab_cache_id; + /* error stat */ int task_fail; int stack_fail; @@ -202,7 +221,7 @@ static inline int can_record(u64 *ctx) __u64 addr = ctx[0]; ok = bpf_map_lookup_elem(&addr_filter, &addr); - if (!ok) + if (!ok && !has_slab) return 0; } @@ -215,6 +234,17 @@ static inline int can_record(u64 *ctx) return 0; } + if (has_slab && bpf_get_kmem_cache) { + __u8 *ok; + __u64 addr = ctx[0]; + long kmem_cache_addr; + + kmem_cache_addr = (long)bpf_get_kmem_cache(addr); + ok = bpf_map_lookup_elem(&slab_filter, &kmem_cache_addr); + if (!ok) + return 0; + } + return 1; } @@ -487,8 +517,28 @@ int contention_end(u64 *ctx) }; int err; - if (aggr_mode == LOCK_AGGR_ADDR) - first.flags |= check_lock_type(pelem->lock, pelem->flags); + if (aggr_mode == LOCK_AGGR_ADDR) { + first.flags |= check_lock_type(pelem->lock, + pelem->flags & LCB_F_TYPE_MASK); + + /* Check if it's from a slab object */ + if (bpf_get_kmem_cache) { + struct kmem_cache *s; + struct slab_cache_data *d; + + s = bpf_get_kmem_cache(pelem->lock); + if (s != NULL) { + /* + * Save the ID of the slab cache in the flags + * (instead of full address) to reduce the + * space in the contention_data. + */ + d = bpf_map_lookup_elem(&slab_caches, &s); + if (d != NULL) + first.flags |= d->id; + } + } + } err = bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST); if (err < 0) { @@ -563,4 +613,43 @@ int BPF_PROG(end_timestamp) return 0; } +/* + * bpf_iter__kmem_cache added recently so old kernels don't have it in the + * vmlinux.h. But we cannot add it here since it will cause a compiler error + * due to redefinition of the struct on later kernels. + * + * So it uses a CO-RE trick to access the member only if it has the type. + * This will support both old and new kernels without compiler errors. + */ +struct bpf_iter__kmem_cache___new { + struct kmem_cache *s; +} __attribute__((preserve_access_index)); + +SEC("iter/kmem_cache") +int slab_cache_iter(void *ctx) +{ + struct kmem_cache *s = NULL; + struct slab_cache_data d; + const char *nameptr; + + if (bpf_core_type_exists(struct bpf_iter__kmem_cache)) { + struct bpf_iter__kmem_cache___new *iter = ctx; + + s = iter->s; + } + + if (s == NULL) + return 0; + + nameptr = s->name; + bpf_probe_read_kernel_str(d.name, sizeof(d.name), nameptr); + + d.id = ++slab_cache_id << LCB_F_SLAB_ID_SHIFT; + if (d.id >= LCB_F_SLAB_ID_END) + return 0; + + bpf_map_update_elem(&slab_caches, &s, &d, BPF_NOEXIST); + return 0; +} + char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h index de12892f992f..c15f734d7fc4 100644 --- a/tools/perf/util/bpf_skel/lock_data.h +++ b/tools/perf/util/bpf_skel/lock_data.h @@ -32,7 +32,15 @@ struct contention_task_data { #define LCD_F_MMAP_LOCK (1U << 31) #define LCD_F_SIGHAND_LOCK (1U << 30) -#define LCB_F_MAX_FLAGS (1U << 7) +#define LCB_F_SLAB_ID_SHIFT 16 +#define LCB_F_SLAB_ID_START (1U << 16) +#define LCB_F_SLAB_ID_END (1U << 26) +#define LCB_F_SLAB_ID_MASK 0x03FF0000U + +#define LCB_F_TYPE_MAX (1U << 7) +#define LCB_F_TYPE_MASK 0x0000007FU + +#define SLAB_NAME_MAX 28 struct contention_data { u64 total_time; @@ -54,4 +62,9 @@ enum lock_class_sym { LOCK_CLASS_RQLOCK, }; +struct slab_cache_data { + u32 id; + char name[SLAB_NAME_MAX]; +}; + #endif /* UTIL_BPF_SKEL_LOCK_DATA_H */ diff --git a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h index 4dcad7b682bd..7b81d3173917 100644 --- a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h +++ b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h @@ -195,4 +195,12 @@ struct bpf_perf_event_data_kern { */ struct rq {}; +struct kmem_cache { + const char *name; +} __attribute__((preserve_access_index)); + +struct bpf_iter__kmem_cache { + struct kmem_cache *s; +} __attribute__((preserve_access_index)); + #endif // __VMLINUX_H diff --git a/tools/perf/util/btf.c b/tools/perf/util/btf.c new file mode 100644 index 000000000000..bb163fe87767 --- /dev/null +++ b/tools/perf/util/btf.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Copyright (C) 2024, Red Hat, Inc + */ + +#include <bpf/btf.h> +#include <util/btf.h> +#include <string.h> + +const struct btf_member *__btf_type__find_member_by_name(struct btf *btf, + int type_id, const char *member_name) +{ + const struct btf_type *t = btf__type_by_id(btf, type_id); + const struct btf_member *m; + int i; + + for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) { + const char *current_member_name = btf__name_by_offset(btf, m->name_off); + + if (!strcmp(current_member_name, member_name)) + return m; + } + + return NULL; +} diff --git a/tools/perf/util/btf.h b/tools/perf/util/btf.h new file mode 100644 index 000000000000..05e6e5bf23d6 --- /dev/null +++ b/tools/perf/util/btf.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_UTIL_BTF +#define __PERF_UTIL_BTF 1 + +struct btf; +struct btf_member; + +const struct btf_member *__btf_type__find_member_by_name(struct btf *btf, + int type_id, const char *member_name); +#endif // __PERF_UTIL_BTF diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 0f759dd96db7..fbcc0626f9ce 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -473,7 +473,7 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, leader = NULL; evlist__for_each_entry(orig_list, pos) { - evsel = evsel__clone(pos); + evsel = evsel__clone(/*dest=*/NULL, pos); if (evsel == NULL) goto out_err; diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 49b79cf0c5cc..8aa456d7c2cd 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -5,6 +5,8 @@ #include <internal/rc_check.h> #include <linux/refcount.h> #include <linux/zalloc.h> +#include <tools/libc_compat.h> // reallocarray + #include "rwsem.h" DECLARE_RC_STRUCT(comm_str) { diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 68f9407ca74b..2d07c9257a1a 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -13,6 +13,7 @@ #include <sys/param.h> #include "cache.h" #include "callchain.h" +#include "header.h" #include <subcmd/exec-cmd.h> #include "util/event.h" /* proc_map_timeout */ #include "util/hist.h" /* perf_hist_config */ @@ -34,6 +35,22 @@ #define DEBUG_CACHE_DIR ".debug" +#define METRIC_ONLY_LEN 20 + +struct perf_stat_config stat_config = { + .aggr_mode = AGGR_GLOBAL, + .aggr_level = MAX_CACHE_LVL + 1, + .scale = true, + .unit_width = 4, /* strlen("unit") */ + .run_count = 1, + .metric_only_len = METRIC_ONLY_LEN, + .walltime_nsecs_stats = &walltime_nsecs_stats, + .ru_stats = &ru_stats, + .big_num = true, + .ctl_fd = -1, + .ctl_fd_ack = -1, + .iostat_run = false, +}; char buildid_dir[MAXPATHLEN]; /* root dir for buildid, binary cache */ @@ -455,6 +472,16 @@ static int perf_ui_config(const char *var, const char *value) return 0; } +void perf_stat__set_big_num(int set) +{ + stat_config.big_num = (set != 0); +} + +static void perf_stat__set_no_csv_summary(int set) +{ + stat_config.no_csv_summary = (set != 0); +} + static int perf_stat_config(const char *var, const char *value) { if (!strcmp(var, "stat.big-num")) diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index 9971313d61c1..a727c95cb119 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -50,6 +50,7 @@ int perf_config_set__collect(struct perf_config_set *set, const char *file_name, const char *var, const char *value); void perf_config__exit(void); void perf_config__refresh(void); +int perf_config__set_variable(const char *var, const char *value); /** * perf_config_sections__for_each - iterate thru all the sections diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 27094211edd8..5c329ad614e9 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -293,7 +293,7 @@ struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data) die = cpu__get_die_id(cpu); /* There is no die_id on legacy system. */ - if (die == -1) + if (die < 0) die = 0; /* @@ -322,7 +322,7 @@ struct aggr_cpu_id aggr_cpu_id__cluster(struct perf_cpu cpu, void *data) struct aggr_cpu_id id; /* There is no cluster_id on legacy system. */ - if (cluster == -1) + if (cluster < 0) cluster = 0; id = aggr_cpu_id__die(cpu, data); diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index f0599c61fab4..5e7ff09fbc95 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -426,8 +426,9 @@ static int add_tracepoint_values(struct ctf_writer *cw, struct evsel *evsel, struct perf_sample *sample) { - struct tep_format_field *common_fields = evsel->tp_format->format.common_fields; - struct tep_format_field *fields = evsel->tp_format->format.fields; + const struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_format_field *common_fields = tp_format->format.common_fields; + struct tep_format_field *fields = tp_format->format.fields; int ret; ret = add_tracepoint_fields_values(cw, event_class, event, @@ -1064,8 +1065,9 @@ static int add_tracepoint_types(struct ctf_writer *cw, struct evsel *evsel, struct bt_ctf_event_class *class) { - struct tep_format_field *common_fields = evsel->tp_format->format.common_fields; - struct tep_format_field *fields = evsel->tp_format->format.fields; + const struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_format_field *common_fields = tp_format ? tp_format->format.common_fields : NULL; + struct tep_format_field *fields = tp_format ? tp_format->format.fields : NULL; int ret; ret = add_tracepoint_fields_types(cw, common_fields, class); diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c index 8304cd2d4a9c..d9f805bf6fb0 100644 --- a/tools/perf/util/data-convert-json.c +++ b/tools/perf/util/data-convert-json.c @@ -230,12 +230,12 @@ static int process_sample_event(const struct perf_tool *tool, #ifdef HAVE_LIBTRACEEVENT if (sample->raw_data) { - int i; - struct tep_format_field **fields; + struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_format_field **fields = tp_format ? tep_event_fields(tp_format) : NULL; - fields = tep_event_fields(evsel->tp_format); if (fields) { - i = 0; + int i = 0; + while (fields[i]) { struct trace_seq s; diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 995f6bb05b5f..f9ef7d045c92 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -46,8 +46,8 @@ int debug_type_profile; FILE *debug_file(void) { if (!_debug_file) { - pr_warning_once("debug_file not set"); debug_set_file(stderr); + pr_warning_once("debug_file not set"); } return _debug_file; } diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c index 28ceb76e465b..50c5c206b70e 100644 --- a/tools/perf/util/disasm.c +++ b/tools/perf/util/disasm.c @@ -1245,6 +1245,9 @@ int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, s scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.", dso__long_name(dso)); break; + case SYMBOL_ANNOTATE_ERRNO__COULDNT_DETERMINE_FILE_TYPE: + scnprintf(buf, buflen, "Couldn't determine the file %s type.", dso__long_name(dso)); + break; default: scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum); break; @@ -2238,7 +2241,7 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) } else if (dso__binary_type(dso) == DSO_BINARY_TYPE__BPF_IMAGE) { return symbol__disassemble_bpf_image(sym, args); } else if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) { - return -1; + return SYMBOL_ANNOTATE_ERRNO__COULDNT_DETERMINE_FILE_TYPE; } else if (dso__is_kcore(dso)) { kce.addr = map__rip_2objdump(map, sym->start); kce.kcore_filename = symfs_filename; diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c index 7d180bdaedbc..ddacef881af2 100644 --- a/tools/perf/util/dlfilter.c +++ b/tools/perf/util/dlfilter.c @@ -234,7 +234,8 @@ static const __u8 *dlfilter__insn(void *ctx, __u32 *len) struct machine *machine = maps__machine(thread__maps(al->thread)); if (machine) - script_fetch_insn(d->sample, al->thread, machine); + script_fetch_insn(d->sample, al->thread, machine, + /*native_arch=*/true); } } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index bb8e8f444054..c0472a41147c 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -808,7 +808,9 @@ static inline bool dso__is_kcore(const struct dso *dso) static inline bool dso__is_kallsyms(const struct dso *dso) { - return RC_CHK_ACCESS(dso)->kernel && RC_CHK_ACCESS(dso)->long_name[0] != '/'; + enum dso_binary_type bt = dso__binary_type(dso); + + return bt == DSO_BINARY_TYPE__KALLSYMS || bt == DSO_BINARY_TYPE__GUEST_KALLSYMS; } bool dso__is_object_file(const struct dso *dso); diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index a6321e7f0633..cae4f6d63318 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -331,10 +331,13 @@ int perf_env__read_cpu_topology_map(struct perf_env *env) for (idx = 0; idx < nr_cpus; ++idx) { struct perf_cpu cpu = { .cpu = idx }; + int core_id = cpu__get_core_id(cpu); + int socket_id = cpu__get_socket_id(cpu); + int die_id = cpu__get_die_id(cpu); - env->cpu[idx].core_id = cpu__get_core_id(cpu); - env->cpu[idx].socket_id = cpu__get_socket_id(cpu); - env->cpu[idx].die_id = cpu__get_die_id(cpu); + env->cpu[idx].core_id = core_id >= 0 ? core_id : -1; + env->cpu[idx].socket_id = socket_id >= 0 ? socket_id : -1; + env->cpu[idx].die_id = die_id >= 0 ? die_id : -1; } env->nr_cpus_avail = nr_cpus; @@ -477,15 +480,19 @@ const char *perf_env__arch(struct perf_env *env) return normalize_arch(arch_name); } +#if defined(HAVE_LIBTRACEEVENT) +#include "trace/beauty/arch_errno_names.c" +#endif + const char *perf_env__arch_strerrno(struct perf_env *env __maybe_unused, int err __maybe_unused) { -#if defined(HAVE_SYSCALL_TABLE_SUPPORT) && defined(HAVE_LIBTRACEEVENT) +#if defined(HAVE_LIBTRACEEVENT) if (env->arch_strerrno == NULL) env->arch_strerrno = arch_syscalls__strerrno_function(perf_env__arch(env)); return env->arch_strerrno ? env->arch_strerrno(err) : "no arch specific strerrno function"; #else - return "!(HAVE_SYSCALL_TABLE_SUPPORT && HAVE_LIBTRACEEVENT)"; + return "!HAVE_LIBTRACEEVENT"; #endif } diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index da11add761d0..d90e343cf1fa 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -56,8 +56,6 @@ struct pmu_caps { typedef const char *(arch_syscalls__strerrno_t)(int err); -arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch); - struct perf_env { char *hostname; char *os_release; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index f0dd174e2deb..633df7d9204c 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1373,19 +1373,18 @@ static int evlist__create_syswide_maps(struct evlist *evlist) */ cpus = perf_cpu_map__new_online_cpus(); if (!cpus) - goto out; + return -ENOMEM; threads = perf_thread_map__new_dummy(); - if (!threads) - goto out_put; + if (!threads) { + perf_cpu_map__put(cpus); + return -ENOMEM; + } perf_evlist__set_maps(&evlist->core, cpus, threads); - perf_thread_map__put(threads); -out_put: perf_cpu_map__put(cpus); -out: - return -ENOMEM; + return 0; } int evlist__open(struct evlist *evlist) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index d22c5df1701e..c99eb9ff17ed 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -395,6 +395,7 @@ void evsel__init(struct evsel *evsel, evsel->group_pmu_name = NULL; evsel->skippable = false; evsel->alternate_hw_config = PERF_COUNT_HW_MAX; + evsel->script_output_type = -1; // FIXME: OUTPUT_TYPE_UNSET, see builtin-script.c } struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -454,7 +455,7 @@ static int evsel__copy_config_terms(struct evsel *dst, struct evsel *src) * The assumption is that @orig is not configured nor opened yet. * So we only care about the attributes that can be set while it's parsed. */ -struct evsel *evsel__clone(struct evsel *orig) +struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig) { struct evsel *evsel; @@ -467,7 +468,11 @@ struct evsel *evsel__clone(struct evsel *orig) if (orig->bpf_obj) return NULL; - evsel = evsel__new(&orig->core.attr); + if (dest) + evsel = dest; + else + evsel = evsel__new(&orig->core.attr); + if (evsel == NULL) return NULL; @@ -506,17 +511,28 @@ struct evsel *evsel__clone(struct evsel *orig) } evsel->cgrp = cgroup__get(orig->cgrp); #ifdef HAVE_LIBTRACEEVENT + if (orig->tp_sys) { + evsel->tp_sys = strdup(orig->tp_sys); + if (evsel->tp_sys == NULL) + goto out_err; + } + if (orig->tp_name) { + evsel->tp_name = strdup(orig->tp_name); + if (evsel->tp_name == NULL) + goto out_err; + } evsel->tp_format = orig->tp_format; #endif evsel->handler = orig->handler; evsel->core.leader = orig->core.leader; evsel->max_events = orig->max_events; - free((char *)evsel->unit); - evsel->unit = strdup(orig->unit); - if (evsel->unit == NULL) - goto out_err; - + zfree(&evsel->unit); + if (orig->unit) { + evsel->unit = strdup(orig->unit); + if (evsel->unit == NULL) + goto out_err; + } evsel->scale = orig->scale; evsel->snapshot = orig->snapshot; evsel->per_pkg = orig->per_pkg; @@ -544,53 +560,105 @@ out_err: return NULL; } +static int trace_event__id(const char *sys, const char *name) +{ + char *tp_dir = get_events_file(sys); + char path[PATH_MAX]; + int id, err; + + if (!tp_dir) + return -1; + + scnprintf(path, PATH_MAX, "%s/%s/id", tp_dir, name); + put_events_file(tp_dir); + err = filename__read_int(path, &id); + if (err) + return err; + + return id; +} + /* * Returns pointer with encoded error via <linux/err.h> interface. */ -#ifdef HAVE_LIBTRACEEVENT struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx, bool format) { + struct perf_event_attr attr = { + .type = PERF_TYPE_TRACEPOINT, + .sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | + PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD), + }; struct evsel *evsel = zalloc(perf_evsel__object.size); - int err = -ENOMEM; + int err = -ENOMEM, id = -1; - if (evsel == NULL) { + if (evsel == NULL) goto out_err; - } else { - struct perf_event_attr attr = { - .type = PERF_TYPE_TRACEPOINT, - .sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | - PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD), - }; - if (asprintf(&evsel->name, "%s:%s", sys, name) < 0) - goto out_free; - event_attr_init(&attr); + if (asprintf(&evsel->name, "%s:%s", sys, name) < 0) + goto out_free; - if (format) { - evsel->tp_format = trace_event__tp_format(sys, name); - if (IS_ERR(evsel->tp_format)) { - err = PTR_ERR(evsel->tp_format); - goto out_free; - } - attr.config = evsel->tp_format->id; - } else { - attr.config = (__u64) -1; - } +#ifdef HAVE_LIBTRACEEVENT + evsel->tp_sys = strdup(sys); + if (!evsel->tp_sys) + goto out_free; + evsel->tp_name = strdup(name); + if (!evsel->tp_name) + goto out_free; +#endif - attr.sample_period = 1; - evsel__init(evsel, &attr, idx); - } + event_attr_init(&attr); + if (format) { + id = trace_event__id(sys, name); + if (id < 0) { + err = id; + goto out_free; + } + } + attr.config = (__u64)id; + attr.sample_period = 1; + evsel__init(evsel, &attr, idx); return evsel; out_free: zfree(&evsel->name); +#ifdef HAVE_LIBTRACEEVENT + zfree(&evsel->tp_sys); + zfree(&evsel->tp_name); +#endif free(evsel); out_err: return ERR_PTR(err); } + +#ifdef HAVE_LIBTRACEEVENT +struct tep_event *evsel__tp_format(struct evsel *evsel) +{ + struct tep_event *tp_format = evsel->tp_format; + + if (tp_format) + return tp_format; + + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) + return NULL; + + if (!evsel->tp_sys) + tp_format = trace_event__tp_format_id(evsel->core.attr.config); + else + tp_format = trace_event__tp_format(evsel->tp_sys, evsel->tp_name); + + if (IS_ERR(tp_format)) { + int err = -PTR_ERR(evsel->tp_format); + + pr_err("Error getting tracepoint format '%s' '%s'(%d)\n", + evsel__name(evsel), strerror(err), err); + return NULL; + } + evsel->tp_format = tp_format; + return evsel->tp_format; +} #endif const char *const evsel__hw_names[PERF_COUNT_HW_MAX] = { @@ -1103,6 +1171,9 @@ static void evsel__apply_config_terms(struct evsel *evsel, case EVSEL__CONFIG_TERM_AUX_OUTPUT: attr->aux_output = term->val.aux_output ? 1 : 0; break; + case EVSEL__CONFIG_TERM_AUX_ACTION: + /* Already applied by auxtrace */ + break; case EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE: /* Already applied by auxtrace */ break; @@ -1587,6 +1658,10 @@ void evsel__exit(struct evsel *evsel) perf_thread_map__put(evsel->core.threads); zfree(&evsel->group_name); zfree(&evsel->name); +#ifdef HAVE_LIBTRACEEVENT + zfree(&evsel->tp_sys); + zfree(&evsel->tp_name); +#endif zfree(&evsel->filter); zfree(&evsel->group_pmu_name); zfree(&evsel->unit); @@ -2090,16 +2165,17 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, return err; } -static bool has_attr_feature(struct perf_event_attr *attr, unsigned long flags) +static bool __has_attr_feature(struct perf_event_attr *attr, + struct perf_cpu cpu, unsigned long flags) { - int fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, /*cpu=*/-1, + int fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, cpu.cpu, /*group_fd=*/-1, flags); close(fd); if (fd < 0) { attr->exclude_kernel = 1; - fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, /*cpu=*/-1, + fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, cpu.cpu, /*group_fd=*/-1, flags); close(fd); } @@ -2107,7 +2183,7 @@ static bool has_attr_feature(struct perf_event_attr *attr, unsigned long flags) if (fd < 0) { attr->exclude_hv = 1; - fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, /*cpu=*/-1, + fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, cpu.cpu, /*group_fd=*/-1, flags); close(fd); } @@ -2115,7 +2191,7 @@ static bool has_attr_feature(struct perf_event_attr *attr, unsigned long flags) if (fd < 0) { attr->exclude_guest = 1; - fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, /*cpu=*/-1, + fd = syscall(SYS_perf_event_open, attr, /*pid=*/0, cpu.cpu, /*group_fd=*/-1, flags); close(fd); } @@ -2127,6 +2203,13 @@ static bool has_attr_feature(struct perf_event_attr *attr, unsigned long flags) return fd >= 0; } +static bool has_attr_feature(struct perf_event_attr *attr, unsigned long flags) +{ + struct perf_cpu cpu = {.cpu = -1}; + + return __has_attr_feature(attr, cpu, flags); +} + static void evsel__detect_missing_pmu_features(struct evsel *evsel) { struct perf_event_attr attr = { @@ -2215,7 +2298,65 @@ found: errno = old_errno; } -static bool evsel__detect_missing_features(struct evsel *evsel) +static bool evsel__probe_aux_action(struct evsel *evsel, struct perf_cpu cpu) +{ + struct perf_event_attr attr = evsel->core.attr; + int old_errno = errno; + + attr.disabled = 1; + attr.aux_start_paused = 1; + + if (__has_attr_feature(&attr, cpu, /*flags=*/0)) { + errno = old_errno; + return true; + } + + /* + * EOPNOTSUPP means the kernel supports the feature but the PMU does + * not, so keep that distinction if possible. + */ + if (errno != EOPNOTSUPP) + errno = old_errno; + + return false; +} + +static void evsel__detect_missing_aux_action_feature(struct evsel *evsel, struct perf_cpu cpu) +{ + static bool detection_done; + struct evsel *leader; + + /* + * Don't bother probing aux_action if it is not being used or has been + * probed before. + */ + if (!evsel->core.attr.aux_action || detection_done) + return; + + detection_done = true; + + /* + * The leader is an AUX area event. If it has failed, assume the feature + * is not supported. + */ + leader = evsel__leader(evsel); + if (evsel == leader) { + perf_missing_features.aux_action = true; + return; + } + + /* + * AUX area event with aux_action must have been opened successfully + * already, so feature is supported. + */ + if (leader->core.attr.aux_action) + return; + + if (!evsel__probe_aux_action(leader, cpu)) + perf_missing_features.aux_action = true; +} + +static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu cpu) { static bool detection_done = false; struct perf_event_attr attr = { @@ -2225,6 +2366,8 @@ static bool evsel__detect_missing_features(struct evsel *evsel) }; int old_errno; + evsel__detect_missing_aux_action_feature(evsel, cpu); + evsel__detect_missing_pmu_features(evsel); if (evsel__has_br_stack(evsel)) @@ -2413,25 +2556,6 @@ check: return false; } -static bool evsel__handle_error_quirks(struct evsel *evsel, int error) -{ - /* - * AMD core PMU tries to forward events with precise_ip to IBS PMU - * implicitly. But IBS PMU has more restrictions so it can fail with - * supported event attributes. Let's forward it back to the core PMU - * by clearing precise_ip only if it's from precise_max (:P). - */ - if ((error == -EINVAL || error == -ENOENT) && x86__is_amd_cpu() && - evsel->core.attr.precise_ip && evsel->precise_max) { - evsel->core.attr.precise_ip = 0; - pr_debug2_peo("removing precise_ip on AMD\n"); - display_attr(&evsel->core.attr); - return true; - } - - return false; -} - static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads, int start_cpu_map_idx, int end_cpu_map_idx) @@ -2439,6 +2563,7 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int idx, thread, nthreads; int pid = -1, err, old_errno; enum rlimit_action set_rlimit = NO_CHANGE; + struct perf_cpu cpu; if (evsel__is_retire_lat(evsel)) return tpebs_start(evsel->evlist); @@ -2476,6 +2601,7 @@ fallback_missing_features: } for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) { + cpu = perf_cpu_map__cpu(cpus, idx); for (thread = 0; thread < nthreads; thread++) { int fd, group_fd; @@ -2496,10 +2622,9 @@ retry_open: /* Debug message used by test scripts */ pr_debug2_peo("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", - pid, perf_cpu_map__cpu(cpus, idx).cpu, group_fd, evsel->open_flags); + pid, cpu.cpu, group_fd, evsel->open_flags); - fd = sys_perf_event_open(&evsel->core.attr, pid, - perf_cpu_map__cpu(cpus, idx).cpu, + fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, group_fd, evsel->open_flags); FD(evsel, idx, thread) = fd; @@ -2515,8 +2640,7 @@ retry_open: bpf_counter__install_pe(evsel, idx, fd); if (unlikely(test_attr__enabled())) { - test_attr__open(&evsel->core.attr, pid, - perf_cpu_map__cpu(cpus, idx), + test_attr__open(&evsel->core.attr, pid, cpu, fd, group_fd, evsel->open_flags); } @@ -2571,15 +2695,12 @@ try_fallback: if (err == -EMFILE && rlimit__increase_nofile(&set_rlimit)) goto retry_open; - if (err == -EINVAL && evsel__detect_missing_features(evsel)) + if (err == -EINVAL && evsel__detect_missing_features(evsel, cpu)) goto fallback_missing_features; if (evsel__precise_ip_fallback(evsel)) goto retry_open; - if (evsel__handle_error_quirks(evsel, err)) - goto retry_open; - out_close: if (err) threads->err_thread = thread; @@ -3218,12 +3339,16 @@ u16 evsel__id_hdr_size(const struct evsel *evsel) #ifdef HAVE_LIBTRACEEVENT struct tep_format_field *evsel__field(struct evsel *evsel, const char *name) { - return tep_find_field(evsel->tp_format, name); + struct tep_event *tp_format = evsel__tp_format(evsel); + + return tp_format ? tep_find_field(tp_format, name) : NULL; } struct tep_format_field *evsel__common_field(struct evsel *evsel, const char *name) { - return tep_find_common_field(evsel->tp_format, name); + struct tep_event *tp_format = evsel__tp_format(evsel); + + return tp_format ? tep_find_common_field(tp_format, name) : NULL; } void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name) @@ -3448,6 +3573,78 @@ static bool find_process(const char *name) return ret ? false : true; } +static int dump_perf_event_processes(char *msg, size_t size) +{ + DIR *proc_dir; + struct dirent *proc_entry; + int printed = 0; + + proc_dir = opendir(procfs__mountpoint()); + if (!proc_dir) + return 0; + + /* Walk through the /proc directory. */ + while ((proc_entry = readdir(proc_dir)) != NULL) { + char buf[256]; + DIR *fd_dir; + struct dirent *fd_entry; + int fd_dir_fd; + + if (proc_entry->d_type != DT_DIR || + !isdigit(proc_entry->d_name[0]) || + strlen(proc_entry->d_name) > sizeof(buf) - 4) + continue; + + scnprintf(buf, sizeof(buf), "%s/fd", proc_entry->d_name); + fd_dir_fd = openat(dirfd(proc_dir), buf, O_DIRECTORY); + if (fd_dir_fd == -1) + continue; + fd_dir = fdopendir(fd_dir_fd); + if (!fd_dir) { + close(fd_dir_fd); + continue; + } + while ((fd_entry = readdir(fd_dir)) != NULL) { + ssize_t link_size; + + if (fd_entry->d_type != DT_LNK) + continue; + link_size = readlinkat(fd_dir_fd, fd_entry->d_name, buf, sizeof(buf)); + if (link_size < 0) + continue; + /* Take care as readlink doesn't null terminate the string. */ + if (!strncmp(buf, "anon_inode:[perf_event]", link_size)) { + int cmdline_fd; + ssize_t cmdline_size; + + scnprintf(buf, sizeof(buf), "%s/cmdline", proc_entry->d_name); + cmdline_fd = openat(dirfd(proc_dir), buf, O_RDONLY); + if (cmdline_fd == -1) + continue; + cmdline_size = read(cmdline_fd, buf, sizeof(buf) - 1); + close(cmdline_fd); + if (cmdline_size < 0) + continue; + buf[cmdline_size] = '\0'; + for (ssize_t i = 0; i < cmdline_size; i++) { + if (buf[i] == '\0') + buf[i] = ' '; + } + + if (printed == 0) + printed += scnprintf(msg, size, "Possible processes:\n"); + + printed += scnprintf(msg + printed, size - printed, + "%s %s\n", proc_entry->d_name, buf); + break; + } + } + closedir(fd_dir); + } + closedir(proc_dir); + return printed; +} + int __weak arch_evsel__open_strerror(struct evsel *evsel __maybe_unused, char *msg __maybe_unused, size_t size __maybe_unused) @@ -3481,7 +3678,7 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, printed += scnprintf(msg, size, "No permission to enable %s event.\n\n", evsel__name(evsel)); - return scnprintf(msg + printed, size - printed, + return printed + scnprintf(msg + printed, size - printed, "Consider adjusting /proc/sys/kernel/perf_event_paranoid setting to open\n" "access to performance monitoring and observability operations for processes\n" "without CAP_PERFMON, CAP_SYS_PTRACE or CAP_SYS_ADMIN Linux capability.\n" @@ -3526,6 +3723,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "%s: PMU Hardware doesn't support 'aux_output' feature", evsel__name(evsel)); + if (evsel->core.attr.aux_action) + return scnprintf(msg, size, + "%s: PMU Hardware doesn't support 'aux_action' feature", + evsel__name(evsel)); if (evsel->core.attr.sample_period != 0) return scnprintf(msg, size, "%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'", @@ -3544,6 +3745,11 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "The PMU counters are busy/taken by another profiler.\n" "We found oprofile daemon running, please stop it and try again."); + printed += scnprintf( + msg, size, + "The PMU %s counters are busy and in use by another process.\n", + evsel->pmu ? evsel->pmu->name : ""); + return printed + dump_perf_event_processes(msg + printed, size - printed); break; case EINVAL: if (evsel->core.attr.sample_type & PERF_SAMPLE_CODE_PAGE_SIZE && perf_missing_features.code_page_size) @@ -3556,6 +3762,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "clockid feature not supported."); if (perf_missing_features.clockid_wrong) return scnprintf(msg, size, "wrong clockid (%d).", clockid); + if (perf_missing_features.aux_action) + return scnprintf(msg, size, "The 'aux_action' feature is not supported, update the kernel."); if (perf_missing_features.aux_output) return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel."); if (!target__has_cpu(target)) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 04934a7af174..5e789fa80590 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -59,6 +59,8 @@ struct evsel { char *group_name; const char *group_pmu_name; #ifdef HAVE_LIBTRACEEVENT + char *tp_sys; + char *tp_name; struct tep_event *tp_format; #endif char *filter; @@ -119,6 +121,7 @@ struct evsel { bool default_metricgroup; /* A member of the Default metricgroup */ struct hashmap *per_pkg_mask; int err; + int script_output_type; struct { evsel__sb_cb_t *cb; void *data; @@ -205,6 +208,7 @@ struct perf_missing_features { bool weight_struct; bool read_lost; bool branch_counters; + bool aux_action; bool inherit_sample_read; }; @@ -241,26 +245,23 @@ static inline struct evsel *evsel__new(struct perf_event_attr *attr) return evsel__new_idx(attr, 0); } -struct evsel *evsel__clone(struct evsel *orig); +struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig); int copy_config_terms(struct list_head *dst, struct list_head *src); void free_config_terms(struct list_head *config_terms); -#ifdef HAVE_LIBTRACEEVENT -struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx, bool format); - /* * Returns pointer with encoded error via <linux/err.h> interface. */ +struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx, bool format); static inline struct evsel *evsel__newtp(const char *sys, const char *name) { return evsel__newtp_idx(sys, name, 0, true); } -#endif #ifdef HAVE_LIBTRACEEVENT -struct tep_event *event_format__new(const char *sys, const char *name); +struct tep_event *evsel__tp_format(struct evsel *evsel); #endif void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx); diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h index aee6f808b512..af52a1516d0b 100644 --- a/tools/perf/util/evsel_config.h +++ b/tools/perf/util/evsel_config.h @@ -25,6 +25,7 @@ enum evsel_term_type { EVSEL__CONFIG_TERM_BRANCH, EVSEL__CONFIG_TERM_PERCORE, EVSEL__CONFIG_TERM_AUX_OUTPUT, + EVSEL__CONFIG_TERM_AUX_ACTION, EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE, EVSEL__CONFIG_TERM_CFG_CHG, }; diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 86b7f46f9e2a..103984b29b1e 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -81,13 +81,15 @@ int evsel__fprintf(struct evsel *evsel, struct perf_attr_details *details, FILE #ifdef HAVE_LIBTRACEEVENT if (details->trace_fields) { struct tep_format_field *field; + const struct tep_event *tp_format; if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) { printed += comma_fprintf(fp, &first, " (not a tracepoint)"); goto out; } - field = evsel->tp_format->format.fields; + tp_format = evsel__tp_format(evsel); + field = tp_format ? tp_format->format.fields : NULL; if (field == NULL) { printed += comma_fprintf(fp, &first, " (no trace field)"); goto out; diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index c221dcce6666..6413537442aa 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -215,6 +215,8 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref) int expr__get_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **data) { + if (!ctx || !id) + return -1; return hashmap__find(ctx->ids, id, data) ? 0 : -1; } diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h index bae649ef50e8..5dee2caba0fe 100644 --- a/tools/perf/util/ftrace.h +++ b/tools/perf/util/ftrace.h @@ -7,6 +7,7 @@ struct evlist; struct hashamp; +struct stats; struct perf_ftrace { struct evlist *evlist; @@ -20,6 +21,9 @@ struct perf_ftrace { unsigned long percpu_buffer_size; bool inherit; bool use_nsec; + unsigned int bucket_range; + unsigned int min_latency; + unsigned int max_latency; int graph_depth; int func_stack_trace; int func_irq_info; @@ -43,7 +47,7 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace); int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace); int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace); int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace, - int buckets[]); + int buckets[], struct stats *stats); int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace); #else /* !HAVE_BPF_SKEL */ @@ -68,7 +72,8 @@ perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused) static inline int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, - int buckets[] __maybe_unused) + int buckets[] __maybe_unused, + struct stats *stats __maybe_unused) { return -1; } diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh index 1b5140e5ce99..6a73c903d690 100755 --- a/tools/perf/util/generate-cmdlist.sh +++ b/tools/perf/util/generate-cmdlist.sh @@ -38,7 +38,7 @@ do done echo "#endif /* HAVE_LIBELF_SUPPORT */" -echo "#if defined(HAVE_LIBTRACEEVENT) && (defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT))" +echo "#if defined(HAVE_LIBTRACEEVENT)" sed -n -e 's/^perf-\([^ ]*\)[ ].* audit*/\1/p' command-list.txt | sort | while read cmd @@ -51,7 +51,7 @@ do p }' "Documentation/perf-$cmd.txt" done -echo "#endif /* HAVE_LIBTRACEEVENT && (HAVE_LIBAUDIT_SUPPORT || HAVE_SYSCALL_TABLE_SUPPORT) */" +echo "#endif /* HAVE_LIBTRACEEVENT */" echo "#ifdef HAVE_LIBTRACEEVENT" sed -n -e 's/^perf-\([^ ]*\)[ ].* traceevent.*/\1/p' command-list.txt | diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index fff134565801..0f30f843c566 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -32,6 +32,9 @@ #include <linux/time64.h> #include <linux/zalloc.h> +static int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); +static int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); + static bool hists__filter_entry_by_dso(struct hists *hists, struct hist_entry *he); static bool hists__filter_entry_by_thread(struct hists *hists, @@ -1292,19 +1295,35 @@ out: return err; } -int64_t -hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) +static int64_t +hist_entry__cmp_impl(struct perf_hpp_list *hpp_list, struct hist_entry *left, + struct hist_entry *right, unsigned long fn_offset, + bool ignore_dynamic, bool ignore_skipped) { struct hists *hists = left->hists; struct perf_hpp_fmt *fmt; - int64_t cmp = 0; + perf_hpp_fmt_cmp_t *fn; + int64_t cmp; + + /* + * Never collapse filtered and non-filtered entries. + * Note this is not the same as having an extra (invisible) fmt + * that corresponds to the filtered status. + */ + cmp = (int64_t)!!left->filtered - (int64_t)!!right->filtered; + if (cmp) + return cmp; - hists__for_each_sort_list(hists, fmt) { - if (perf_hpp__is_dynamic_entry(fmt) && + perf_hpp_list__for_each_sort_list(hpp_list, fmt) { + if (ignore_dynamic && perf_hpp__is_dynamic_entry(fmt) && !perf_hpp__defined_dynamic_entry(fmt, hists)) continue; - cmp = fmt->cmp(fmt, left, right); + if (ignore_skipped && perf_hpp__should_skip(fmt, hists)) + continue; + + fn = (void *)fmt + fn_offset; + cmp = (*fn)(fmt, left, right); if (cmp) break; } @@ -1313,23 +1332,33 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) } int64_t -hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) +hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) { - struct hists *hists = left->hists; - struct perf_hpp_fmt *fmt; - int64_t cmp = 0; + return hist_entry__cmp_impl(left->hists->hpp_list, left, right, + offsetof(struct perf_hpp_fmt, cmp), true, false); +} - hists__for_each_sort_list(hists, fmt) { - if (perf_hpp__is_dynamic_entry(fmt) && - !perf_hpp__defined_dynamic_entry(fmt, hists)) - continue; +static int64_t +hist_entry__sort(struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_impl(left->hists->hpp_list, left, right, + offsetof(struct perf_hpp_fmt, sort), false, true); +} - cmp = fmt->collapse(fmt, left, right); - if (cmp) - break; - } +int64_t +hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_impl(left->hists->hpp_list, left, right, + offsetof(struct perf_hpp_fmt, collapse), true, false); +} - return cmp; +static int64_t +hist_entry__collapse_hierarchy(struct perf_hpp_list *hpp_list, + struct hist_entry *left, + struct hist_entry *right) +{ + return hist_entry__cmp_impl(hpp_list, left, right, + offsetof(struct perf_hpp_fmt, collapse), false, false); } void hist_entry__delete(struct hist_entry *he) @@ -1503,14 +1532,7 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists, while (*p != NULL) { parent = *p; iter = rb_entry(parent, struct hist_entry, rb_node_in); - - cmp = 0; - perf_hpp_list__for_each_sort_list(hpp_list, fmt) { - cmp = fmt->collapse(fmt, iter, he); - if (cmp) - break; - } - + cmp = hist_entry__collapse_hierarchy(hpp_list, iter, he); if (!cmp) { he_stat__add_stat(&iter->stat, &he->stat); return iter; @@ -1730,24 +1752,6 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog) return 0; } -static int64_t hist_entry__sort(struct hist_entry *a, struct hist_entry *b) -{ - struct hists *hists = a->hists; - struct perf_hpp_fmt *fmt; - int64_t cmp = 0; - - hists__for_each_sort_list(hists, fmt) { - if (perf_hpp__should_skip(fmt, a->hists)) - continue; - - cmp = fmt->sort(fmt, a, b); - if (cmp) - break; - } - - return cmp; -} - static void hists__reset_filter_stats(struct hists *hists) { hists->nr_non_filtered_entries = 0; @@ -2449,21 +2453,15 @@ static struct hist_entry *add_dummy_hierarchy_entry(struct hists *hists, struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; - struct perf_hpp_fmt *fmt; bool leftmost = true; p = &root->rb_root.rb_node; while (*p != NULL) { - int64_t cmp = 0; + int64_t cmp; parent = *p; he = rb_entry(parent, struct hist_entry, rb_node_in); - - perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) { - cmp = fmt->collapse(fmt, he, pair); - if (cmp) - break; - } + cmp = hist_entry__collapse_hierarchy(he->hpp_list, he, pair); if (!cmp) goto out; @@ -2521,16 +2519,10 @@ static struct hist_entry *hists__find_hierarchy_entry(struct rb_root_cached *roo while (n) { struct hist_entry *iter; - struct perf_hpp_fmt *fmt; - int64_t cmp = 0; + int64_t cmp; iter = rb_entry(n, struct hist_entry, rb_node_in); - perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) { - cmp = fmt->collapse(fmt, iter, he); - if (cmp) - break; - } - + cmp = hist_entry__collapse_hierarchy(he->hpp_list, iter, he); if (cmp < 0) n = n->rb_left; else if (cmp > 0) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 1131056924d9..46c8373e3146 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -342,8 +342,6 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, struct perf_hpp; struct perf_hpp_fmt; -int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); -int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); int hist_entry__transaction_len(void); int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size, struct hists *hists); @@ -452,6 +450,9 @@ struct perf_hpp { bool skip; }; +typedef int64_t (*perf_hpp_fmt_cmp_t)( + struct perf_hpp_fmt *, struct hist_entry *, struct hist_entry *); + struct perf_hpp_fmt { const char *name; int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, @@ -463,12 +464,9 @@ struct perf_hpp_fmt { struct hist_entry *he); int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he); - int64_t (*cmp)(struct perf_hpp_fmt *fmt, - struct hist_entry *a, struct hist_entry *b); - int64_t (*collapse)(struct perf_hpp_fmt *fmt, - struct hist_entry *a, struct hist_entry *b); - int64_t (*sort)(struct perf_hpp_fmt *fmt, - struct hist_entry *a, struct hist_entry *b); + perf_hpp_fmt_cmp_t cmp; + perf_hpp_fmt_cmp_t collapse; + perf_hpp_fmt_cmp_t sort; bool (*equal)(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); void (*free)(struct perf_hpp_fmt *fmt); diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c index 4acb9bb19b84..acd889b2462f 100644 --- a/tools/perf/util/hwmon_pmu.c +++ b/tools/perf/util/hwmon_pmu.c @@ -108,20 +108,6 @@ struct hwmon_pmu { }; /** - * union hwmon_pmu_event_key: Key for hwmon_pmu->events as such each key - * represents an event. - * - * Related hwmon files start <type><number> that this key represents. - */ -union hwmon_pmu_event_key { - long type_and_num; - struct { - int num :16; - enum hwmon_type type :8; - }; -}; - -/** * struct hwmon_pmu_event_value: Value in hwmon_pmu->events. * * Hwmon files are of the form <type><number>_<item> and may have a suffix diff --git a/tools/perf/util/hwmon_pmu.h b/tools/perf/util/hwmon_pmu.h index 882566846df4..b3329774d2b2 100644 --- a/tools/perf/util/hwmon_pmu.h +++ b/tools/perf/util/hwmon_pmu.h @@ -91,6 +91,22 @@ enum hwmon_item { HWMON_ITEM__MAX, }; +/** + * union hwmon_pmu_event_key: Key for hwmon_pmu->events as such each key + * represents an event. + * union is exposed for testing to ensure problems are avoided on big + * endian machines. + * + * Related hwmon files start <type><number> that this key represents. + */ +union hwmon_pmu_event_key { + long type_and_num; + struct { + int num :16; + enum hwmon_type type :8; + }; +}; + bool perf_pmu__is_hwmon(const struct perf_pmu *pmu); bool evsel__is_hwmon(const struct evsel *evsel); diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index 30793d08c6d4..5b8f0149167d 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -7,16 +7,24 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table $(call rule_mkdir) @$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@ -# Busybox's diff doesn't have -I, avoid warning in the case +ifeq ($(SRCARCH),x86) + perf-util-y += inat.o insn.o +else + perf-util-$(CONFIG_AUXTRACE) += inat.o insn.o +endif -$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c +$(OUTPUT)util/intel-pt-decoder/inat.o: $(srctree)/tools/arch/x86/lib/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(call rule_mkdir) $(call if_changed_dep,cc_o_c) -CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder +CFLAGS_inat.o += -I$(OUTPUT)util/intel-pt-decoder + +$(OUTPUT)util/intel-pt-decoder/insn.o: $(srctree)/tools/arch/x86/lib/insn.c + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) ifeq ($(CC_NO_CLANG), 1) - CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init + CFLAGS_insn.o += -Wno-override-init endif -CFLAGS_intel-pt-insn-decoder.o += -Wno-packed +CFLAGS_insn.o += -Wno-packed 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 47cf35799a4d..8fabddc1c0da 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 @@ -11,9 +11,6 @@ #include <byteswap.h> #include "../../../arch/x86/include/asm/insn.h" -#include "../../../arch/x86/lib/inat.c" -#include "../../../arch/x86/lib/insn.c" - #include "event.h" #include "intel-pt-insn-decoder.h" diff --git a/tools/perf/util/intel-tpebs.c b/tools/perf/util/intel-tpebs.c index 50a3c3e07160..2c421b475b3b 100644 --- a/tools/perf/util/intel-tpebs.c +++ b/tools/perf/util/intel-tpebs.c @@ -254,7 +254,7 @@ int tpebs_start(struct evlist *evsel_list) new = zalloc(sizeof(*new)); if (!new) { ret = -1; - zfree(name); + zfree(&name); goto err; } new->name = name; diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 346513e5e9b7..f23e21502bf8 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -737,7 +737,7 @@ jit_inject(struct jit_buf_desc *jd, const char *path) * as captured in the RECORD_MMAP record */ static int -jit_detect(const char *mmap_name, pid_t pid, struct nsinfo *nsi) +jit_detect(const char *mmap_name, pid_t pid, struct nsinfo *nsi, bool *in_pidns) { char *p; char *end = NULL; @@ -773,11 +773,16 @@ jit_detect(const char *mmap_name, pid_t pid, struct nsinfo *nsi) if (!end) return -1; + *in_pidns = pid == nsinfo__nstgid(nsi); /* * pid does not match mmap pid * pid==0 in system-wide mode (synthesized) + * + * If the pid in the file name is equal to the nstgid, then + * the agent ran inside a container and perf outside the + * container, so record it for further use in jit_inject(). */ - if (pid && pid2 != nsinfo__nstgid(nsi)) + if (pid && !(pid2 == pid || *in_pidns)) return -1; /* * validate suffix @@ -830,6 +835,7 @@ jit_process(struct perf_session *session, struct nsinfo *nsi; struct evsel *first; struct jit_buf_desc jd; + bool in_pidns = false; int ret; thread = machine__findnew_thread(machine, pid, tid); @@ -844,7 +850,7 @@ jit_process(struct perf_session *session, /* * first, detect marker mmap (i.e., the jitdump mmap) */ - if (jit_detect(filename, pid, nsi)) { + if (jit_detect(filename, pid, nsi, &in_pidns)) { nsinfo__put(nsi); /* @@ -866,6 +872,9 @@ jit_process(struct perf_session *session, jd.machine = machine; jd.nsi = nsi; + if (in_pidns) + nsinfo__set_in_pidns(nsi); + /* * track sample_type to compute id_all layout * perf sets the same sample type to all events as of now diff --git a/tools/perf/util/kvm-stat.c b/tools/perf/util/kvm-stat.c new file mode 100644 index 000000000000..38ace736db5c --- /dev/null +++ b/tools/perf/util/kvm-stat.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "debug.h" +#include "evsel.h" +#include "kvm-stat.h" + +#if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) + +bool kvm_exit_event(struct evsel *evsel) +{ + return evsel__name_is(evsel, kvm_exit_trace); +} + +void exit_event_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->info = 0; + key->key = evsel__intval(evsel, sample, kvm_exit_reason); +} + + +bool exit_event_begin(struct evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + if (kvm_exit_event(evsel)) { + exit_event_get_key(evsel, sample, key); + return true; + } + + return false; +} + +bool kvm_entry_event(struct evsel *evsel) +{ + return evsel__name_is(evsel, kvm_entry_trace); +} + +bool exit_event_end(struct evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return kvm_entry_event(evsel); +} + +static const char *get_exit_reason(struct perf_kvm_stat *kvm, + struct exit_reasons_table *tbl, + u64 exit_code) +{ + while (tbl->reason != NULL) { + if (tbl->exit_code == exit_code) + return tbl->reason; + tbl++; + } + + pr_err("unknown kvm exit code:%lld on %s\n", + (unsigned long long)exit_code, kvm->exit_reasons_isa); + return "UNKNOWN"; +} + +void exit_event_decode_key(struct perf_kvm_stat *kvm, + struct event_key *key, + char *decode) +{ + const char *exit_reason = get_exit_reason(kvm, key->exit_reasons, + key->key); + + scnprintf(decode, KVM_EVENT_NAME_LEN, "%s", exit_reason); +} + +#endif diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 3e9ac754c3d1..4249542544bb 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -115,6 +115,8 @@ struct kvm_reg_events_ops { struct kvm_events_ops *ops; }; +#if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) + void exit_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key); @@ -127,6 +129,7 @@ bool exit_event_end(struct evsel *evsel, void exit_event_decode_key(struct perf_kvm_stat *kvm, struct event_key *key, char *decode); +#endif bool kvm_exit_event(struct evsel *evsel); bool kvm_entry_event(struct evsel *evsel); diff --git a/tools/perf/util/kwork.h b/tools/perf/util/kwork.h index 76fe2a821bcf..db00269b73f2 100644 --- a/tools/perf/util/kwork.h +++ b/tools/perf/util/kwork.h @@ -1,6 +1,7 @@ #ifndef PERF_UTIL_KWORK_H #define PERF_UTIL_KWORK_H +#include "perf.h" #include "util/tool.h" #include "util/time-utils.h" @@ -251,12 +252,14 @@ struct perf_kwork { * perf kwork top data */ struct kwork_top_stat top_stat; -}; -struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork, + /* Add work callback. */ + struct kwork_work *(*add_work)(struct perf_kwork *kwork, struct kwork_class *class, struct kwork_work *key); +}; + #ifdef HAVE_BPF_SKEL int perf_kwork__trace_prepare_bpf(struct perf_kwork *kwork); diff --git a/tools/perf/util/llvm-c-helpers.cpp b/tools/perf/util/llvm-c-helpers.cpp index 663bcaba2041..004081bd12c9 100644 --- a/tools/perf/util/llvm-c-helpers.cpp +++ b/tools/perf/util/llvm-c-helpers.cpp @@ -18,7 +18,6 @@ extern "C" { #include <linux/zalloc.h> } -#include "symbol_conf.h" #include "llvm-c-helpers.h" extern "C" diff --git a/tools/perf/util/lock-contention.c b/tools/perf/util/lock-contention.c new file mode 100644 index 000000000000..92e7b7b572a2 --- /dev/null +++ b/tools/perf/util/lock-contention.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "debug.h" +#include "env.h" +#include "lock-contention.h" +#include "machine.h" +#include "symbol.h" + +#include <limits.h> +#include <string.h> + +#include <linux/hash.h> +#include <linux/zalloc.h> + +#define __lockhashfn(key) hash_long((unsigned long)key, LOCKHASH_BITS) +#define lockhashentry(key) (lockhash_table + __lockhashfn((key))) + +struct callstack_filter { + struct list_head list; + char name[]; +}; + +static LIST_HEAD(callstack_filters); +struct hlist_head *lockhash_table; + +int parse_call_stack(const struct option *opt __maybe_unused, const char *str, + int unset __maybe_unused) +{ + char *s, *tmp, *tok; + int ret = 0; + + s = strdup(str); + if (s == NULL) + return -1; + + for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { + struct callstack_filter *entry; + + entry = malloc(sizeof(*entry) + strlen(tok) + 1); + if (entry == NULL) { + pr_err("Memory allocation failure\n"); + free(s); + return -1; + } + + strcpy(entry->name, tok); + list_add_tail(&entry->list, &callstack_filters); + } + + free(s); + return ret; +} + +bool needs_callstack(void) +{ + return !list_empty(&callstack_filters); +} + +struct lock_stat *lock_stat_find(u64 addr) +{ + struct hlist_head *entry = lockhashentry(addr); + struct lock_stat *ret; + + hlist_for_each_entry(ret, entry, hash_entry) { + if (ret->addr == addr) + return ret; + } + return NULL; +} + +struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags) +{ + struct hlist_head *entry = lockhashentry(addr); + struct lock_stat *ret, *new; + + hlist_for_each_entry(ret, entry, hash_entry) { + if (ret->addr == addr) + return ret; + } + + new = zalloc(sizeof(struct lock_stat)); + if (!new) + goto alloc_failed; + + new->addr = addr; + new->name = strdup(name); + if (!new->name) { + free(new); + goto alloc_failed; + } + + new->flags = flags; + new->wait_time_min = ULLONG_MAX; + + hlist_add_head(&new->hash_entry, entry); + return new; + +alloc_failed: + pr_err("memory allocation failed\n"); + return NULL; +} + +bool match_callstack_filter(struct machine *machine, u64 *callstack, int max_stack_depth) +{ + struct map *kmap; + struct symbol *sym; + u64 ip; + const char *arch = perf_env__arch(machine->env); + + if (list_empty(&callstack_filters)) + return true; + + for (int i = 0; i < max_stack_depth; i++) { + struct callstack_filter *filter; + + /* + * In powerpc, the callchain saved by kernel always includes + * first three entries as the NIP (next instruction pointer), + * LR (link register), and the contents of LR save area in the + * second stack frame. In certain scenarios its possible to have + * invalid kernel instruction addresses in either LR or the second + * stack frame's LR. In that case, kernel will store that address as + * zero. + * + * The below check will continue to look into callstack, + * incase first or second callstack index entry has 0 + * address for powerpc. + */ + if (!callstack || (!callstack[i] && (strcmp(arch, "powerpc") || + (i != 1 && i != 2)))) + break; + + ip = callstack[i]; + sym = machine__find_kernel_symbol(machine, ip, &kmap); + if (sym == NULL) + continue; + + list_for_each_entry(filter, &callstack_filters, list) { + if (strstr(sym->name, filter->name)) + return true; + } + } + return false; +} diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h index 1a7248ff3889..a09f7fe877df 100644 --- a/tools/perf/util/lock-contention.h +++ b/tools/perf/util/lock-contention.h @@ -10,10 +10,12 @@ struct lock_filter { int nr_addrs; int nr_syms; int nr_cgrps; + int nr_slabs; unsigned int *types; unsigned long *addrs; char **syms; u64 *cgrps; + char **slabs; }; struct lock_stat { @@ -67,10 +69,11 @@ struct lock_stat { */ #define MAX_LOCK_DEPTH 48 -struct lock_stat *lock_stat_find(u64 addr); -struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags); +/* based on kernel/lockdep.c */ +#define LOCKHASH_BITS 12 +#define LOCKHASH_SIZE (1UL << LOCKHASH_BITS) -bool match_callstack_filter(struct machine *machine, u64 *callstack); +extern struct hlist_head *lockhash_table; /* * struct lock_seq_stat: @@ -148,8 +151,17 @@ struct lock_contention { bool save_callstack; }; -#ifdef HAVE_BPF_SKEL +struct option; +int parse_call_stack(const struct option *opt, const char *str, int unset); +bool needs_callstack(void); +struct lock_stat *lock_stat_find(u64 addr); +struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags); + +bool match_callstack_filter(struct machine *machine, u64 *callstack, int max_stack_depth); + + +#ifdef HAVE_BPF_SKEL int lock_contention_prepare(struct lock_contention *con); int lock_contention_start(void); int lock_contention_stop(void); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 9be2f4479f52..9c7bf17bcbe8 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1561,6 +1561,8 @@ int machine__create_kernel_maps(struct machine *machine) } } + maps__fixup_end(machine__kernel_maps(machine)); + out_put: dso__put(kernel); return ret; diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index bf5090f5220b..0277d3e1505c 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -189,7 +189,7 @@ static bool perf_pmu__mem_events_supported(const char *mnt, struct perf_pmu *pmu if (!e->event_name) return true; - scnprintf(path, PATH_MAX, "%s/devices/%s/events/%s", mnt, pmu->name, e->event_name); + scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/events/%s", mnt, pmu->name, e->event_name); return !stat(path, &st); } @@ -258,6 +258,7 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr) const char *s; char *copy; struct perf_cpu_map *cpu_map = NULL; + int ret; while ((pmu = perf_pmus__scan_mem(pmu)) != NULL) { for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) { @@ -283,7 +284,9 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr) rec_argv[i++] = "-e"; rec_argv[i++] = copy; - cpu_map = perf_cpu_map__merge(cpu_map, pmu->cpus); + ret = perf_cpu_map__merge(&cpu_map, pmu->cpus); + if (ret < 0) + return ret; } } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index afeb8d815bbf..6c36b98875bc 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -489,7 +489,6 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name, return found_supported ? 0 : -EINVAL; } -#ifdef HAVE_LIBTRACEEVENT static void tracepoint_error(struct parse_events_error *e, int err, const char *sys, const char *name, int column) { @@ -644,7 +643,6 @@ static int add_tracepoint_multi_sys(struct parse_events_state *parse_state, closedir(events_dir); return ret; } -#endif /* HAVE_LIBTRACEEVENT */ size_t default_breakpoint_len(void) { @@ -795,6 +793,7 @@ const char *parse_events__term_type_str(enum parse_events__term_type term_type) [PARSE_EVENTS__TERM_TYPE_DRV_CFG] = "driver-config", [PARSE_EVENTS__TERM_TYPE_PERCORE] = "percore", [PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT] = "aux-output", + [PARSE_EVENTS__TERM_TYPE_AUX_ACTION] = "aux-action", [PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE] = "aux-sample-size", [PARSE_EVENTS__TERM_TYPE_METRIC_ID] = "metric-id", [PARSE_EVENTS__TERM_TYPE_RAW] = "raw", @@ -844,6 +843,7 @@ config_term_avail(enum parse_events__term_type term_type, struct parse_events_er case PARSE_EVENTS__TERM_TYPE_OVERWRITE: case PARSE_EVENTS__TERM_TYPE_DRV_CFG: case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: case PARSE_EVENTS__TERM_TYPE_RAW: case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: @@ -963,6 +963,9 @@ do { \ case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: CHECK_TYPE_VAL(NUM); break; + case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: + CHECK_TYPE_VAL(STR); + break; case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: CHECK_TYPE_VAL(NUM); if (term->val.num > UINT_MAX) { @@ -1066,7 +1069,6 @@ static int config_term_pmu(struct perf_event_attr *attr, return config_term_common(attr, term, err); } -#ifdef HAVE_LIBTRACEEVENT static int config_term_tracepoint(struct perf_event_attr *attr, struct parse_events_term *term, struct parse_events_error *err) @@ -1081,6 +1083,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr, case PARSE_EVENTS__TERM_TYPE_OVERWRITE: case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: return config_term_common(attr, term, err); case PARSE_EVENTS__TERM_TYPE_USER: @@ -1111,7 +1114,6 @@ static int config_term_tracepoint(struct perf_event_attr *attr, return 0; } -#endif static int config_attr(struct perf_event_attr *attr, const struct parse_events_terms *head, @@ -1217,6 +1219,9 @@ do { \ ADD_CONFIG_TERM_VAL(AUX_OUTPUT, aux_output, term->val.num ? 1 : 0, term->weak); break; + case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: + ADD_CONFIG_TERM_STR(AUX_ACTION, term->val.str, term->weak); + break; case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size, term->val.num, term->weak); @@ -1279,6 +1284,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct parse_events_terms *head case PARSE_EVENTS__TERM_TYPE_DRV_CFG: case PARSE_EVENTS__TERM_TYPE_PERCORE: case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_ACTION: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: case PARSE_EVENTS__TERM_TYPE_METRIC_ID: case PARSE_EVENTS__TERM_TYPE_RAW: @@ -1303,7 +1309,7 @@ int parse_events_add_tracepoint(struct parse_events_state *parse_state, struct parse_events_terms *head_config, void *loc_) { YYLTYPE *loc = loc_; -#ifdef HAVE_LIBTRACEEVENT + if (head_config) { struct perf_event_attr attr; @@ -1318,16 +1324,6 @@ int parse_events_add_tracepoint(struct parse_events_state *parse_state, else return add_tracepoint_event(parse_state, list, sys, event, err, head_config, loc); -#else - (void)parse_state; - (void)list; - (void)sys; - (void)event; - (void)head_config; - parse_events_error__handle(err, loc->first_column, strdup("unsupported tracepoint"), - strdup("libtraceevent is necessary for tracepoint support")); - return -1; -#endif } static int __parse_events_add_numeric(struct parse_events_state *parse_state, @@ -1664,7 +1660,7 @@ int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state /* Failed to add, try wildcard expansion of event_or_pmu as a PMU name. */ while ((pmu = perf_pmus__scan(pmu)) != NULL) { if (!parse_events__filter_pmu(parse_state, pmu) && - perf_pmu__match(pmu, event_or_pmu)) { + perf_pmu__wildcard_match(pmu, event_or_pmu)) { bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu); if (!parse_events_add_pmu(parse_state, *listp, pmu, diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 3f4334ec6231..e176a34ab088 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -74,6 +74,7 @@ enum parse_events__term_type { PARSE_EVENTS__TERM_TYPE_DRV_CFG, PARSE_EVENTS__TERM_TYPE_PERCORE, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT, + PARSE_EVENTS__TERM_TYPE_AUX_ACTION, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE, PARSE_EVENTS__TERM_TYPE_METRIC_ID, PARSE_EVENTS__TERM_TYPE_RAW, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 14e5bd856a18..bf7f73548605 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -321,6 +321,7 @@ overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); } no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); } percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); } aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); } +aux-action { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_ACTION); } aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); } metric-id { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); } cpu-cycles|cycles { return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); } diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index 00adf872bf00..2e62f272fda8 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -68,14 +68,12 @@ bool is_directory(const char *base_path, const struct dirent *dent) return S_ISDIR(st.st_mode); } -bool is_executable_file(const char *base_path, const struct dirent *dent) +bool is_directory_at(int dir_fd, const char *path) { - char path[PATH_MAX]; struct stat st; - snprintf(path, sizeof(path), "%s/%s", base_path, dent->d_name); - if (stat(path, &st)) + if (fstatat(dir_fd, path, &st, /*flags=*/0)) return false; - return !S_ISDIR(st.st_mode) && (st.st_mode & S_IXUSR); + return S_ISDIR(st.st_mode); } diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h index d94902c22222..fb850fb55c60 100644 --- a/tools/perf/util/path.h +++ b/tools/perf/util/path.h @@ -12,6 +12,6 @@ int path__join3(char *bf, size_t size, const char *path1, const char *path2, con bool is_regular_file(const char *file); bool is_directory(const char *base_path, const struct dirent *dent); -bool is_executable_file(const char *base_path, const struct dirent *dent); +bool is_directory_at(int dir_fd, const char *path); #endif /* _PERF_PATH_H */ diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index 59fbbba79697..c7f3543b9921 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -212,7 +212,6 @@ static void __p_config_hw_cache_id(char *buf, size_t size, u64 value) } } -#ifdef HAVE_LIBTRACEEVENT static void __p_config_tracepoint_id(char *buf, size_t size, u64 value) { char *str = tracepoint_id_to_name(value); @@ -220,7 +219,6 @@ static void __p_config_tracepoint_id(char *buf, size_t size, u64 value) print_id_hex(str); free(str); } -#endif static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type, u64 value) { @@ -238,9 +236,7 @@ static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type case PERF_TYPE_HW_CACHE: return __p_config_hw_cache_id(buf, size, value); case PERF_TYPE_TRACEPOINT: -#ifdef HAVE_LIBTRACEEVENT return __p_config_tracepoint_id(buf, size, value); -#endif case PERF_TYPE_RAW: case PERF_TYPE_BREAKPOINT: default: @@ -335,6 +331,9 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(sample_max_stack, p_unsigned); PRINT_ATTRf(aux_sample_size, p_unsigned); PRINT_ATTRf(sig_data, p_unsigned); + PRINT_ATTRf(aux_start_paused, p_unsigned); + PRINT_ATTRf(aux_pause, p_unsigned); + PRINT_ATTRf(aux_resume, p_unsigned); return ret; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 08a9d0bd9301..72aa6167c090 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -12,6 +12,7 @@ #include <stdbool.h> #include <dirent.h> #include <api/fs/fs.h> +#include <api/io.h> #include <locale.h> #include <fnmatch.h> #include <math.h> @@ -35,12 +36,12 @@ #define UNIT_MAX_LEN 31 /* max length for event unit name */ enum event_source { - /* An event loaded from /sys/devices/<pmu>/events. */ + /* An event loaded from /sys/bus/event_source/devices/<pmu>/events. */ EVENT_SRC_SYSFS, /* An event loaded from a CPUID matched json file. */ EVENT_SRC_CPU_JSON, /* - * An event loaded from a /sys/devices/<pmu>/identifier matched json + * An event loaded from a /sys/bus/event_source/devices/<pmu>/identifier matched json * file. */ EVENT_SRC_SYS_JSON, @@ -595,7 +596,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, }; if (pmu_events_table__find_event(pmu->events_table, pmu, name, update_alias, &data) == 0) - pmu->cpu_json_aliases++; + pmu->cpu_common_json_aliases++; } pmu->sysfs_aliases++; break; @@ -748,26 +749,35 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias, int err_loc, struct lis * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64) * may have a "cpus" file. */ -static struct perf_cpu_map *pmu_cpumask(int dirfd, const char *name, bool is_core) +static struct perf_cpu_map *pmu_cpumask(int dirfd, const char *pmu_name, bool is_core) { - struct perf_cpu_map *cpus; const char *templates[] = { "cpumask", "cpus", NULL }; const char **template; - char pmu_name[PATH_MAX]; - struct perf_pmu pmu = {.name = pmu_name}; - FILE *file; - strlcpy(pmu_name, name, sizeof(pmu_name)); for (template = templates; *template; template++) { - file = perf_pmu__open_file_at(&pmu, dirfd, *template); - if (!file) + struct io io; + char buf[128]; + char *cpumask = NULL; + size_t cpumask_len; + ssize_t ret; + struct perf_cpu_map *cpus; + + io.fd = perf_pmu__pathname_fd(dirfd, pmu_name, *template, O_RDONLY); + if (io.fd < 0) continue; - cpus = perf_cpu_map__read(file); - fclose(file); + + io__init(&io, io.fd, buf, sizeof(buf)); + ret = io__getline(&io, &cpumask, &cpumask_len); + close(io.fd); + if (ret < 0) + continue; + + cpus = perf_cpu_map__new(cpumask); + free(cpumask); if (cpus) return cpus; } @@ -837,21 +847,23 @@ static size_t pmu_deduped_name_len(const struct perf_pmu *pmu, const char *name, } /** - * perf_pmu__match_ignoring_suffix - Does the pmu_name match tok ignoring any - * trailing suffix? The Suffix must be in form - * tok_{digits}, or tok{digits}. + * perf_pmu__match_wildcard - Does the pmu_name start with tok and is then only + * followed by nothing or a suffix? tok may contain + * part of a suffix. * @pmu_name: The pmu_name with possible suffix. - * @tok: The possible match to pmu_name without suffix. + * @tok: The wildcard argument to match. */ -static bool perf_pmu__match_ignoring_suffix(const char *pmu_name, const char *tok) +static bool perf_pmu__match_wildcard(const char *pmu_name, const char *tok) { const char *p, *suffix; bool has_hex = false; + size_t tok_len = strlen(tok); - if (strncmp(pmu_name, tok, strlen(tok))) + /* Check start of pmu_name for equality. */ + if (strncmp(pmu_name, tok, tok_len)) return false; - suffix = p = pmu_name + strlen(tok); + suffix = p = pmu_name + tok_len; if (*p == 0) return true; @@ -877,60 +889,84 @@ static bool perf_pmu__match_ignoring_suffix(const char *pmu_name, const char *to } /** - * pmu_uncore_alias_match - does name match the PMU name? - * @pmu_name: the json struct pmu_event name. This may lack a suffix (which + * perf_pmu__match_ignoring_suffix_uncore - Does the pmu_name match tok ignoring + * any trailing suffix on pmu_name and + * tok? The Suffix must be in form + * tok_{digits}, or tok{digits}. + * @pmu_name: The pmu_name with possible suffix. + * @tok: The possible match to pmu_name. + */ +static bool perf_pmu__match_ignoring_suffix_uncore(const char *pmu_name, const char *tok) +{ + size_t pmu_name_len, tok_len; + + /* For robustness, check for NULL. */ + if (pmu_name == NULL) + return tok == NULL; + + /* uncore_ prefixes are ignored. */ + if (!strncmp(pmu_name, "uncore_", 7)) + pmu_name += 7; + if (!strncmp(tok, "uncore_", 7)) + tok += 7; + + pmu_name_len = pmu_name_len_no_suffix(pmu_name); + tok_len = pmu_name_len_no_suffix(tok); + if (pmu_name_len != tok_len) + return false; + + return strncmp(pmu_name, tok, pmu_name_len) == 0; +} + + +/** + * perf_pmu__match_wildcard_uncore - does to_match match the PMU's name? + * @pmu_name: The pmu->name or pmu->alias to match against. + * @to_match: the json struct pmu_event name. This may lack a suffix (which * matches) or be of the form "socket,pmuname" which will match * "socketX_pmunameY". - * @name: a real full PMU name as from sysfs. */ -static bool pmu_uncore_alias_match(const char *pmu_name, const char *name) +static bool perf_pmu__match_wildcard_uncore(const char *pmu_name, const char *to_match) { - char *tmp = NULL, *tok, *str; - bool res; - - if (strchr(pmu_name, ',') == NULL) - return perf_pmu__match_ignoring_suffix(name, pmu_name); + char *mutable_to_match, *tok, *tmp; - str = strdup(pmu_name); - if (!str) + if (!pmu_name) return false; - /* - * uncore alias may be from different PMU with common prefix - */ - tok = strtok_r(str, ",", &tmp); - if (strncmp(pmu_name, tok, strlen(tok))) { - res = false; - goto out; - } + /* uncore_ prefixes are ignored. */ + if (!strncmp(pmu_name, "uncore_", 7)) + pmu_name += 7; + if (!strncmp(to_match, "uncore_", 7)) + to_match += 7; - /* - * Match more complex aliases where the alias name is a comma-delimited - * list of tokens, orderly contained in the matching PMU name. - * - * Example: For alias "socket,pmuname" and PMU "socketX_pmunameY", we - * match "socket" in "socketX_pmunameY" and then "pmuname" in - * "pmunameY". - */ - while (1) { - char *next_tok = strtok_r(NULL, ",", &tmp); + if (strchr(to_match, ',') == NULL) + return perf_pmu__match_wildcard(pmu_name, to_match); - name = strstr(name, tok); - if (!name || - (!next_tok && !perf_pmu__match_ignoring_suffix(name, tok))) { - res = false; - goto out; + /* Process comma separated list of PMU name components. */ + mutable_to_match = strdup(to_match); + if (!mutable_to_match) + return false; + + tok = strtok_r(mutable_to_match, ",", &tmp); + while (tok) { + size_t tok_len = strlen(tok); + + if (strncmp(pmu_name, tok, tok_len)) { + /* Mismatch between part of pmu_name and tok. */ + free(mutable_to_match); + return false; } - if (!next_tok) - break; - tok = next_tok; - name += strlen(tok); + /* Move pmu_name forward over tok and suffix. */ + pmu_name += tok_len; + while (*pmu_name != '\0' && isdigit(*pmu_name)) + pmu_name++; + if (*pmu_name == '_') + pmu_name++; + + tok = strtok_r(NULL, ",", &tmp); } - - res = true; -out: - free(str); - return res; + free(mutable_to_match); + return *pmu_name == '\0'; } bool pmu_uncore_identifier_match(const char *compat, const char *id) @@ -993,11 +1029,19 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe, { struct perf_pmu *pmu = vdata; - if (!pe->compat || !pe->pmu) + if (!pe->compat || !pe->pmu) { + /* No data to match. */ return 0; + } - if (pmu_uncore_alias_match(pe->pmu, pmu->name) && - pmu_uncore_identifier_match(pe->compat, pmu->id)) { + if (!perf_pmu__match_wildcard_uncore(pmu->name, pe->pmu) && + !perf_pmu__match_wildcard_uncore(pmu->alias_name, pe->pmu)) { + /* PMU name/alias_name don't match. */ + return 0; + } + + if (pmu_uncore_identifier_match(pe->compat, pmu->id)) { + /* Id matched. */ perf_pmu__new_alias(pmu, pe->name, pe->desc, @@ -1006,7 +1050,6 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe, pe, EVENT_SRC_SYS_JSON); } - return 0; } @@ -1763,6 +1806,7 @@ int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_call "no-overwrite", "percore", "aux-output", + "aux-action=(pause|resume|start-paused)", "aux-sample-size=number", }; struct perf_pmu_format *format; @@ -1840,9 +1884,10 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu) if (pmu->cpu_aliases_added) nr += pmu->cpu_json_aliases; else if (pmu->events_table) - nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->cpu_json_aliases; + nr += pmu_events_table__num_events(pmu->events_table, pmu) - + pmu->cpu_common_json_aliases; else - assert(pmu->cpu_json_aliases == 0); + assert(pmu->cpu_json_aliases == 0 && pmu->cpu_common_json_aliases == 0); if (perf_pmu__is_tool(pmu)) nr -= tool_pmu__num_skip_events(); @@ -1963,15 +2008,82 @@ out: return ret; } -bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name) +static bool perf_pmu___name_match(const struct perf_pmu *pmu, const char *to_match, bool wildcard) { - return !strcmp(pmu->name, pmu_name) || - (pmu->is_uncore && pmu_uncore_alias_match(pmu_name, pmu->name)) || + const char *names[2] = { + pmu->name, + pmu->alias_name, + }; + if (pmu->is_core) { + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + const char *name = names[i]; + + if (!name) + continue; + + if (!strcmp(name, to_match)) { + /* Exact name match. */ + return true; + } + } + if (!strcmp(to_match, "default_core")) { + /* + * jevents and tests use default_core as a marker for any core + * PMU as the PMU name varies across architectures. + */ + return true; + } + return false; + } + if (!pmu->is_uncore) { /* - * jevents and tests use default_core as a marker for any core - * PMU as the PMU name varies across architectures. + * PMU isn't core or uncore, some kind of broken CPU mask + * situation. Only match exact name. */ - (pmu->is_core && !strcmp(pmu_name, "default_core")); + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + const char *name = names[i]; + + if (!name) + continue; + + if (!strcmp(name, to_match)) { + /* Exact name match. */ + return true; + } + } + return false; + } + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + const char *name = names[i]; + + if (wildcard && perf_pmu__match_wildcard_uncore(name, to_match)) + return true; + if (!wildcard && perf_pmu__match_ignoring_suffix_uncore(name, to_match)) + return true; + } + return false; +} + +/** + * perf_pmu__name_wildcard_match - Called by the jevents generated code to see + * if pmu matches the json to_match string. + * @pmu: The pmu whose name/alias to match. + * @to_match: The possible match to pmu_name. + */ +bool perf_pmu__name_wildcard_match(const struct perf_pmu *pmu, const char *to_match) +{ + return perf_pmu___name_match(pmu, to_match, /*wildcard=*/true); +} + +/** + * perf_pmu__name_no_suffix_match - Does pmu's name match to_match ignoring any + * trailing suffix on the pmu_name and/or tok? + * @pmu: The pmu whose name/alias to match. + * @to_match: The possible match to pmu_name. + */ +bool perf_pmu__name_no_suffix_match(const struct perf_pmu *pmu, const char *to_match) +{ + return perf_pmu___name_match(pmu, to_match, /*wildcard=*/false); } bool perf_pmu__is_software(const struct perf_pmu *pmu) @@ -2218,29 +2330,31 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, name ?: "N/A", buf, config_name, config); } -bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok) +bool perf_pmu__wildcard_match(const struct perf_pmu *pmu, const char *wildcard_to_match) { - const char *name = pmu->name; - bool need_fnmatch = strisglob(tok); + const char *names[2] = { + pmu->name, + pmu->alias_name, + }; + bool need_fnmatch = strisglob(wildcard_to_match); - if (!strncmp(tok, "uncore_", 7)) - tok += 7; - if (!strncmp(name, "uncore_", 7)) - name += 7; + if (!strncmp(wildcard_to_match, "uncore_", 7)) + wildcard_to_match += 7; - if (perf_pmu__match_ignoring_suffix(name, tok) || - (need_fnmatch && !fnmatch(tok, name, 0))) - return true; + for (size_t i = 0; i < ARRAY_SIZE(names); i++) { + const char *pmu_name = names[i]; - name = pmu->alias_name; - if (!name) - return false; + if (!pmu_name) + continue; - if (!strncmp(name, "uncore_", 7)) - name += 7; + if (!strncmp(pmu_name, "uncore_", 7)) + pmu_name += 7; - return perf_pmu__match_ignoring_suffix(name, tok) || - (need_fnmatch && !fnmatch(tok, name, 0)); + if (perf_pmu__match_wildcard(pmu_name, wildcard_to_match) || + (need_fnmatch && !fnmatch(wildcard_to_match, pmu_name, 0))) + return true; + } + return false; } int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size) diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index dbed6c243a5e..b93014cc3670 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -37,6 +37,8 @@ struct perf_pmu_caps { }; enum { + PERF_PMU_TYPE_PE_START = 0, + PERF_PMU_TYPE_PE_END = 0xFFFEFFFF, PERF_PMU_TYPE_HWMON_START = 0xFFFF0000, PERF_PMU_TYPE_HWMON_END = 0xFFFFFFFD, PERF_PMU_TYPE_TOOL = 0xFFFFFFFE, @@ -134,6 +136,11 @@ struct perf_pmu { uint32_t cpu_json_aliases; /** @sys_json_aliases: Number of json event aliases loaded matching the PMU's identifier. */ uint32_t sys_json_aliases; + /** + * @cpu_common_json_aliases: Number of json events that overlapped with sysfs when + * loading all sysfs events. + */ + uint32_t cpu_common_json_aliases; /** @sysfs_aliases_loaded: Are sysfs aliases loaded from disk? */ bool sysfs_aliases_loaded; /** @@ -238,7 +245,8 @@ bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name); size_t perf_pmu__num_events(struct perf_pmu *pmu); int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, void *state, pmu_event_callback cb); -bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name); +bool perf_pmu__name_wildcard_match(const struct perf_pmu *pmu, const char *to_match); +bool perf_pmu__name_no_suffix_match(const struct perf_pmu *pmu, const char *to_match); /** * perf_pmu_is_software - is the PMU a software PMU as in it uses the @@ -273,7 +281,7 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, const char *config_name); void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu); -bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok); +bool perf_pmu__wildcard_match(const struct perf_pmu *pmu, const char *wildcard_to_match); int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size); int perf_pmu__pathname_scnprintf(char *buf, size_t size, diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c index b493da0d22ef..7959af59908c 100644 --- a/tools/perf/util/pmus.c +++ b/tools/perf/util/pmus.c @@ -37,10 +37,25 @@ */ static LIST_HEAD(core_pmus); static LIST_HEAD(other_pmus); -static bool read_sysfs_core_pmus; -static bool read_sysfs_all_pmus; +enum perf_tool_pmu_type { + PERF_TOOL_PMU_TYPE_PE_CORE, + PERF_TOOL_PMU_TYPE_PE_OTHER, + PERF_TOOL_PMU_TYPE_TOOL, + PERF_TOOL_PMU_TYPE_HWMON, + +#define PERF_TOOL_PMU_TYPE_PE_CORE_MASK (1 << PERF_TOOL_PMU_TYPE_PE_CORE) +#define PERF_TOOL_PMU_TYPE_PE_OTHER_MASK (1 << PERF_TOOL_PMU_TYPE_PE_OTHER) +#define PERF_TOOL_PMU_TYPE_TOOL_MASK (1 << PERF_TOOL_PMU_TYPE_TOOL) +#define PERF_TOOL_PMU_TYPE_HWMON_MASK (1 << PERF_TOOL_PMU_TYPE_HWMON) + +#define PERF_TOOL_PMU_TYPE_ALL_MASK (PERF_TOOL_PMU_TYPE_PE_CORE_MASK | \ + PERF_TOOL_PMU_TYPE_PE_OTHER_MASK | \ + PERF_TOOL_PMU_TYPE_TOOL_MASK | \ + PERF_TOOL_PMU_TYPE_HWMON_MASK) +}; +static unsigned int read_pmu_types; -static void pmu_read_sysfs(bool core_only); +static void pmu_read_sysfs(unsigned int to_read_pmus); size_t pmu_name_len_no_suffix(const char *str) { @@ -102,8 +117,7 @@ void perf_pmus__destroy(void) perf_pmu__delete(pmu); } - read_sysfs_core_pmus = false; - read_sysfs_all_pmus = false; + read_pmu_types = 0; } static struct perf_pmu *pmu_find(const char *name) @@ -129,6 +143,7 @@ struct perf_pmu *perf_pmus__find(const char *name) struct perf_pmu *pmu; int dirfd; bool core_pmu; + unsigned int to_read_pmus = 0; /* * Once PMU is loaded it stays in the list, @@ -139,11 +154,11 @@ struct perf_pmu *perf_pmus__find(const char *name) if (pmu) return pmu; - if (read_sysfs_all_pmus) + if (read_pmu_types == PERF_TOOL_PMU_TYPE_ALL_MASK) return NULL; core_pmu = is_pmu_core(name); - if (core_pmu && read_sysfs_core_pmus) + if (core_pmu && (read_pmu_types & PERF_TOOL_PMU_TYPE_PE_CORE_MASK)) return NULL; dirfd = perf_pmu__event_source_devices_fd(); @@ -151,15 +166,27 @@ struct perf_pmu *perf_pmus__find(const char *name) /*eager_load=*/false); close(dirfd); - if (!pmu) { - /* - * Looking up an inidividual PMU failed. This may mean name is - * an alias, so read the PMUs from sysfs and try to find again. - */ - pmu_read_sysfs(core_pmu); + if (pmu) + return pmu; + + /* Looking up an individual perf event PMU failed, check if a tool PMU should be read. */ + if (!strncmp(name, "hwmon_", 6)) + to_read_pmus |= PERF_TOOL_PMU_TYPE_HWMON_MASK; + else if (!strcmp(name, "tool")) + to_read_pmus |= PERF_TOOL_PMU_TYPE_TOOL_MASK; + + if (to_read_pmus) { + pmu_read_sysfs(to_read_pmus); pmu = pmu_find(name); + if (pmu) + return pmu; } - return pmu; + /* Read all necessary PMUs from sysfs and see if the PMU is found. */ + to_read_pmus = PERF_TOOL_PMU_TYPE_PE_CORE_MASK; + if (!core_pmu) + to_read_pmus |= PERF_TOOL_PMU_TYPE_PE_OTHER_MASK; + pmu_read_sysfs(to_read_pmus); + return pmu_find(name); } static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name) @@ -176,11 +203,11 @@ static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name) if (pmu) return pmu; - if (read_sysfs_all_pmus) + if (read_pmu_types == PERF_TOOL_PMU_TYPE_ALL_MASK) return NULL; core_pmu = is_pmu_core(name); - if (core_pmu && read_sysfs_core_pmus) + if (core_pmu && (read_pmu_types & PERF_TOOL_PMU_TYPE_PE_CORE_MASK)) return NULL; return perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name, @@ -197,52 +224,61 @@ static int pmus_cmp(void *priv __maybe_unused, } /* Add all pmus in sysfs to pmu list: */ -static void pmu_read_sysfs(bool core_only) +static void pmu_read_sysfs(unsigned int to_read_types) { - int fd; - DIR *dir; - struct dirent *dent; struct perf_pmu *tool_pmu; - if (read_sysfs_all_pmus || (core_only && read_sysfs_core_pmus)) + if ((read_pmu_types & to_read_types) == to_read_types) { + /* All requested PMU types have been read. */ return; + } - fd = perf_pmu__event_source_devices_fd(); - if (fd < 0) - return; + if (to_read_types & (PERF_TOOL_PMU_TYPE_PE_CORE_MASK | PERF_TOOL_PMU_TYPE_PE_OTHER_MASK)) { + int fd = perf_pmu__event_source_devices_fd(); + DIR *dir; + struct dirent *dent; + bool core_only = (to_read_types & PERF_TOOL_PMU_TYPE_PE_OTHER_MASK) == 0; - dir = fdopendir(fd); - if (!dir) { - close(fd); - return; - } + if (fd < 0) + goto skip_pe_pmus; - while ((dent = readdir(dir))) { - if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) - continue; - if (core_only && !is_pmu_core(dent->d_name)) - continue; - /* add to static LIST_HEAD(core_pmus) or LIST_HEAD(other_pmus): */ - perf_pmu__find2(fd, dent->d_name); - } + dir = fdopendir(fd); + if (!dir) { + close(fd); + goto skip_pe_pmus; + } - closedir(dir); - if (list_empty(&core_pmus)) { + while ((dent = readdir(dir))) { + if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) + continue; + if (core_only && !is_pmu_core(dent->d_name)) + continue; + /* add to static LIST_HEAD(core_pmus) or LIST_HEAD(other_pmus): */ + perf_pmu__find2(fd, dent->d_name); + } + + closedir(dir); + } +skip_pe_pmus: + if ((to_read_types & PERF_TOOL_PMU_TYPE_PE_CORE_MASK) && list_empty(&core_pmus)) { if (!perf_pmu__create_placeholder_core_pmu(&core_pmus)) pr_err("Failure to set up any core PMUs\n"); } list_sort(NULL, &core_pmus, pmus_cmp); - if (!core_only) { - tool_pmu = perf_pmus__tool_pmu(); - list_add_tail(&tool_pmu->list, &other_pmus); - perf_pmus__read_hwmon_pmus(&other_pmus); + + if ((to_read_types & PERF_TOOL_PMU_TYPE_TOOL_MASK) != 0 && + (read_pmu_types & PERF_TOOL_PMU_TYPE_TOOL_MASK) == 0) { + tool_pmu = tool_pmu__new(); + if (tool_pmu) + list_add_tail(&tool_pmu->list, &other_pmus); } + if ((to_read_types & PERF_TOOL_PMU_TYPE_HWMON_MASK) != 0 && + (read_pmu_types & PERF_TOOL_PMU_TYPE_HWMON_MASK) == 0) + perf_pmus__read_hwmon_pmus(&other_pmus); + list_sort(NULL, &other_pmus, pmus_cmp); - if (!list_empty(&core_pmus)) { - read_sysfs_core_pmus = true; - if (!core_only) - read_sysfs_all_pmus = true; - } + + read_pmu_types |= to_read_types; } static struct perf_pmu *__perf_pmus__find_by_type(unsigned int type) @@ -263,12 +299,21 @@ static struct perf_pmu *__perf_pmus__find_by_type(unsigned int type) struct perf_pmu *perf_pmus__find_by_type(unsigned int type) { + unsigned int to_read_pmus; struct perf_pmu *pmu = __perf_pmus__find_by_type(type); - if (pmu || read_sysfs_all_pmus) + if (pmu || (read_pmu_types == PERF_TOOL_PMU_TYPE_ALL_MASK)) return pmu; - pmu_read_sysfs(/*core_only=*/false); + if (type >= PERF_PMU_TYPE_PE_START && type <= PERF_PMU_TYPE_PE_END) { + to_read_pmus = PERF_TOOL_PMU_TYPE_PE_CORE_MASK | + PERF_TOOL_PMU_TYPE_PE_OTHER_MASK; + } else if (type >= PERF_PMU_TYPE_HWMON_START && type <= PERF_PMU_TYPE_HWMON_END) { + to_read_pmus = PERF_TOOL_PMU_TYPE_HWMON_MASK; + } else { + to_read_pmus = PERF_TOOL_PMU_TYPE_TOOL_MASK; + } + pmu_read_sysfs(to_read_pmus); pmu = __perf_pmus__find_by_type(type); return pmu; } @@ -282,7 +327,7 @@ struct perf_pmu *perf_pmus__scan(struct perf_pmu *pmu) bool use_core_pmus = !pmu || pmu->is_core; if (!pmu) { - pmu_read_sysfs(/*core_only=*/false); + pmu_read_sysfs(PERF_TOOL_PMU_TYPE_ALL_MASK); pmu = list_prepare_entry(pmu, &core_pmus, list); } if (use_core_pmus) { @@ -300,7 +345,7 @@ struct perf_pmu *perf_pmus__scan(struct perf_pmu *pmu) struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu) { if (!pmu) { - pmu_read_sysfs(/*core_only=*/true); + pmu_read_sysfs(PERF_TOOL_PMU_TYPE_PE_CORE_MASK); return list_first_entry_or_null(&core_pmus, typeof(*pmu), list); } list_for_each_entry_continue(pmu, &core_pmus, list) @@ -316,7 +361,7 @@ static struct perf_pmu *perf_pmus__scan_skip_duplicates(struct perf_pmu *pmu) const char *last_pmu_name = (pmu && pmu->name) ? pmu->name : ""; if (!pmu) { - pmu_read_sysfs(/*core_only=*/false); + pmu_read_sysfs(PERF_TOOL_PMU_TYPE_ALL_MASK); pmu = list_prepare_entry(pmu, &core_pmus, list); } else last_pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: ""); @@ -710,11 +755,25 @@ char *perf_pmus__default_pmu_name(void) struct perf_pmu *evsel__find_pmu(const struct evsel *evsel) { struct perf_pmu *pmu = evsel->pmu; + bool legacy_core_type; - if (!pmu) { - pmu = perf_pmus__find_by_type(evsel->core.attr.type); - ((struct evsel *)evsel)->pmu = pmu; + if (pmu) + return pmu; + + pmu = perf_pmus__find_by_type(evsel->core.attr.type); + legacy_core_type = + evsel->core.attr.type == PERF_TYPE_HARDWARE || + evsel->core.attr.type == PERF_TYPE_HW_CACHE; + if (!pmu && legacy_core_type) { + if (perf_pmus__supports_extended_type()) { + u32 type = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT; + + pmu = perf_pmus__find_by_type(type); + } else { + pmu = perf_pmus__find_core_pmu(); + } } + ((struct evsel *)evsel)->pmu = pmu; return pmu; } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index eaa0318e9b87..307ad6242a4e 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1383,20 +1383,20 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) if (p == buf) { semantic_error("No file/function name in '%s'.\n", p); err = -EINVAL; - goto err; + goto out; } *(p++) = '\0'; err = parse_line_num(&p, &lr->start, "start line"); if (err) - goto err; + goto out; if (*p == '+' || *p == '-') { const char c = *(p++); err = parse_line_num(&p, &lr->end, "end line"); if (err) - goto err; + goto out; if (c == '+') { lr->end += lr->start; @@ -1416,11 +1416,11 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) if (lr->start > lr->end) { semantic_error("Start line must be smaller" " than end line.\n"); - goto err; + goto out; } if (*p != '\0') { semantic_error("Tailing with invalid str '%s'.\n", p); - goto err; + goto out; } } @@ -1431,7 +1431,7 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) lr->file = strdup_esq(p); if (lr->file == NULL) { err = -ENOMEM; - goto err; + goto out; } } if (*buf != '\0') @@ -1439,7 +1439,7 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) if (!lr->function && !lr->file) { semantic_error("Only '@*' is not allowed.\n"); err = -EINVAL; - goto err; + goto out; } } else if (strpbrk_esq(buf, "/.")) lr->file = strdup_esq(buf); @@ -1448,10 +1448,10 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) else { /* Invalid name */ semantic_error("'%s' is not a valid function name.\n", buf); err = -EINVAL; - goto err; + goto out; } -err: +out: free(buf); return err; } @@ -2775,7 +2775,7 @@ int show_perf_probe_events(struct strfilter *filter) static int get_new_event_name(char *buf, size_t len, const char *base, struct strlist *namelist, bool ret_event, - bool allow_suffix) + bool allow_suffix, bool not_C_symname) { int i, ret; char *p, *nbase; @@ -2786,10 +2786,24 @@ static int get_new_event_name(char *buf, size_t len, const char *base, if (!nbase) return -ENOMEM; - /* Cut off the dot suffixes (e.g. .const, .isra) and version suffixes */ - p = strpbrk(nbase, ".@"); - if (p && p != nbase) - *p = '\0'; + if (not_C_symname) { + /* Replace non-alnum with '_' */ + char *s, *d; + + s = d = nbase; + do { + if (*s && !isalnum(*s)) { + if (d != nbase && *(d - 1) != '_') + *d++ = '_'; + } else + *d++ = *s; + } while (*s++); + } else { + /* Cut off the dot suffixes (e.g. .const, .isra) and version suffixes */ + p = strpbrk(nbase, ".@"); + if (p && p != nbase) + *p = '\0'; + } /* Try no suffix number */ ret = e_snprintf(buf, len, "%s%s", nbase, ret_event ? "__return" : ""); @@ -2884,6 +2898,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev, bool allow_suffix) { const char *event, *group; + bool not_C_symname = true; char buf[MAX_EVENT_NAME_LEN]; int ret; @@ -2898,8 +2913,10 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev, (strncmp(pev->point.function, "0x", 2) != 0) && !strisglob(pev->point.function)) event = pev->point.function; - else + else { event = tev->point.realname; + not_C_symname = !is_known_C_lang(tev->lang); + } } if (pev->group && !pev->sdt) group = pev->group; @@ -2916,7 +2933,8 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev, /* Get an unused new event name */ ret = get_new_event_name(buf, sizeof(buf), event, namelist, - tev->point.retprobe, allow_suffix); + tev->point.retprobe, allow_suffix, + not_C_symname); if (ret < 0) return ret; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 61a5f4ff4e9c..71905ede0207 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -58,6 +58,7 @@ struct probe_trace_event { char *group; /* Group name */ struct probe_trace_point point; /* Trace point */ int nargs; /* Number of args */ + int lang; /* Dwarf language code */ bool uprobes; /* uprobes only */ struct probe_trace_arg *args; /* Arguments */ }; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 7f2ee0cb43ca..1e769b68da37 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -35,6 +35,19 @@ /* Kprobe tracer basic type is up to u64 */ #define MAX_BASIC_TYPE_BITS 64 +bool is_known_C_lang(int lang) +{ + switch (lang) { + case DW_LANG_C89: + case DW_LANG_C: + case DW_LANG_C99: + case DW_LANG_C11: + return true; + default: + return false; + } +} + /* * Probe finder related functions */ @@ -1270,6 +1283,8 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) goto end; } + tev->lang = dwarf_srclang(dwarf_diecu(sc_die, &pf->cu_die, NULL, NULL)); + pr_debug("Probe point found: %s+%lu\n", tev->point.symbol, tev->point.offset); diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index be7b46ea2460..dcf6cc1e1cbe 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -26,6 +26,9 @@ static inline int is_c_varname(const char *name) #include "dwarf-aux.h" #include "debuginfo.h" +/* Check the language code is known C */ +bool is_known_C_lang(int lang); + /* Find probe_trace_events specified by perf_probe_event from debuginfo */ int debuginfo__find_trace_events(struct debuginfo *dbg, struct perf_probe_event *pev, @@ -103,6 +106,8 @@ struct line_finder { int found; }; +#else +#define is_known_C_lang(lang) (false) #endif /* HAVE_LIBDW_SUPPORT */ #endif /*_PROBE_FINDER_H */ diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 2096cdbaa53b..a23fa5d95394 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -13,30 +13,12 @@ #include "evsel.h" #include "event.h" #include "print_binary.h" +#include "strbuf.h" #include "thread_map.h" #include "trace-event.h" #include "mmap.h" -#include "util/bpf-filter.h" -#include "util/env.h" -#include "util/kvm-stat.h" -#include "util/stat.h" -#include "util/kwork.h" #include "util/sample.h" -#include "util/lock-contention.h" #include <internal/lib.h> -#include "../builtin.h" - -#if PY_MAJOR_VERSION < 3 -#define _PyUnicode_FromString(arg) \ - PyString_FromString(arg) -#define _PyUnicode_AsString(arg) \ - PyString_AsString(arg) -#define _PyUnicode_FromFormat(...) \ - PyString_FromFormat(__VA_ARGS__) -#define _PyLong_FromLong(arg) \ - PyInt_FromLong(arg) - -#else #define _PyUnicode_FromString(arg) \ PyUnicode_FromString(arg) @@ -44,22 +26,8 @@ PyUnicode_FromFormat(__VA_ARGS__) #define _PyLong_FromLong(arg) \ PyLong_FromLong(arg) -#endif - -#ifndef Py_TYPE -#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type) -#endif -/* Define PyVarObject_HEAD_INIT for python 2.5 */ -#ifndef PyVarObject_HEAD_INIT -# define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size, -#endif - -#if PY_MAJOR_VERSION < 3 -PyMODINIT_FUNC initperf(void); -#else PyMODINIT_FUNC PyInit_perf(void); -#endif #define member_def(type, member, ptype, help) \ { #member, ptype, \ @@ -79,7 +47,7 @@ struct pyrf_event { }; #define sample_members \ - sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"), \ + sample_member_def(sample_ip, ip, T_ULONGLONG, "event ip"), \ sample_member_def(sample_pid, pid, T_INT, "event pid"), \ sample_member_def(sample_tid, tid, T_INT, "event tid"), \ sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"), \ @@ -89,7 +57,7 @@ struct pyrf_event { sample_member_def(sample_period, period, T_ULONGLONG, "event period"), \ sample_member_def(sample_cpu, cpu, T_UINT, "event cpu"), -static char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object."); +static const char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object."); static PyMemberDef pyrf_mmap_event__members[] = { sample_members @@ -104,7 +72,7 @@ static PyMemberDef pyrf_mmap_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_mmap_event__repr(const struct pyrf_event *pevent) { PyObject *ret; char *s; @@ -117,7 +85,7 @@ static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent) pevent->event.mmap.pgoff, pevent->event.mmap.filename) < 0) { ret = PyErr_NoMemory(); } else { - ret = _PyUnicode_FromString(s); + ret = PyUnicode_FromString(s); free(s); } return ret; @@ -133,7 +101,7 @@ static PyTypeObject pyrf_mmap_event__type = { .tp_repr = (reprfunc)pyrf_mmap_event__repr, }; -static char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event object."); +static const char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event object."); static PyMemberDef pyrf_task_event__members[] = { sample_members @@ -146,9 +114,9 @@ static PyMemberDef pyrf_task_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_task_event__repr(const struct pyrf_event *pevent) { - return _PyUnicode_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, " + return PyUnicode_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, " "ptid: %u, time: %" PRI_lu64 "}", pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit", pevent->event.fork.pid, @@ -168,7 +136,7 @@ static PyTypeObject pyrf_task_event__type = { .tp_repr = (reprfunc)pyrf_task_event__repr, }; -static char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object."); +static const char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object."); static PyMemberDef pyrf_comm_event__members[] = { sample_members @@ -179,9 +147,9 @@ static PyMemberDef pyrf_comm_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_comm_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_comm_event__repr(const struct pyrf_event *pevent) { - return _PyUnicode_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }", + return PyUnicode_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }", pevent->event.comm.pid, pevent->event.comm.tid, pevent->event.comm.comm); @@ -197,7 +165,7 @@ static PyTypeObject pyrf_comm_event__type = { .tp_repr = (reprfunc)pyrf_comm_event__repr, }; -static char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object."); +static const char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object."); static PyMemberDef pyrf_throttle_event__members[] = { sample_members @@ -208,11 +176,12 @@ static PyMemberDef pyrf_throttle_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_throttle_event__repr(const struct pyrf_event *pevent) { - struct perf_record_throttle *te = (struct perf_record_throttle *)(&pevent->event.header + 1); + const struct perf_record_throttle *te = (const struct perf_record_throttle *) + (&pevent->event.header + 1); - return _PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRI_lu64 ", id: %" PRI_lu64 + return PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRI_lu64 ", id: %" PRI_lu64 ", stream_id: %" PRI_lu64 " }", pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un", te->time, te->id, te->stream_id); @@ -228,7 +197,7 @@ static PyTypeObject pyrf_throttle_event__type = { .tp_repr = (reprfunc)pyrf_throttle_event__repr, }; -static char pyrf_lost_event__doc[] = PyDoc_STR("perf lost event object."); +static const char pyrf_lost_event__doc[] = PyDoc_STR("perf lost event object."); static PyMemberDef pyrf_lost_event__members[] = { sample_members @@ -237,7 +206,7 @@ static PyMemberDef pyrf_lost_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_lost_event__repr(const struct pyrf_event *pevent) { PyObject *ret; char *s; @@ -247,7 +216,7 @@ static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent) pevent->event.lost.id, pevent->event.lost.lost) < 0) { ret = PyErr_NoMemory(); } else { - ret = _PyUnicode_FromString(s); + ret = PyUnicode_FromString(s); free(s); } return ret; @@ -263,7 +232,7 @@ static PyTypeObject pyrf_lost_event__type = { .tp_repr = (reprfunc)pyrf_lost_event__repr, }; -static char pyrf_read_event__doc[] = PyDoc_STR("perf read event object."); +static const char pyrf_read_event__doc[] = PyDoc_STR("perf read event object."); static PyMemberDef pyrf_read_event__members[] = { sample_members @@ -272,9 +241,9 @@ static PyMemberDef pyrf_read_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_read_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_read_event__repr(const struct pyrf_event *pevent) { - return _PyUnicode_FromFormat("{ type: read, pid: %u, tid: %u }", + return PyUnicode_FromFormat("{ type: read, pid: %u, tid: %u }", pevent->event.read.pid, pevent->event.read.tid); /* @@ -293,7 +262,7 @@ static PyTypeObject pyrf_read_event__type = { .tp_repr = (reprfunc)pyrf_read_event__repr, }; -static char pyrf_sample_event__doc[] = PyDoc_STR("perf sample event object."); +static const char pyrf_sample_event__doc[] = PyDoc_STR("perf sample event object."); static PyMemberDef pyrf_sample_event__members[] = { sample_members @@ -301,7 +270,7 @@ static PyMemberDef pyrf_sample_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_sample_event__repr(const struct pyrf_event *pevent) { PyObject *ret; char *s; @@ -309,20 +278,20 @@ static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent) if (asprintf(&s, "{ type: sample }") < 0) { ret = PyErr_NoMemory(); } else { - ret = _PyUnicode_FromString(s); + ret = PyUnicode_FromString(s); free(s); } return ret; } #ifdef HAVE_LIBTRACEEVENT -static bool is_tracepoint(struct pyrf_event *pevent) +static bool is_tracepoint(const struct pyrf_event *pevent) { return pevent->evsel->core.attr.type == PERF_TYPE_TRACEPOINT; } static PyObject* -tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field) +tracepoint_field(const struct pyrf_event *pe, struct tep_format_field *field) { struct tep_handle *pevent = field->event->tep; void *data = pe->sample.raw_data; @@ -343,7 +312,7 @@ tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field) } if (field->flags & TEP_FIELD_IS_STRING && is_printable_array(data + offset, len)) { - ret = _PyUnicode_FromString((char *)data + offset); + ret = PyUnicode_FromString((char *)data + offset); } else { ret = PyByteArray_FromStringAndSize((const char *) data + offset, len); field->flags &= ~TEP_FIELD_IS_STRING; @@ -411,7 +380,7 @@ static PyTypeObject pyrf_sample_event__type = { .tp_getattro = (getattrofunc) pyrf_sample_event__getattro, }; -static char pyrf_context_switch_event__doc[] = PyDoc_STR("perf context_switch event object."); +static const char pyrf_context_switch_event__doc[] = PyDoc_STR("perf context_switch event object."); static PyMemberDef pyrf_context_switch_event__members[] = { sample_members @@ -421,7 +390,7 @@ static PyMemberDef pyrf_context_switch_event__members[] = { { .name = NULL, }, }; -static PyObject *pyrf_context_switch_event__repr(struct pyrf_event *pevent) +static PyObject *pyrf_context_switch_event__repr(const struct pyrf_event *pevent) { PyObject *ret; char *s; @@ -432,7 +401,7 @@ static PyObject *pyrf_context_switch_event__repr(struct pyrf_event *pevent) !!(pevent->event.header.misc & PERF_RECORD_MISC_SWITCH_OUT)) < 0) { ret = PyErr_NoMemory(); } else { - ret = _PyUnicode_FromString(s); + ret = PyUnicode_FromString(s); free(s); } return ret; @@ -501,7 +470,7 @@ static PyTypeObject *pyrf_event__type[] = { [PERF_RECORD_SWITCH_CPU_WIDE] = &pyrf_context_switch_event__type, }; -static PyObject *pyrf_event__new(union perf_event *event) +static PyObject *pyrf_event__new(const union perf_event *event) { struct pyrf_event *pevent; PyTypeObject *ptype; @@ -512,6 +481,11 @@ static PyObject *pyrf_event__new(union perf_event *event) event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)) return NULL; + // FIXME this better be dynamic or we need to parse everything + // before calling perf_mmap__consume(), including tracepoint fields. + if (sizeof(pevent->event) < event->header.size) + return NULL; + ptype = pyrf_event__type[event->header.type]; pevent = PyObject_New(struct pyrf_event, ptype); if (pevent != NULL) @@ -569,7 +543,7 @@ static PySequenceMethods pyrf_cpu_map__sequence_methods = { .sq_item = pyrf_cpu_map__item, }; -static char pyrf_cpu_map__doc[] = PyDoc_STR("cpu map object."); +static const char pyrf_cpu_map__doc[] = PyDoc_STR("cpu map object."); static PyTypeObject pyrf_cpu_map__type = { PyVarObject_HEAD_INIT(NULL, 0) @@ -638,7 +612,7 @@ static PySequenceMethods pyrf_thread_map__sequence_methods = { .sq_item = pyrf_thread_map__item, }; -static char pyrf_thread_map__doc[] = PyDoc_STR("thread map object."); +static const char pyrf_thread_map__doc[] = PyDoc_STR("thread map object."); static PyTypeObject pyrf_thread_map__type = { PyVarObject_HEAD_INIT(NULL, 0) @@ -812,6 +786,17 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, return Py_None; } +static PyObject *pyrf_evsel__str(PyObject *self) +{ + struct pyrf_evsel *pevsel = (void *)self; + struct evsel *evsel = &pevsel->evsel; + + if (!evsel->pmu) + return PyUnicode_FromFormat("evsel(%s)", evsel__name(evsel)); + + return PyUnicode_FromFormat("evsel(%s/%s/)", evsel->pmu->name, evsel__name(evsel)); +} + static PyMethodDef pyrf_evsel__methods[] = { { .ml_name = "open", @@ -822,7 +807,7 @@ static PyMethodDef pyrf_evsel__methods[] = { { .ml_name = NULL, } }; -static char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object."); +static const char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object."); static PyTypeObject pyrf_evsel__type = { PyVarObject_HEAD_INIT(NULL, 0) @@ -833,6 +818,8 @@ static PyTypeObject pyrf_evsel__type = { .tp_doc = pyrf_evsel__doc, .tp_methods = pyrf_evsel__methods, .tp_init = (initproc)pyrf_evsel__init, + .tp_str = pyrf_evsel__str, + .tp_repr = pyrf_evsel__str, }; static int pyrf_evsel__setup_types(void) @@ -918,17 +905,8 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, for (i = 0; i < evlist->core.pollfd.nr; ++i) { PyObject *file; -#if PY_MAJOR_VERSION < 3 - FILE *fp = fdopen(evlist->core.pollfd.entries[i].fd, "r"); - - if (fp == NULL) - goto free_list; - - file = PyFile_FromFile(fp, "perf", "r", NULL); -#else file = PyFile_FromFd(evlist->core.pollfd.entries[i].fd, "perf", "r", -1, NULL, NULL, NULL, 0); -#endif if (file == NULL) goto free_list; @@ -1011,20 +989,22 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, evsel = evlist__event2evsel(evlist, event); if (!evsel) { + Py_DECREF(pyevent); Py_INCREF(Py_None); return Py_None; } pevent->evsel = evsel; - err = evsel__parse_sample(evsel, event, &pevent->sample); - - /* Consume the even only after we parsed it out. */ perf_mmap__consume(&md->core); - if (err) + err = evsel__parse_sample(evsel, &pevent->event, &pevent->sample); + if (err) { + Py_DECREF(pyevent); return PyErr_Format(PyExc_OSError, "perf: can't parse sample, err=%d", err); + } + return pyevent; } end: @@ -1098,8 +1078,10 @@ static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i) struct pyrf_evlist *pevlist = (void *)obj; struct evsel *pos; - if (i >= pevlist->evlist.core.nr_entries) + if (i >= pevlist->evlist.core.nr_entries) { + PyErr_SetString(PyExc_IndexError, "Index out of range"); return NULL; + } evlist__for_each_entry(&pevlist->evlist, pos) { if (i-- == 0) @@ -1109,12 +1091,36 @@ static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i) return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel)); } +static PyObject *pyrf_evlist__str(PyObject *self) +{ + struct pyrf_evlist *pevlist = (void *)self; + struct evsel *pos; + struct strbuf sb = STRBUF_INIT; + bool first = true; + PyObject *result; + + strbuf_addstr(&sb, "evlist(["); + evlist__for_each_entry(&pevlist->evlist, pos) { + if (!first) + strbuf_addch(&sb, ','); + if (!pos->pmu) + strbuf_addstr(&sb, evsel__name(pos)); + else + strbuf_addf(&sb, "%s/%s/", pos->pmu->name, evsel__name(pos)); + first = false; + } + strbuf_addstr(&sb, "])"); + result = PyUnicode_FromString(sb.buf); + strbuf_release(&sb); + return result; +} + static PySequenceMethods pyrf_evlist__sequence_methods = { .sq_length = pyrf_evlist__length, .sq_item = pyrf_evlist__item, }; -static char pyrf_evlist__doc[] = PyDoc_STR("perf event selector list object."); +static const char pyrf_evlist__doc[] = PyDoc_STR("perf event selector list object."); static PyTypeObject pyrf_evlist__type = { PyVarObject_HEAD_INIT(NULL, 0) @@ -1126,6 +1132,8 @@ static PyTypeObject pyrf_evlist__type = { .tp_doc = pyrf_evlist__doc, .tp_methods = pyrf_evlist__methods, .tp_init = (initproc)pyrf_evlist__init, + .tp_repr = pyrf_evlist__str, + .tp_str = pyrf_evlist__str, }; static int pyrf_evlist__setup_types(void) @@ -1136,10 +1144,12 @@ static int pyrf_evlist__setup_types(void) #define PERF_CONST(name) { #name, PERF_##name } -static struct { +struct perf_constant { const char *name; int value; -} perf__constants[] = { +}; + +static const struct perf_constant perf__constants[] = { PERF_CONST(TYPE_HARDWARE), PERF_CONST(TYPE_SOFTWARE), PERF_CONST(TYPE_TRACEPOINT), @@ -1234,12 +1244,66 @@ static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel, tp_format = trace_event__tp_format(sys, name); if (IS_ERR(tp_format)) - return _PyLong_FromLong(-1); + return PyLong_FromLong(-1); - return _PyLong_FromLong(tp_format->id); + return PyLong_FromLong(tp_format->id); #endif // HAVE_LIBTRACEEVENT } +static PyObject *pyrf_evsel__from_evsel(struct evsel *evsel) +{ + struct pyrf_evsel *pevsel = PyObject_New(struct pyrf_evsel, &pyrf_evsel__type); + + if (!pevsel) + return NULL; + + memset(&pevsel->evsel, 0, sizeof(pevsel->evsel)); + evsel__init(&pevsel->evsel, &evsel->core.attr, evsel->core.idx); + + evsel__clone(&pevsel->evsel, evsel); + return (PyObject *)pevsel; +} + +static PyObject *pyrf_evlist__from_evlist(struct evlist *evlist) +{ + struct pyrf_evlist *pevlist = PyObject_New(struct pyrf_evlist, &pyrf_evlist__type); + struct evsel *pos; + + if (!pevlist) + return NULL; + + memset(&pevlist->evlist, 0, sizeof(pevlist->evlist)); + evlist__init(&pevlist->evlist, evlist->core.all_cpus, evlist->core.threads); + evlist__for_each_entry(evlist, pos) { + struct pyrf_evsel *pevsel = (void *)pyrf_evsel__from_evsel(pos); + + evlist__add(&pevlist->evlist, &pevsel->evsel); + } + return (PyObject *)pevlist; +} + +static PyObject *pyrf__parse_events(PyObject *self, PyObject *args) +{ + const char *input; + struct evlist evlist = {}; + struct parse_events_error err; + PyObject *result; + + if (!PyArg_ParseTuple(args, "s", &input)) + return NULL; + + parse_events_error__init(&err); + evlist__init(&evlist, NULL, NULL); + if (parse_events(&evlist, input, &err)) { + parse_events_error__print(&err, input); + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + result = pyrf_evlist__from_evlist(&evlist); + evlist__exit(&evlist); + return result; +} + static PyMethodDef perf__methods[] = { { .ml_name = "tracepoint", @@ -1247,21 +1311,20 @@ static PyMethodDef perf__methods[] = { .ml_flags = METH_VARARGS | METH_KEYWORDS, .ml_doc = PyDoc_STR("Get tracepoint config.") }, + { + .ml_name = "parse_events", + .ml_meth = (PyCFunction) pyrf__parse_events, + .ml_flags = METH_VARARGS, + .ml_doc = PyDoc_STR("Parse a string of events and return an evlist.") + }, { .ml_name = NULL, } }; -#if PY_MAJOR_VERSION < 3 -PyMODINIT_FUNC initperf(void) -#else PyMODINIT_FUNC PyInit_perf(void) -#endif { PyObject *obj; int i; PyObject *dict; -#if PY_MAJOR_VERSION < 3 - PyObject *module = Py_InitModule("perf", perf__methods); -#else static struct PyModuleDef moduledef = { PyModuleDef_HEAD_INIT, "perf", /* m_name */ @@ -1274,7 +1337,6 @@ PyMODINIT_FUNC PyInit_perf(void) NULL, /* m_free */ }; PyObject *module = PyModule_Create(&moduledef); -#endif if (module == NULL || pyrf_event__setup_types() < 0 || @@ -1282,11 +1344,7 @@ PyMODINIT_FUNC PyInit_perf(void) pyrf_evsel__setup_types() < 0 || pyrf_thread_map__setup_types() < 0 || pyrf_cpu_map__setup_types() < 0) -#if PY_MAJOR_VERSION < 3 - return; -#else return module; -#endif /* The page_size is placed in util object. */ page_size = sysconf(_SC_PAGE_SIZE); @@ -1335,7 +1393,7 @@ PyMODINIT_FUNC PyInit_perf(void) goto error; for (i = 0; perf__constants[i].name != NULL; i++) { - obj = _PyLong_FromLong(perf__constants[i].value); + obj = PyLong_FromLong(perf__constants[i].value); if (obj == NULL) goto error; PyDict_SetItemString(dict, perf__constants[i].name, obj); @@ -1345,109 +1403,5 @@ PyMODINIT_FUNC PyInit_perf(void) error: if (PyErr_Occurred()) PyErr_SetString(PyExc_ImportError, "perf: Init failed!"); -#if PY_MAJOR_VERSION >= 3 return module; -#endif -} - - -/* The following are stubs to avoid dragging in builtin-* objects. */ -/* TODO: move the code out of the builtin-* file into util. */ - -unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; - -#ifdef HAVE_KVM_STAT_SUPPORT -bool kvm_entry_event(struct evsel *evsel __maybe_unused) -{ - return false; -} - -bool kvm_exit_event(struct evsel *evsel __maybe_unused) -{ - return false; -} - -bool exit_event_begin(struct evsel *evsel __maybe_unused, - struct perf_sample *sample __maybe_unused, - struct event_key *key __maybe_unused) -{ - return false; -} - -bool exit_event_end(struct evsel *evsel __maybe_unused, - struct perf_sample *sample __maybe_unused, - struct event_key *key __maybe_unused) -{ - return false; -} - -void exit_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, - struct event_key *key __maybe_unused, - char *decode __maybe_unused) -{ -} -#endif // HAVE_KVM_STAT_SUPPORT - -int find_scripts(char **scripts_array __maybe_unused, char **scripts_path_array __maybe_unused, - int num __maybe_unused, int pathlen __maybe_unused) -{ - return -1; -} - -void perf_stat__set_no_csv_summary(int set __maybe_unused) -{ -} - -void perf_stat__set_big_num(int set __maybe_unused) -{ -} - -int script_spec_register(const char *spec __maybe_unused, struct scripting_ops *ops __maybe_unused) -{ - return -1; -} - -arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch __maybe_unused) -{ - return NULL; -} - -struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork __maybe_unused, - struct kwork_class *class __maybe_unused, - struct kwork_work *key __maybe_unused) -{ - return NULL; -} - -void script_fetch_insn(struct perf_sample *sample __maybe_unused, - struct thread *thread __maybe_unused, - struct machine *machine __maybe_unused) -{ -} - -int perf_sample__sprintf_flags(u32 flags __maybe_unused, char *str __maybe_unused, - size_t sz __maybe_unused) -{ - return -1; -} - -bool match_callstack_filter(struct machine *machine __maybe_unused, u64 *callstack __maybe_unused) -{ - return false; -} - -struct lock_stat *lock_stat_find(u64 addr __maybe_unused) -{ - return NULL; -} - -struct lock_stat *lock_stat_findnew(u64 addr __maybe_unused, const char *name __maybe_unused, - int flags __maybe_unused) -{ - return NULL; -} - -int cmd_inject(int argc __maybe_unused, const char *argv[] __maybe_unused) -{ - return -1; } diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 85b7f188f729..e261a57b87d4 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -344,7 +344,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, struct addr_location *al) { struct thread *thread = al->thread; - struct tep_event *event = evsel->tp_format; + struct tep_event *event; struct tep_format_field *field; static char handler[256]; unsigned long long val; @@ -362,6 +362,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) return; + event = evsel__tp_format(evsel); if (!event) { pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->core.attr.config); return; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 8bdae066e839..b1b5e94537e4 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -58,22 +58,6 @@ #include "mem-events.h" #include "util/perf_regs.h" -#if PY_MAJOR_VERSION < 3 -#define _PyUnicode_FromString(arg) \ - PyString_FromString(arg) -#define _PyUnicode_FromStringAndSize(arg1, arg2) \ - PyString_FromStringAndSize((arg1), (arg2)) -#define _PyBytes_FromStringAndSize(arg1, arg2) \ - PyString_FromStringAndSize((arg1), (arg2)) -#define _PyLong_FromLong(arg) \ - PyInt_FromLong(arg) -#define _PyLong_AsLong(arg) \ - PyInt_AsLong(arg) -#define _PyCapsule_New(arg1, arg2, arg3) \ - PyCObject_FromVoidPtr((arg1), (arg2)) - -PyMODINIT_FUNC initperf_trace_context(void); -#else #define _PyUnicode_FromString(arg) \ PyUnicode_FromString(arg) #define _PyUnicode_FromStringAndSize(arg1, arg2) \ @@ -88,7 +72,6 @@ PyMODINIT_FUNC initperf_trace_context(void); PyCapsule_New((arg1), (arg2), (arg3)) PyMODINIT_FUNC PyInit_perf_trace_context(void); -#endif #ifdef HAVE_LIBTRACEEVENT #define TRACE_EVENT_TYPE_MAX \ @@ -181,17 +164,7 @@ static int get_argument_count(PyObject *handler) { int arg_count = 0; - /* - * The attribute for the code object is func_code in Python 2, - * whereas it is __code__ in Python 3.0+. - */ - PyObject *code_obj = PyObject_GetAttrString(handler, - "func_code"); - if (PyErr_Occurred()) { - PyErr_Clear(); - code_obj = PyObject_GetAttrString(handler, - "__code__"); - } + PyObject *code_obj = code_obj = PyObject_GetAttrString(handler, "__code__"); PyErr_Clear(); if (code_obj) { PyObject *arg_count_obj = PyObject_GetAttrString(code_obj, @@ -949,7 +922,7 @@ static void python_process_tracepoint(struct perf_sample *sample, struct addr_location *al, struct addr_location *addr_al) { - struct tep_event *event = evsel->tp_format; + struct tep_event *event; PyObject *handler, *context, *t, *obj = NULL, *callchain; PyObject *dict = NULL, *all_entries_dict = NULL; static char handler_name[256]; @@ -966,6 +939,7 @@ static void python_process_tracepoint(struct perf_sample *sample, bitmap_zero(events_defined, TRACE_EVENT_TYPE_MAX); + event = evsel__tp_format(evsel); if (!event) { snprintf(handler_name, sizeof(handler_name), "ug! no event found for type %" PRIu64, (u64)evsel->core.attr.config); @@ -1902,12 +1876,6 @@ static void set_table_handlers(struct tables *tables) tables->synth_handler = get_handler("synth_data"); } -#if PY_MAJOR_VERSION < 3 -static void _free_command_line(const char **command_line, int num) -{ - free(command_line); -} -#else static void _free_command_line(wchar_t **command_line, int num) { int i; @@ -1915,7 +1883,6 @@ static void _free_command_line(wchar_t **command_line, int num) PyMem_RawFree(command_line[i]); free(command_line); } -#endif /* @@ -1925,30 +1892,12 @@ static int python_start_script(const char *script, int argc, const char **argv, struct perf_session *session) { struct tables *tables = &tables_global; -#if PY_MAJOR_VERSION < 3 - const char **command_line; -#else wchar_t **command_line; -#endif - /* - * Use a non-const name variable to cope with python 2.6's - * PyImport_AppendInittab prototype - */ - char buf[PATH_MAX], name[19] = "perf_trace_context"; + char buf[PATH_MAX]; int i, err = 0; FILE *fp; scripting_context->session = session; -#if PY_MAJOR_VERSION < 3 - command_line = malloc((argc + 1) * sizeof(const char *)); - if (!command_line) - return -1; - - command_line[0] = script; - for (i = 1; i < argc + 1; i++) - command_line[i] = argv[i - 1]; - PyImport_AppendInittab(name, initperf_trace_context); -#else command_line = malloc((argc + 1) * sizeof(wchar_t *)); if (!command_line) return -1; @@ -1956,15 +1905,10 @@ static int python_start_script(const char *script, int argc, const char **argv, command_line[0] = Py_DecodeLocale(script, NULL); for (i = 1; i < argc + 1; i++) command_line[i] = Py_DecodeLocale(argv[i - 1], NULL); - PyImport_AppendInittab(name, PyInit_perf_trace_context); -#endif + PyImport_AppendInittab("perf_trace_context", PyInit_perf_trace_context); Py_Initialize(); -#if PY_MAJOR_VERSION < 3 - PySys_SetArgv(argc + 1, (char **)command_line); -#else PySys_SetArgv(argc + 1, command_line); -#endif fp = fopen(script, "r"); if (!fp) { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 507e6cba9545..c06e3020a976 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -37,6 +37,7 @@ #include "arch/common.h" #include "units.h" #include "annotate.h" +#include "perf.h" #include <internal/lib.h> static int perf_session__deliver_event(struct perf_session *session, diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 9dd60c7869a2..3dd33721823f 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1038,17 +1038,19 @@ static char *get_trace_output(struct hist_entry *he) .data = he->raw_data, .size = he->raw_size, }; + struct tep_event *tp_format; evsel = hists_to_evsel(he->hists); trace_seq_init(&seq); - if (symbol_conf.raw_trace) { - tep_print_fields(&seq, he->raw_data, he->raw_size, - evsel->tp_format); - } else { - tep_print_event(evsel->tp_format->tep, - &seq, &rec, "%s", TEP_PRINT_INFO); + tp_format = evsel__tp_format(evsel); + if (tp_format) { + if (symbol_conf.raw_trace) + tep_print_fields(&seq, he->raw_data, he->raw_size, tp_format); + else + tep_print_event(tp_format->tep, &seq, &rec, "%s", TEP_PRINT_INFO); } + /* * Trim the buffer, it starts at 4KB and we're not going to * add anything more to this buffer. @@ -3293,9 +3295,8 @@ static int __dynamic_dimension__add(struct evsel *evsel, static int add_evsel_fields(struct evsel *evsel, bool raw_trace, int level) { int ret; - struct tep_format_field *field; - - field = evsel->tp_format->format.fields; + struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_format_field *field = tp_format ? tp_format->format.fields : NULL; while (field) { ret = __dynamic_dimension__add(evsel, field, raw_trace, level); if (ret < 0) @@ -3328,13 +3329,19 @@ static int add_all_matching_fields(struct evlist *evlist, { int ret = -ESRCH; struct evsel *evsel; - struct tep_format_field *field; evlist__for_each_entry(evlist, evsel) { + struct tep_event *tp_format; + struct tep_format_field *field; + if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) continue; - field = tep_find_any_field(evsel->tp_format, field_name); + tp_format = evsel__tp_format(evsel); + if (tp_format == NULL) + continue; + + field = tep_find_any_field(tp_format, field_name); if (field == NULL) continue; @@ -3416,7 +3423,9 @@ static int add_dynamic_entry(struct evlist *evlist, const char *tok, if (!strcmp(field_name, "*")) { ret = add_evsel_fields(evsel, raw_trace, level); } else { - struct tep_format_field *field = tep_find_any_field(evsel->tp_format, field_name); + struct tep_event *tp_format = evsel__tp_format(evsel); + struct tep_format_field *field = + tp_format ? tep_find_any_field(tp_format, field_name) : NULL; if (field == NULL) { pr_debug("Cannot find event field for %s.%s\n", diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index a5d72f4a515c..ba79f73e1cf5 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -115,14 +115,29 @@ static void print_running_csv(struct perf_stat_config *config, u64 run, u64 ena) config->csv_sep, run, config->csv_sep, enabled_percent); } struct outstate { - FILE *fh; + /* Std mode: insert a newline before the next metric */ bool newline; + /* JSON mode: track need for comma for a previous field or not */ bool first; - const char *prefix; - int nfields; - int aggr_nr; + /* Num CSV separators remaining to pad out when not all fields are printed */ + int csv_col_pad; + + /* + * The following don't track state across fields, but are here as a shortcut to + * pass data to the print functions. The alternative would be to update the + * function signatures of the entire print stack to pass them through. + */ + /* Place to output to */ + FILE * const fh; + /* Lines are timestamped in --interval-print mode */ + char timestamp[64]; + /* Num items aggregated in current line. See struct perf_stat_aggr.nr */ + int aggr_nr; + /* Core/socket/die etc ID for the current line */ struct aggr_cpu_id id; + /* Event for current line */ struct evsel *evsel; + /* Cgroup for current line */ struct cgroup *cgrp; }; @@ -419,8 +434,8 @@ static inline void __new_line_std_csv(struct perf_stat_config *config, struct outstate *os) { fputc('\n', os->fh); - if (os->prefix) - fputs(os->prefix, os->fh); + if (config->interval) + fputs(os->timestamp, os->fh); aggr_printout(config, os, os->evsel, os->id, os->aggr_nr); } @@ -472,7 +487,7 @@ static void new_line_csv(struct perf_stat_config *config, void *ctx) int i; __new_line_std_csv(config, os); - for (i = 0; i < os->nfields; i++) + for (i = 0; i < os->csv_col_pad; i++) fputs(config->csv_sep, os->fh); } @@ -523,8 +538,8 @@ static void new_line_json(struct perf_stat_config *config, void *ctx) fputs("\n{", os->fh); os->first = true; - if (os->prefix) - json_out(os, "%s", os->prefix); + if (config->interval) + json_out(os, "%s", os->timestamp); aggr_printout(config, os, os->evsel, os->id, os->aggr_nr); } @@ -549,12 +564,12 @@ static void print_metricgroup_header_csv(struct perf_stat_config *config, if (!metricgroup_name) { /* Leave space for running and enabling */ - for (i = 0; i < os->nfields - 2; i++) + for (i = 0; i < os->csv_col_pad - 2; i++) fputs(config->csv_sep, os->fh); return; } - for (i = 0; i < os->nfields; i++) + for (i = 0; i < os->csv_col_pad; i++) fputs(config->csv_sep, os->fh); fprintf(config->output, "%s", metricgroup_name); new_line_csv(config, ctx); @@ -673,11 +688,6 @@ static void print_metric_only_json(struct perf_stat_config *config __maybe_unuse json_out(os, "\"%s\" : \"%s\"", unit, vals); } -static void new_line_metric(struct perf_stat_config *config __maybe_unused, - void *ctx __maybe_unused) -{ -} - static void print_metric_header(struct perf_stat_config *config, void *ctx, enum metric_threshold_classify thresh __maybe_unused, @@ -839,22 +849,23 @@ static void printout(struct perf_stat_config *config, struct outstate *os, if (config->csv_output) { pm = config->metric_only ? print_metric_only_csv : print_metric_csv; - nl = config->metric_only ? new_line_metric : new_line_csv; + nl = config->metric_only ? NULL : new_line_csv; pmh = print_metricgroup_header_csv; - os->nfields = 4 + (counter->cgrp ? 1 : 0); + os->csv_col_pad = 4 + (counter->cgrp ? 1 : 0); } else if (config->json_output) { pm = config->metric_only ? print_metric_only_json : print_metric_json; - nl = config->metric_only ? new_line_metric : new_line_json; + nl = config->metric_only ? NULL : new_line_json; pmh = print_metricgroup_header_json; } else { pm = config->metric_only ? print_metric_only : print_metric_std; - nl = config->metric_only ? new_line_metric : new_line_std; + nl = config->metric_only ? NULL : new_line_std; pmh = print_metricgroup_header_std; } if (run == 0 || ena == 0 || counter->counts->scaled == -1) { if (config->metric_only) { - pm(config, os, METRIC_THRESHOLD_UNKNOWN, "", "", 0); + pm(config, os, METRIC_THRESHOLD_UNKNOWN, /*format=*/NULL, + /*unit=*/NULL, /*val=*/0); return; } @@ -909,7 +920,7 @@ static void printout(struct perf_stat_config *config, struct outstate *os, perf_stat__print_shadow_stats(config, counter, uval, aggr_idx, &out, &config->metric_events); } else { - pm(config, os, METRIC_THRESHOLD_UNKNOWN, /*format=*/NULL, /*unit=*/"", /*val=*/0); + pm(config, os, METRIC_THRESHOLD_UNKNOWN, /*format=*/NULL, /*unit=*/NULL, /*val=*/0); } if (!config->metric_only) { @@ -1095,13 +1106,13 @@ static void print_counter_aggrdata(struct perf_stat_config *config, os->first = true; fputc('{', output); } - if (os->prefix) { + if (config->interval) { if (config->json_output) - json_out(os, "%s", os->prefix); + json_out(os, "%s", os->timestamp); else - fprintf(output, "%s", os->prefix); + fprintf(output, "%s", os->timestamp); } else if (config->summary && config->csv_output && - !config->no_csv_summary && !config->interval) + !config->no_csv_summary) fprintf(output, "%s%s", "summary", config->csv_sep); } @@ -1128,11 +1139,11 @@ static void print_metric_begin(struct perf_stat_config *config, if (config->json_output) fputc('{', config->output); - if (os->prefix) { + if (config->interval) { if (config->json_output) - json_out(os, "%s", os->prefix); + json_out(os, "%s", os->timestamp); else - fprintf(config->output, "%s", os->prefix); + fprintf(config->output, "%s", os->timestamp); } evsel = evlist__first(evlist); id = config->aggr_map->map[aggr_idx]; @@ -1318,7 +1329,7 @@ static void print_metric_headers(struct perf_stat_config *config, struct perf_stat_output_ctx out = { .ctx = &os, .print_metric = print_metric_header, - .new_line = new_line_metric, + .new_line = NULL, .force_header = true, }; @@ -1353,20 +1364,20 @@ static void print_metric_headers(struct perf_stat_config *config, fputc('\n', config->output); } -static void prepare_interval(struct perf_stat_config *config, - char *prefix, size_t len, struct timespec *ts) +static void prepare_timestamp(struct perf_stat_config *config, + struct outstate *os, struct timespec *ts) { if (config->iostat_run) return; if (config->json_output) - scnprintf(prefix, len, "\"interval\" : %lu.%09lu", + scnprintf(os->timestamp, sizeof(os->timestamp), "\"interval\" : %lu.%09lu", (unsigned long) ts->tv_sec, ts->tv_nsec); else if (config->csv_output) - scnprintf(prefix, len, "%lu.%09lu%s", + scnprintf(os->timestamp, sizeof(os->timestamp), "%lu.%09lu%s", (unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep); else - scnprintf(prefix, len, "%6lu.%09lu ", + scnprintf(os->timestamp, sizeof(os->timestamp), "%6lu.%09lu ", (unsigned long) ts->tv_sec, ts->tv_nsec); } @@ -1689,9 +1700,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf int argc, const char **argv) { bool metric_only = config->metric_only; - int interval = config->interval; struct evsel *counter; - char buf[64]; struct outstate os = { .fh = config->output, .first = true, @@ -1702,10 +1711,8 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf if (config->iostat_run) evlist->selected = evlist__first(evlist); - if (interval) { - os.prefix = buf; - prepare_interval(config, buf, sizeof(buf), ts); - } + if (config->interval) + prepare_timestamp(config, &os, ts); print_header(config, _target, evlist, argc, argv); @@ -1724,7 +1731,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf case AGGR_THREAD: case AGGR_GLOBAL: if (config->iostat_run) { - iostat_print_counters(evlist, config, ts, buf, + iostat_print_counters(evlist, config, ts, os.timestamp, (iostat_print_counter_t)print_counter, &os); } else if (config->cgroup_list) { print_cgroup_counter(config, evlist, &os); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 47718610d5d8..d83bda5824d2 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -151,6 +151,7 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type { struct evsel *cur; int evsel_ctx = evsel_context(evsel); + struct perf_pmu *evsel_pmu = evsel__find_pmu(evsel); evlist__for_each_entry(evsel->evlist, cur) { struct perf_stat_aggr *aggr; @@ -177,7 +178,7 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type * Except the SW CLOCK events, * ignore if not the PMU we're looking for. */ - if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu)) + if ((type != STAT_NSECS) && (evsel_pmu != evsel__find_pmu(cur))) continue; aggr = &cur->stats->aggr[aggr_idx]; @@ -327,7 +328,8 @@ static void print_instructions(struct perf_stat_config *config, "insn per cycle", 0); } if (max_stalled && instructions) { - out->new_line(config, ctxp); + if (out->new_line) + out->new_line(config, ctxp); print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN, "%7.2f ", "stalled cycles per insn", max_stalled / instructions); } @@ -670,7 +672,7 @@ void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config, } } - if ((*num)++ > 0) + if ((*num)++ > 0 && out->new_line) out->new_line(config, ctxp); generic_metric(config, mexp, evsel, aggr_idx, out); } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 7c2ccdcc3fdb..1f7abd8754c7 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -535,7 +535,10 @@ static int evsel__merge_aggr_counters(struct evsel *evsel, struct evsel *alias) return 0; } -/* events should have the same name, scale, unit, cgroup but on different PMUs */ +/* + * Events should have the same name, scale, unit, cgroup but on different core + * PMUs or on different but matching uncore PMUs. + */ static bool evsel__is_alias(struct evsel *evsel_a, struct evsel *evsel_b) { if (strcmp(evsel__name(evsel_a), evsel__name(evsel_b))) @@ -553,7 +556,13 @@ static bool evsel__is_alias(struct evsel *evsel_a, struct evsel *evsel_b) if (evsel__is_clock(evsel_a) != evsel__is_clock(evsel_b)) return false; - return evsel_a->pmu != evsel_b->pmu; + if (evsel_a->pmu == evsel_b->pmu || evsel_a->pmu == NULL || evsel_b->pmu == NULL) + return false; + + if (evsel_a->pmu->is_core) + return evsel_b->pmu->is_core; + + return perf_pmu__name_no_suffix_match(evsel_a->pmu, evsel_b->pmu->name); } static void evsel__merge_aliases(struct evsel *evsel) diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 6f8cff3cd39a..2fda9acd7374 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -117,8 +117,9 @@ struct perf_stat_config { unsigned int topdown_level; }; +extern struct perf_stat_config stat_config; + void perf_stat__set_big_num(int set); -void perf_stat__set_no_csv_summary(int set); void update_stats(struct stats *stats, u64 val); double avg_stats(struct stats *stats); diff --git a/tools/perf/util/stream.c b/tools/perf/util/stream.c index 545e44981a27..3de4a6130853 100644 --- a/tools/perf/util/stream.c +++ b/tools/perf/util/stream.c @@ -52,7 +52,6 @@ static struct evlist_streams *evlist_streams__new(int nr_evsel, goto err; s->nr_streams_max = nr_streams_max; - s->evsel_idx = -1; } els->ev_streams = es; @@ -139,7 +138,7 @@ static int evlist__init_callchain_streams(struct evlist *evlist, hists__output_resort(hists, NULL); init_hot_callchain(hists, &es[i]); - es[i].evsel_idx = pos->core.idx; + es[i].evsel = pos; i++; } @@ -166,12 +165,12 @@ struct evlist_streams *evlist__create_streams(struct evlist *evlist, } struct evsel_streams *evsel_streams__entry(struct evlist_streams *els, - int evsel_idx) + const struct evsel *evsel) { struct evsel_streams *es = els->ev_streams; for (int i = 0; i < els->nr_evsel; i++) { - if (es[i].evsel_idx == evsel_idx) + if (es[i].evsel == evsel) return &es[i]; } diff --git a/tools/perf/util/stream.h b/tools/perf/util/stream.h index bee768874fea..50f7e6e04982 100644 --- a/tools/perf/util/stream.h +++ b/tools/perf/util/stream.h @@ -2,7 +2,9 @@ #ifndef __PERF_STREAM_H #define __PERF_STREAM_H -#include "callchain.h" +struct callchain_node; +struct evlist; +struct evsel; struct stream { struct callchain_node *cnode; @@ -11,9 +13,9 @@ struct stream { struct evsel_streams { struct stream *streams; + const struct evsel *evsel; int nr_streams_max; int nr_streams; - int evsel_idx; u64 streams_hits; }; @@ -22,15 +24,13 @@ struct evlist_streams { int nr_evsel; }; -struct evlist; - void evlist_streams__delete(struct evlist_streams *els); struct evlist_streams *evlist__create_streams(struct evlist *evlist, int nr_streams_max); struct evsel_streams *evsel_streams__entry(struct evlist_streams *els, - int evsel_idx); + const struct evsel *evsel); void evsel_streams__match(struct evsel_streams *es_base, struct evsel_streams *es_pair); diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index 308fc7ec88cc..c0e927bbadf6 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -254,11 +254,20 @@ char *strpbrk_esc(char *str, const char *stopset) do { ptr = strpbrk(str, stopset); - if (ptr == str || - (ptr == str + 1 && *(ptr - 1) != '\\')) + if (!ptr) { + /* stopset not in str. */ break; + } + if (ptr == str) { + /* stopset character is first in str. */ + break; + } + if (ptr == str + 1 && str[0] != '\\') { + /* stopset chacter is second and wasn't preceded by a '\'. */ + break; + } str = ptr + 1; - } while (ptr && *(ptr - 1) == '\\' && *(ptr - 2) != '\\'); + } while (ptr[-1] == '\\' && ptr[-2] != '\\'); return ptr; } diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 2b04f47f4db0..b1d259f590e9 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -21,6 +21,7 @@ #include <perf/cpumap.h> #include "env.h" +#include "perf.h" #include "svghelper.h" static u64 first_time, last_time; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index e398abfd13a0..66fd1249660a 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -287,8 +287,9 @@ static bool want_demangle(bool is_kernel_sym) * Demangle C++ function signature, typically replaced by demangle-cxx.cpp * version. */ -__weak char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused, - bool modifiers __maybe_unused) +#ifndef HAVE_CXA_DEMANGLE_SUPPORT +char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused, + bool modifiers __maybe_unused) { #ifdef HAVE_LIBBFD_SUPPORT int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); @@ -302,6 +303,7 @@ __weak char *cxx_demangle_sym(const char *str __maybe_unused, bool params __mayb return NULL; #endif } +#endif /* !HAVE_CXA_DEMANGLE_SUPPORT */ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) { diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index a58444c4aed1..6923b0d5efed 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -1686,12 +1686,16 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo } if (type & PERF_SAMPLE_RAW) { - u.val32[0] = sample->raw_size; - *array = u.val64; - array = (void *)array + sizeof(u32); + u32 *array32 = (void *)array; + + *array32 = sample->raw_size; + array32++; + + memcpy(array32, sample->raw_data, sample->raw_size); + array = (void *)(array32 + (sample->raw_size / sizeof(u32))); - memcpy(array, sample->raw_data, sample->raw_size); - array = (void *)array + sample->raw_size; + /* make sure the array is 64-bit aligned */ + BUG_ON(((long)array) % sizeof(u64)); } if (type & PERF_SAMPLE_BRANCH_STACK) { diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 69d8dcf5cf28..928aca4cd6e9 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -10,52 +10,12 @@ #include <linux/compiler.h> #include <linux/zalloc.h> -#ifdef HAVE_SYSCALL_TABLE_SUPPORT #include <string.h> #include "string2.h" -#if defined(__x86_64__) -#include <asm/syscalls_64.c> -const int syscalltbl_native_max_id = SYSCALLTBL_x86_64_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_x86_64; -#elif defined(__i386__) -#include <asm/syscalls_32.c> -const int syscalltbl_native_max_id = SYSCALLTBL_x86_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_x86; -#elif defined(__s390x__) -#include <asm/syscalls_64.c> -const int syscalltbl_native_max_id = SYSCALLTBL_S390_64_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_s390_64; -#elif defined(__powerpc64__) -#include <asm/syscalls_64.c> -const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_64_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_powerpc_64; -#elif defined(__powerpc__) -#include <asm/syscalls_32.c> -const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_powerpc_32; -#elif defined(__aarch64__) -#include <asm/syscalls.c> -const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_arm64; -#elif defined(__mips__) -#include <asm/syscalls_n64.c> -const int syscalltbl_native_max_id = SYSCALLTBL_MIPS_N64_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_mips_n64; -#elif defined(__loongarch__) -#include <asm/syscalls.c> -const int syscalltbl_native_max_id = SYSCALLTBL_LOONGARCH_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_loongarch; -#elif defined(__riscv) -#include <asm/syscalls.c> -const int syscalltbl_native_max_id = SYSCALLTBL_RISCV_MAX_ID; -static const char *const *syscalltbl_native = syscalltbl_riscv; -#else -const int syscalltbl_native_max_id = 0; -static const char *const syscalltbl_native[] = { - [0] = "unknown", -}; -#endif +#include <syscall_table.h> +const int syscalltbl_native_max_id = SYSCALLTBL_MAX_ID; +static const char *const *syscalltbl_native = syscalltbl; struct syscall { int id; @@ -163,47 +123,3 @@ int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_g *idx = -1; return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx); } - -#else /* HAVE_SYSCALL_TABLE_SUPPORT */ - -#include <libaudit.h> - -struct syscalltbl *syscalltbl__new(void) -{ - struct syscalltbl *tbl = zalloc(sizeof(*tbl)); - if (tbl) - tbl->audit_machine = audit_detect_machine(); - return tbl; -} - -void syscalltbl__delete(struct syscalltbl *tbl) -{ - free(tbl); -} - -const char *syscalltbl__name(const struct syscalltbl *tbl, int id) -{ - return audit_syscall_to_name(id, tbl->audit_machine); -} - -int syscalltbl__id(struct syscalltbl *tbl, const char *name) -{ - return audit_name_to_syscall(name, tbl->audit_machine); -} - -int syscalltbl__id_at_idx(struct syscalltbl *tbl __maybe_unused, int idx) -{ - return idx; -} - -int syscalltbl__strglobmatch_next(struct syscalltbl *tbl __maybe_unused, - const char *syscall_glob __maybe_unused, int *idx __maybe_unused) -{ - return -1; -} - -int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx) -{ - return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx); -} -#endif /* HAVE_SYSCALL_TABLE_SUPPORT */ diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h index 2b53b7ed25a6..362411a6d849 100644 --- a/tools/perf/util/syscalltbl.h +++ b/tools/perf/util/syscalltbl.h @@ -3,7 +3,6 @@ #define __PERF_SYSCALLTBL_H struct syscalltbl { - int audit_machine; struct { int max_id; int nr_entries; diff --git a/tools/perf/util/tool_pmu.c b/tools/perf/util/tool_pmu.c index 4fb097578479..d43d6cf6e4a2 100644 --- a/tools/perf/util/tool_pmu.c +++ b/tools/perf/util/tool_pmu.c @@ -62,7 +62,8 @@ int tool_pmu__num_skip_events(void) const char *tool_pmu__event_to_str(enum tool_pmu_event ev) { - if (ev > TOOL_PMU__EVENT_NONE && ev < TOOL_PMU__EVENT_MAX) + if ((ev > TOOL_PMU__EVENT_NONE && ev < TOOL_PMU__EVENT_MAX) && + !tool_pmu__skip_event(tool_pmu__event_names[ev])) return tool_pmu__event_names[ev]; return NULL; @@ -489,17 +490,24 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) return 0; } -struct perf_pmu *perf_pmus__tool_pmu(void) +struct perf_pmu *tool_pmu__new(void) { - static struct perf_pmu tool = { - .name = "tool", - .type = PERF_PMU_TYPE_TOOL, - .aliases = LIST_HEAD_INIT(tool.aliases), - .caps = LIST_HEAD_INIT(tool.caps), - .format = LIST_HEAD_INIT(tool.format), - }; - if (!tool.events_table) - tool.events_table = find_core_events_table("common", "common"); - - return &tool; + struct perf_pmu *tool = zalloc(sizeof(struct perf_pmu)); + + if (!tool) + goto out; + tool->name = strdup("tool"); + if (!tool->name) { + zfree(&tool); + goto out; + } + + tool->type = PERF_PMU_TYPE_TOOL; + INIT_LIST_HEAD(&tool->aliases); + INIT_LIST_HEAD(&tool->caps); + INIT_LIST_HEAD(&tool->format); + tool->events_table = find_core_events_table("common", "common"); + +out: + return tool; } diff --git a/tools/perf/util/tool_pmu.h b/tools/perf/util/tool_pmu.h index a60184859080..c6ad1dd90a56 100644 --- a/tools/perf/util/tool_pmu.h +++ b/tools/perf/util/tool_pmu.h @@ -51,6 +51,6 @@ int evsel__tool_pmu_open(struct evsel *evsel, int start_cpu_map_idx, int end_cpu_map_idx); int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread); -struct perf_pmu *perf_pmus__tool_pmu(void); +struct perf_pmu *tool_pmu__new(void); #endif /* __TOOL_PMU_H */ diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 41d53e1b43e7..9c015fc2bcfb 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -99,7 +99,7 @@ unsigned long long read_size(struct tep_event *event, void *ptr, int size) return tep_read_number(event->tep, ptr, size); } -void event_format__fprintf(struct tep_event *event, +void event_format__fprintf(const struct tep_event *event, int cpu, void *data, int size, FILE *fp) { struct tep_record record; diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 5596fcda2c10..4e81e02a4f18 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -13,14 +13,94 @@ #include <event-parse.h> #endif +#include "archinsn.h" #include "debug.h" +#include "event.h" #include "trace-event.h" #include "evsel.h" +#include <linux/perf_event.h> #include <linux/zalloc.h> #include "util/sample.h" +unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; + struct scripting_context *scripting_context; +struct script_spec { + struct list_head node; + struct scripting_ops *ops; + char spec[]; +}; + +static LIST_HEAD(script_specs); + +static struct script_spec *script_spec__new(const char *spec, + struct scripting_ops *ops) +{ + struct script_spec *s = malloc(sizeof(*s) + strlen(spec) + 1); + + if (s != NULL) { + strcpy(s->spec, spec); + s->ops = ops; + } + + return s; +} + +static void script_spec__add(struct script_spec *s) +{ + list_add_tail(&s->node, &script_specs); +} + +static struct script_spec *script_spec__find(const char *spec) +{ + struct script_spec *s; + + list_for_each_entry(s, &script_specs, node) + if (strcasecmp(s->spec, spec) == 0) + return s; + return NULL; +} + +static int script_spec_register(const char *spec, struct scripting_ops *ops) +{ + struct script_spec *s; + + s = script_spec__find(spec); + if (s) + return -1; + + s = script_spec__new(spec, ops); + if (!s) + return -1; + + script_spec__add(s); + return 0; +} + +struct scripting_ops *script_spec__lookup(const char *spec) +{ + struct script_spec *s = script_spec__find(spec); + + if (!s) + return NULL; + + return s->ops; +} + +int script_spec__for_each(int (*cb)(struct scripting_ops *ops, const char *spec)) +{ + struct script_spec *s; + int ret = 0; + + list_for_each_entry(s, &script_specs, node) { + ret = cb(s->ops, s->spec); + if (ret) + break; + } + return ret; +} + void scripting_context__update(struct scripting_context *c, union perf_event *event, struct perf_sample *sample, @@ -28,12 +108,14 @@ void scripting_context__update(struct scripting_context *c, struct addr_location *al, struct addr_location *addr_al) { - c->event_data = sample->raw_data; - c->pevent = NULL; #ifdef HAVE_LIBTRACEEVENT - if (evsel->tp_format) - c->pevent = evsel->tp_format->tep; + const struct tep_event *tp_format = evsel__tp_format(evsel); + + c->pevent = tp_format ? tp_format->tep : NULL; +#else + c->pevent = NULL; #endif + c->event_data = sample->raw_data; c->event = event; c->sample = sample; c->evsel = evsel; @@ -191,3 +273,100 @@ void setup_perl_scripting(void) } #endif #endif + +#if !defined(__i386__) && !defined(__x86_64__) +void arch_fetch_insn(struct perf_sample *sample __maybe_unused, + struct thread *thread __maybe_unused, + struct machine *machine __maybe_unused) +{ +} +#endif + +void script_fetch_insn(struct perf_sample *sample, struct thread *thread, + struct machine *machine, bool native_arch) +{ + if (sample->insn_len == 0 && native_arch) + arch_fetch_insn(sample, thread, machine); +} + +static const struct { + u32 flags; + const char *name; +} sample_flags[] = { + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "jcc"}, + {PERF_IP_FLAG_BRANCH, "jmp"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT, "int"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT, "iret"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET, "syscall"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET, "sysret"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "async"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_INTERRUPT, + "hw int"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "tx abrt"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "tr strt"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMENTRY, "vmentry"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_VMEXIT, "vmexit"}, + {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_BRANCH_MISS, "br miss"}, + {0, NULL} +}; + +static const char *sample_flags_to_name(u32 flags) +{ + int i; + + for (i = 0; sample_flags[i].name ; i++) { + if (sample_flags[i].flags == flags) + return sample_flags[i].name; + } + + return NULL; +} + +int perf_sample__sprintf_flags(u32 flags, char *str, size_t sz) +{ + u32 xf = PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_INTR_DISABLE | + PERF_IP_FLAG_INTR_TOGGLE; + const char *chars = PERF_IP_FLAG_CHARS; + const size_t n = strlen(PERF_IP_FLAG_CHARS); + const char *name = NULL; + size_t i, pos = 0; + char xs[16] = {0}; + + if (flags & xf) + snprintf(xs, sizeof(xs), "(%s%s%s)", + flags & PERF_IP_FLAG_IN_TX ? "x" : "", + flags & PERF_IP_FLAG_INTR_DISABLE ? "D" : "", + flags & PERF_IP_FLAG_INTR_TOGGLE ? "t" : ""); + + name = sample_flags_to_name(flags & ~xf); + if (name) + return snprintf(str, sz, "%-15s%6s", name, xs); + + if (flags & PERF_IP_FLAG_TRACE_BEGIN) { + name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_BEGIN)); + if (name) + return snprintf(str, sz, "tr strt %-7s%6s", name, xs); + } + + if (flags & PERF_IP_FLAG_TRACE_END) { + name = sample_flags_to_name(flags & ~(xf | PERF_IP_FLAG_TRACE_END)); + if (name) + return snprintf(str, sz, "tr end %-7s%6s", name, xs); + } + + for (i = 0; i < n; i++, flags >>= 1) { + if ((flags & 1) && pos < sz) + str[pos++] = chars[i]; + } + for (; i < 32; i++, flags >>= 1) { + if ((flags & 1) && pos < sz) + str[pos++] = '?'; + } + if (pos < sz) + str[pos] = 0; + + return pos; +} diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 79b939f947dd..ac9fde2f980c 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -39,7 +39,7 @@ trace_event__tp_format(const char *sys, const char *name); struct tep_event *trace_event__tp_format_id(int id); -void event_format__fprintf(struct tep_event *event, +void event_format__fprintf(const struct tep_event *event, int cpu, void *data, int size, FILE *fp); int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size); @@ -113,10 +113,11 @@ struct scripting_ops { extern unsigned int scripting_max_stack; -int script_spec_register(const char *spec, struct scripting_ops *ops); +struct scripting_ops *script_spec__lookup(const char *spec); +int script_spec__for_each(int (*cb)(struct scripting_ops *ops, const char *spec)); void script_fetch_insn(struct perf_sample *sample, struct thread *thread, - struct machine *machine); + struct machine *machine, bool native_arch); void setup_perl_scripting(void); void setup_python_scripting(void); diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c index 32c39cfe209b..4c6a86e1cb54 100644 --- a/tools/perf/util/units.c +++ b/tools/perf/util/units.c @@ -64,7 +64,7 @@ unsigned long convert_unit(unsigned long value, char *unit) int unit_number__scnprintf(char *buf, size_t size, u64 n) { - char unit[4] = "BKMG"; + char unit[] = "BKMG"; int i = 0; while (((n / 1024) > 1) && (i < 3)) { diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index b9823f414f10..ec72d29f3d58 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -8,6 +8,7 @@ #include "values.h" #include "debug.h" +#include "evsel.h" int perf_read_values_init(struct perf_read_values *values) { @@ -22,21 +23,17 @@ int perf_read_values_init(struct perf_read_values *values) values->threads = 0; values->counters_max = 16; - values->counterrawid = malloc(values->counters_max - * sizeof(*values->counterrawid)); - values->countername = malloc(values->counters_max - * sizeof(*values->countername)); - if (!values->counterrawid || !values->countername) { - pr_debug("failed to allocate read_values counters arrays"); + values->counters = malloc(values->counters_max * sizeof(*values->counters)); + if (!values->counters) { + pr_debug("failed to allocate read_values counters array"); goto out_free_counter; } - values->counters = 0; + values->num_counters = 0; return 0; out_free_counter: - zfree(&values->counterrawid); - zfree(&values->countername); + zfree(&values->counters); out_free_pid: zfree(&values->pid); zfree(&values->tid); @@ -56,10 +53,7 @@ void perf_read_values_destroy(struct perf_read_values *values) zfree(&values->value); zfree(&values->pid); zfree(&values->tid); - zfree(&values->counterrawid); - for (i = 0; i < values->counters; i++) - zfree(&values->countername[i]); - zfree(&values->countername); + zfree(&values->counters); } static int perf_read_values__enlarge_threads(struct perf_read_values *values) @@ -116,81 +110,71 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values, static int perf_read_values__enlarge_counters(struct perf_read_values *values) { - char **countername; - int i, counters_max = values->counters_max * 2; - u64 *counterrawid = realloc(values->counterrawid, counters_max * sizeof(*values->counterrawid)); + int counters_max = values->counters_max * 2; + struct evsel **new_counters = realloc(values->counters, + counters_max * sizeof(*values->counters)); - if (!counterrawid) { - pr_debug("failed to enlarge read_values rawid array"); + if (!new_counters) { + pr_debug("failed to enlarge read_values counters array"); goto out_enomem; } - 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++) { + for (int i = 0; i < values->threads; i++) { u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value)); - int j; if (!value) { pr_debug("failed to enlarge read_values ->values array"); - goto out_free_name; + goto out_free_counters; } - for (j = values->counters_max; j < counters_max; j++) + for (int j = values->counters_max; j < counters_max; j++) value[j] = 0; values->value[i] = value; } values->counters_max = counters_max; - values->counterrawid = counterrawid; - values->countername = countername; + values->counters = new_counters; return 0; -out_free_name: - free(countername); -out_free_rawid: - free(counterrawid); +out_free_counters: + free(new_counters); out_enomem: return -ENOMEM; } static int perf_read_values__findnew_counter(struct perf_read_values *values, - u64 rawid, const char *name) + struct evsel *evsel) { int i; - for (i = 0; i < values->counters; i++) - if (values->counterrawid[i] == rawid) + for (i = 0; i < values->num_counters; i++) + if (values->counters[i] == evsel) return i; - if (values->counters == values->counters_max) { - i = perf_read_values__enlarge_counters(values); - if (i) - return i; + if (values->num_counters == values->counters_max) { + int err = perf_read_values__enlarge_counters(values); + + if (err) + return err; } - i = values->counters++; - values->counterrawid[i] = rawid; - values->countername[i] = strdup(name); + i = values->num_counters++; + values->counters[i] = evsel; return i; } int perf_read_values_add_value(struct perf_read_values *values, u32 pid, u32 tid, - u64 rawid, const char *name, u64 value) + struct evsel *evsel, u64 value) { int tindex, cindex; tindex = perf_read_values__findnew_thread(values, pid, tid); if (tindex < 0) return tindex; - cindex = perf_read_values__findnew_counter(values, rawid, name); + cindex = perf_read_values__findnew_counter(values, evsel); if (cindex < 0) return cindex; @@ -205,15 +189,15 @@ static void perf_read_values__display_pretty(FILE *fp, int pidwidth, tidwidth; int *counterwidth; - counterwidth = malloc(values->counters * sizeof(*counterwidth)); + counterwidth = malloc(values->num_counters * sizeof(*counterwidth)); if (!counterwidth) { fprintf(fp, "INTERNAL ERROR: Failed to allocate counterwidth array\n"); return; } tidwidth = 3; pidwidth = 3; - for (j = 0; j < values->counters; j++) - counterwidth[j] = strlen(values->countername[j]); + for (j = 0; j < values->num_counters; j++) + counterwidth[j] = strlen(evsel__name(values->counters[j])); for (i = 0; i < values->threads; i++) { int width; @@ -223,7 +207,7 @@ static void perf_read_values__display_pretty(FILE *fp, width = snprintf(NULL, 0, "%d", values->tid[i]); if (width > tidwidth) tidwidth = width; - for (j = 0; j < values->counters; j++) { + for (j = 0; j < values->num_counters; j++) { width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]); if (width > counterwidth[j]) counterwidth[j] = width; @@ -231,14 +215,14 @@ static void perf_read_values__display_pretty(FILE *fp, } fprintf(fp, "# %*s %*s", pidwidth, "PID", tidwidth, "TID"); - for (j = 0; j < values->counters; j++) - fprintf(fp, " %*s", counterwidth[j], values->countername[j]); + for (j = 0; j < values->num_counters; j++) + fprintf(fp, " %*s", counterwidth[j], evsel__name(values->counters[j])); fprintf(fp, "\n"); for (i = 0; i < values->threads; i++) { fprintf(fp, " %*d %*d", pidwidth, values->pid[i], tidwidth, values->tid[i]); - for (j = 0; j < values->counters; j++) + for (j = 0; j < values->num_counters; j++) fprintf(fp, " %*" PRIu64, counterwidth[j], values->value[i][j]); fprintf(fp, "\n"); @@ -266,16 +250,16 @@ static void perf_read_values__display_raw(FILE *fp, if (width > tidwidth) tidwidth = width; } - for (j = 0; j < values->counters; j++) { - width = strlen(values->countername[j]); + for (j = 0; j < values->num_counters; j++) { + width = strlen(evsel__name(values->counters[j])); if (width > namewidth) namewidth = width; - width = snprintf(NULL, 0, "%" PRIx64, values->counterrawid[j]); + width = snprintf(NULL, 0, "%x", values->counters[j]->core.idx); if (width > rawwidth) rawwidth = width; } for (i = 0; i < values->threads; i++) { - for (j = 0; j < values->counters; j++) { + for (j = 0; j < values->num_counters; j++) { width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]); if (width > countwidth) countwidth = width; @@ -287,12 +271,12 @@ static void perf_read_values__display_raw(FILE *fp, namewidth, "Name", rawwidth, "Raw", countwidth, "Count"); for (i = 0; i < values->threads; i++) - for (j = 0; j < values->counters; j++) - fprintf(fp, " %*d %*d %*s %*" PRIx64 " %*" PRIu64, + for (j = 0; j < values->num_counters; j++) + fprintf(fp, " %*d %*d %*s %*x %*" PRIu64, pidwidth, values->pid[i], tidwidth, values->tid[i], - namewidth, values->countername[j], - rawwidth, values->counterrawid[j], + namewidth, evsel__name(values->counters[j]), + rawwidth, values->counters[j]->core.idx, countwidth, values->value[i][j]); } diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h index 791c1ad606c2..bbca33daca19 100644 --- a/tools/perf/util/values.h +++ b/tools/perf/util/values.h @@ -5,14 +5,15 @@ #include <stdio.h> #include <linux/types.h> +struct evsel; + struct perf_read_values { int threads; int threads_max; u32 *pid, *tid; - int counters; + int num_counters; int counters_max; - u64 *counterrawid; - char **countername; + struct evsel **counters; u64 **value; }; @@ -21,7 +22,7 @@ void perf_read_values_destroy(struct perf_read_values *values); int perf_read_values_add_value(struct perf_read_values *values, u32 pid, u32 tid, - u64 rawid, const char *name, u64 value); + struct evsel *evsel, u64 value); void perf_read_values_display(FILE *fp, struct perf_read_values *values, int raw); |